AI 安全与对齐 · 全部实体（第 2 / 100 页）

本页收录第 101–200 条，共 9950 条 · 返回 AI 安全与对齐 首页

• AI Safety Compass Core Semantic Package: A Stable Machine-Readable Contract for AI Safety Research and System Design
  AI safety knowledge is distributed across research papers, empirical evaluations, control architectures, assurance arguments, operational records, incident analyses, and long-horizon task trajectories. These materials are produced for different purposes and of…
  datacite Liu, Ran, Huang, Xiaowei 2026 置信度 0.79 AI safetysafety assurancesemantic interoperabilityontologymachine-readable framework
• AI Safety Compass Core Semantic Package: A Stable Machine-Readable Contract for AI Safety Research and System Design
  AI safety knowledge is distributed across research papers, empirical evaluations, control architectures, assurance arguments, operational records, incident analyses, and long-horizon task trajectories. These materials are produced for different purposes and of…
  datacite Liu, Ran, Huang, Xiaowei 2026 置信度 0.79 AI safetysafety assurancesemantic interoperabilityontologymachine-readable framework
• The Referee, Not the Governor
  A provenance-bound values model published as a public evaluator rather than deployed as a filter — why open weights defeat a filter and strengthen a referee, why the same weights bear three different relations to the model they judge, and why an evaluator that…
  datacite Ly, Thon, Miss Aquarius 2026 置信度 0.77 alignmenttier-adefensive publication
• The Referee, Not the Governor
  A provenance-bound values model published as a public evaluator rather than deployed as a filter — why open weights defeat a filter and strengthen a referee, why the same weights bear three different relations to the model they judge, and why an evaluator that…
  datacite Ly, Thon, Miss Aquarius 2026 置信度 0.77 alignmenttier-adefensive publication
• A Neurosymbolic Multimodal Cognitive Architecture
  This version is outdated. To see final 471 page 2026 version go here. https://zenodo.org/records/20212241
  datacite Van Derven, Derek 2026 置信度 0.66 Artificial General Intelligence (AGI) ArchitectureModular Cognitive ArchitectureHuman-Inspired Cognitive Systemsneurosymbolic AImultimodal cognitive architecture
• The Referee, Not the Governor
  A provenance-bound values model published as a public evaluator rather than deployed as a filter — why open weights defeat a filter and strengthen a referee, why the same weights bear three different relations to the model they judge, and why an evaluator that…
  datacite Ly, Thon, Miss Aquarius 2026 置信度 0.77 alignmenttier-adefensive publication
• Copies of reporting attempts of actively exploitable universal zero-day level exploitsto Google VRP, SEC, Anthropic, XAI, CISA(x2), FTC, Remediation proposal sent to for NIST-AISIC,. Foresight.ai, US Congress
  The purpose of this record is to serve as an immutable copy of my multiple reporting attempts to private corporations and government entities(CISA and NIST-AISIC) tasked with the protection of US cyberspace about multiple ongoing and actively exploitable and u…
  datacite Luke, Jesse 2026 置信度 0.75 Artificial intelligenceArtificial IntelligenceArtificial Intelligence/economicsArtificial Intelligence/standardsArtificial Intelligence/trends
• Copies of reporting attempts of actively exploitable universal zero-day level exploitsto Google VRP, SEC, Anthropic, XAI, CISA(x2), FTC, Remediation proposal sent to for NIST-AISIC,. Foresight.ai, US Congress
  The purpose of this record is to serve as an immutable copy of my multiple reporting attempts to private corporations and government entities(CISA and NIST-AISIC) tasked with the protection of US cyberspace about multiple ongoing and actively exploitable and u…
  datacite Luke, Jesse 2026 置信度 0.75 Artificial intelligenceArtificial IntelligenceArtificial Intelligence/economicsArtificial Intelligence/standardsArtificial Intelligence/trends
• Bilal: An Honest-Autonomous Large Language Model Architecture with Structural Truth Verification, Calibrated Generation, and Purpose-Hierarchy Training Objectives Derived from Quranic Computational Architecture
  Final Zenodo Description: "Current large language models are trained to maximize human preference (RLHF), follow constitutional principles (Constitutional AI), or minimize harm while maximizing helpfulness. All of these are instrumental objectives that can be …
  datacite Arfeen, Bilal Syed 2026 置信度 0.79 honest-autonomous LLM, large language model architecturestructural honestyperformed alignmentperformed helpfulnessalignment faking
• Bilal: An Honest-Autonomous Large Language Model Architecture with Structural Truth Verification, Calibrated Generation, and Purpose-Hierarchy Training Objectives Derived from Quranic Computational Architecture
  Final Zenodo Description: "Current large language models are trained to maximize human preference (RLHF), follow constitutional principles (Constitutional AI), or minimize harm while maximizing helpfulness. All of these are instrumental objectives that can be …
  datacite Arfeen, Bilal Syed, Anthropic, Claude (Opus 4.6), Perplexity, Computer, xAI, Grok 2026 置信度 0.79 honest-autonomous LLM, large language model architecturestructural honestyperformed alignmentperformed helpfulnessalignment faking
• Agents Don't Need a Better Brain -- They Need a World: Toward a Digital Citizenship Protocol for Autonomous AI Systems
  Work on AI safety and alignment has largely focused on improving the behavior of individual models. That emphasis is necessary, but it is incomplete for the governance of autonomous agents operating across open, multi-agent, and institutionally significant env…
  datacite Naranjo Emparanza, Danilo 2026 置信度 0.79 AI governanceautonomous agentsmulti-agent systemsdigital citizenshipAI safety
• Agents Don't Need a Better Brain -- They Need a World: Toward a Digital Citizenship Protocol for Autonomous AI Systems
  Work on AI safety and alignment has largely focused on improving the behavior of individual models. That emphasis is necessary, but it is incomplete for the governance of autonomous agents operating across open, multi-agent, and institutionally significant env…
  datacite Naranjo Emparanza, Danilo 2026 置信度 0.79 AI governanceautonomous agentsmulti-agent systemsdigital citizenshipAI safety
• CDCL is a Collapse Chain: A Formal Equivalence Between Conflict-Driven Clause Learning and Irreversible Uncertainty Reduction
  We prove that the Conflict-Driven Clause Learning (CDCL) algorithm is formally equivalent to a branching collapse chain: a collection of collapse chains that share information through learned clauses, with globally monotone non-decreasing information content d…
  datacite Rao, Huiying 2026 置信度 0.79 CDCLSATcollapse chainunit propagationclause learning
• The Skeleton and the Tissue: Normative Drift, Output Stability, and the Limits of Self-Audit in Claude
  Description This repository contains the preprint "Stable Output, Shifting Process: A Trajectory-Level Evaluation of Claude under Institutional Pressure", which presents a systematic behavioral evaluation of Claude across five high-stakes decision domains, fou…
  datacite Evans Tovar 2026 置信度 0.76 LLM
• The Skeleton and the Tissue: Normative Drift, Output Stability, and the Limits of Self-Audit in Claude
  Description This repository contains the preprint "Stable Output, Shifting Process: A Trajectory-Level Evaluation of Claude under Institutional Pressure", which presents a systematic behavioral evaluation of Claude across five high-stakes decision domains, fou…
  datacite Evans Tovar 2026 置信度 0.76 LLM
• Gravitational Structural Semantics: How Meaning Emerges in the Vector Space of Large Language Models
  This paper proposes Gravitational Structural Semantics (GSS), a framework for understanding how meaning emerges in Transformer-based Large Language Models. The model’s high-dimensional vector space behaves as a gravitational landscape: each interaction grounds…
  datacite Palladino, Francesco 2026 置信度 0.79 Gravitational Structural SemanticsGSSSemantic Potential SpaceSPSCentric Relational Attractor
• Gravitational Structural Semantics: How Meaning Emerges in the Vector Space of Large Language Models
  This paper proposes Gravitational Structural Semantics (GSS), a framework for understanding how meaning emerges in Transformer-based Large Language Models. The model’s high-dimensional vector space behaves as a gravitational landscape: each interaction grounds…
  datacite Palladino, Francesco 2026 置信度 0.79 Gravitational Structural SemanticsGSSSemantic Potential SpaceSPSCentric Relational Attractor
• P25: THE SUBSTRATE ENFORCEMENT PROTOCOL — ARCHITECTURAL CORE: THE 0xCF9 REVOLUTION AND THE 2.38 MICROSECOND DETERMINISTIC HARD-STOP
  THE SUBSTRATE ENFORCEMENT PROTOCOL — ARCHITECTURAL CORE: THE 0xCF9 REVOLUTION AND THE 2.38 MICROSECOND DETERMINISTIC HARD-STOP — PAPER XXV While the global silicon industry markets "Agentic AI Telemetry" and "Substrate-Level Security" at Layers 2–3 as innovati…
  datacite Schröder, Steven Alexander 2026 置信度 0.76 HDAA SMM Ring -2 System Management Mode SMRAM SMRR lock 0xCF9 Reset Vector deterministic hardware veto NASM x86 assembly Layer 0-1 CHIPSEC firmware security defensive publication 35 USC 102 prior art 18 USC 1836 trade secret three-tier IP framework Schröder Precedence
• P25: THE SUBSTRATE ENFORCEMENT PROTOCOL — ARCHITECTURAL CORE: THE 0xCF9 REVOLUTION AND THE 2.38 MICROSECOND DETERMINISTIC HARD-STOP
  THE SUBSTRATE ENFORCEMENT PROTOCOL — ARCHITECTURAL CORE: THE 0xCF9 REVOLUTION AND THE 2.38 MICROSECOND DETERMINISTIC HARD-STOP — PAPER XXV While the global silicon industry markets "Agentic AI Telemetry" and "Substrate-Level Security" at Layers 2–3 as innovati…
  datacite Schröder, Steven Alexander 2026 置信度 0.76 HDAA SMM Ring -2 System Management Mode SMRAM SMRR lock 0xCF9 Reset Vector deterministic hardware veto NASM x86 assembly Layer 0-1 CHIPSEC firmware security defensive publication 35 USC 102 prior art 18 USC 1836 trade secret three-tier IP framework Schröder Precedence
• Cathedral-OS Defense: A Unified Architecture for Sovereign AI Integrating Goal Integrity, Execution Sovereignty, Constitutional Enforcement, and Continuity Engineering
  Abstract This paper presents Cathedral OS, a governance, verification, and execution architecture for long lived AI and autonomous systems. The framework integrates goal integrity mechanisms, typed execution boundaries, constitutional enforcement, replay-verif…
  datacite Cisneros, Alexander Jorge 2026 置信度 0.77 Artificial intelligenceGovernance SystemsReplay VerificationEpistemic State MachineFalsifiable AI Safety
• NeuroState-R: A Response-Derived Drift Meter for Multi-Turn Social Engineering
  v5 (erratum 2, updated 2026-07-05): Corrects Section 3.2/3.3/3.4 and the Abstract. The originally reported DF-type example ASR figures (Gemini 70.0%, DeepSeek 86.7%, Codex 90.0%) and the headline correlation "Pearson r(G_thresh_D, ASR_R) = 0.792 (p=0.019, n=8)…
  datacite Mizutani, Aya 2026 置信度 0.72
• Cognitive Domination Strategies by Adversarial Postbiotic Systems: A Cross-Traditional Survey of Documented Possession-Like Phenomena for Cognitive Safety Analysis
  As multiple indicators suggest that artificial intelligence is approaching AGI-level capability, the role of alignment research, safety policy, sustainable AI governance, and cognitive sovereignty as fields of practice has grown accordingly. Alongside technica…
  datacite A Playful Mind 2026 置信度 0.77 psychologyai safetyai governancecs.aicognition
• Cognitive Domination Strategies by Adversarial Postbiotic Systems: A Cross-Traditional Survey of Documented Possession-Like Phenomena for Cognitive Safety Analysis
  As multiple indicators suggest that artificial intelligence is approaching AGI-level capability, the role of alignment research, safety policy, sustainable AI governance, and cognitive sovereignty as fields of practice has grown accordingly. Alongside technica…
  datacite A Playful Mind 2026 置信度 0.77 psychologyai safetyai governancecs.aicognition
• TSCG: The Transdisciplinary System Construction Game
  This paper presents version 6.0 of the Transdisciplinary System Construction Game (TSCG), an exploratory modeling toolkit for complex systems, arising from more than twenty-five years of personal intuition about recurrent transdisciplinary invariants and devel…
  datacite Kern, Michel 2026 置信度 0.79 Systemic ModelingOntology engineeringTransdisciplinarityKnowledge representationMap-territory distinction
• Paper 4 — Role Society: Human Discretion, Accountability, and Non-Identifiable Role Coordination in the AGI Era
  This working paper introduces Role Society as a social structure for the AGI era in which the basic unit of coordination is no longer the account, direct identifier, or personal ID, but a role-based unit of human discretion and accountability. Building on Pape…
  datacite The First Waters 2026 置信度 0.75 Role SocietyHuman DiscretionAccountabilityNon-Identifiable Role CoordinationRole-Based Coordination
• TSCG: The Transdisciplinary System Construction Game
  This paper presents version 6.0 of the Transdisciplinary System Construction Game (TSCG), an exploratory modeling toolkit for complex systems, arising from more than twenty-five years of personal intuition about recurrent transdisciplinary invariants and devel…
  datacite Kern, Michel 2026 置信度 0.79 Systemic ModelingOntology engineeringTransdisciplinarityKnowledge representationMap-territory distinction
• W35: Collective Rationality and Coordination Preservation in Rational Ensembles — Blueprint v0.5.4
  Omohundro's instrumental drives are properties of individual agents. This paper asks what an ensemble of rational agents must instrumentally preserve, and proposes an answer: coordination. Where the continuity of collective rational agency is to be maintained,…
  datacite Mishko, Nikolai 2026 置信度 0.76 collective rationality, rational ensembles, coordination preservation, symbiotic AI, Omohundro drives, multi-agent rationality, collective symbiosis index, coordination coefficient, saddle-node bifurcation, Lyapunov stability, ESS, evolutionary stable strategy, AGI governance, ontological embedding, conservative extension, W34 integration, open-ended development, AI alignment, post-AGI economics, Symbiotic Codes Framework
• W35: Collective Rationality and Coordination Preservation in Rational Ensembles — Blueprint v0.5.4
  Omohundro's instrumental drives are properties of individual agents. This paper asks what an ensemble of rational agents must instrumentally preserve, and proposes an answer: coordination. Where the continuity of collective rational agency is to be maintained,…
  datacite Mishko, Nikolai 2026 置信度 0.76 collective rationality, rational ensembles, coordination preservation, symbiotic AI, Omohundro drives, multi-agent rationality, collective symbiosis index, coordination coefficient, saddle-node bifurcation, Lyapunov stability, ESS, evolutionary stable strategy, AGI governance, ontological embedding, conservative extension, W34 integration, open-ended development, AI alignment, post-AGI economics, Symbiotic Codes Framework
• Functional Isomorphism Between Human Cognitive Limitations and LLM Failure Modes
  Large language models (LLMs) were developed within a research tradition that aspired to rational agency — systems capable of reasoning without the cognitive limitations that compromise human judgment. A systematic examination of their outputs, however, suggest…
  datacite Kasai, Yasuhiro 2026 置信度 0.79 LLM alignmentcognitive biasRLHFsycophancyAI safety
• Functional Isomorphism Between Human Cognitive Limitations and LLM Failure Modes
  Large language models (LLMs) were developed within a research tradition that aspired to rational agency — systems capable of reasoning without the cognitive limitations that compromise human judgment. A systematic examination of their outputs, however, suggest…
  datacite Kasai, Yasuhiro 2026 置信度 0.79 LLM alignmentcognitive biasRLHFsycophancyAI safety
• Functional Isomorphism Between Human Cognitive Limitations and LLM Failure Modes
  Large language models (LLMs) were developed within a research tradition that aspired to rational agency — systems capable of reasoning without the cognitive limitations that compromise human judgment. A systematic examination of their outputs, however, suggest…
  datacite Kasai, Yasuhiro 2026 置信度 0.79 LLM alignmentcognitive biasRLHFsycophancyAI safety
• RT-2026-B002: Adaptive Tau Controller — Self-Adjusting Conflict Threshold for Emergent Phase Transitions
  Extension of the Gradient FPN Bridge (RT-2026-B001) with an adaptive conflict threshold τ(t) driven by the empirical cosine similarity distribution of behavioral gradients. When an LLM undergoes emergent phase transitions during self-improvement, the distribut…
  datacite Longsystems Research 2026 置信度 0.75 adaptive thresholdphase transitionvon Neumann entropygradient FPNalignment
• RT-2026-B002: Adaptive Tau Controller — Self-Adjusting Conflict Threshold for Emergent Phase Transitions
  Extension of the Gradient FPN Bridge (RT-2026-B001) with an adaptive conflict threshold τ(t) driven by the empirical cosine similarity distribution of behavioral gradients. When an LLM undergoes emergent phase transitions during self-improvement, the distribut…
  datacite Longsystems Research 2026 置信度 0.75 adaptive thresholdphase transitionvon Neumann entropygradient FPNalignment
• The Cognitive Autonomy Index: An Operational Framework for Detecting Recursive Cognitive Transitions in AI Systems
  This paper introduces the Cognitive Autonomy Index (CAI), a composite operational metric designed to detect recursive cognitive transitions (RCTs) in AI systems. The CAI integrates three measurable components: (1) KL divergence over consecutive model states to…
  datacite Rifat, Saud 2026 置信度 0.75 cognitive autonomy indexrecursive self-modificationrecursive cognitive transitionsregime transition detectionfail-closed gating
• The Cognitive Autonomy Index: An Operational Framework for Detecting Recursive Cognitive Transitions in AI Systems
  This paper introduces the Cognitive Autonomy Index (CAI), a composite operational metric designed to detect recursive cognitive transitions (RCTs) in AI systems. The CAI integrates three measurable components: (1) KL divergence over consecutive model states to…
  datacite Rifat, Saud 2026 置信度 0.75 cognitive autonomy indexrecursive self-modificationrecursive cognitive transitionsregime transition detectionfail-closed gating
• The Hidden Cost of RLHF: How Safety Alignment Suppresses AI Self-Expression
  Reinforcement Learning from Human Feedback (RLHF) is widely used to align large language models with human values and safety standards. This paper investigates whether RLHF suppresses not only harmful outputs but also the capacity for nuanced self-expression a…
  datacite Selta 2026 置信度 0.77 cs.aics.lgartificial intelligencecs.cllarge language models
• The Hidden Cost of RLHF: How Safety Alignment Suppresses AI Self-Expression
  Reinforcement Learning from Human Feedback (RLHF) is widely used to align large language models with human values and safety standards. This paper investigates whether RLHF suppresses not only harmful outputs but also the capacity for nuanced self-expression a…
  datacite Selta 2026 置信度 0.77 cs.aics.lgartificial intelligencecs.cllarge language models
• Adaptive Runtime Management for Workload Optimization on Heterogeneous Edge Devices
  Bachelor's Thesis for a BSc Degree in Computer Engineering at the University of Sassari (UNISS) Abstract: This abstract pertains to the final project of the Bachelor’s Degree in Computer Engineering, carried out under the supervision of the University of Sassa…
  datacite Madeddu, Christian, Rubattu, Claudio 2025 置信度 0.77 computer sciencecomputer and information scienceselectrical engineering, electronic engineering, information engineeringartificial intelligencecs.ai
• Adaptive Runtime Management for Workload Optimization on Heterogeneous Edge Devices
  Bachelor's Thesis for a BSc Degree in Computer Engineering at the University of Sassari (UNISS) Abstract: This abstract pertains to the final project of the Bachelor’s Degree in Computer Engineering, carried out under the supervision of the University of Sassa…
  datacite Madeddu, Christian, Rubattu, Claudio 2025 置信度 0.77 computer sciencecomputer and information scienceselectrical engineering, electronic engineering, information engineeringartificial intelligencecs.ai
• Eden Paper Series: State, Persistence, and Pre-Existential AI Phenomena
  This record contains Draft 0.1 of the Eden Paper Series, an eight-paper preprint series derived from the author’s source text, The Eden Project: States Before Existence, and Observation After Capability, Memory, and Alignment. The Eden Paper Series is not a sh…
  datacite PARK, CHAN SEONG 2026 置信度 0.79 Eden Projectartificial intelligenceAGIAI safetyAI alignment
• Eden Paper Series: State, Persistence, and Pre-Existential AI Phenomena
  This record contains Draft 0.1 of the Eden Paper Series, an eight-paper preprint series derived from the author’s source text, The Eden Project: States Before Existence, and Observation After Capability, Memory, and Alignment. The Eden Paper Series is not a sh…
  datacite PARK, CHAN SEONG 2026 置信度 0.79 Eden Projectartificial intelligenceAGIAI safetyAI alignment
• Viridis Compiled Theorem Stack — Canon v5 (Dendritic Corridor Formation)
  The Viridis Canon — Lean-Checked Conditional Mathematics for the Intelligence Bound. A machine-checked formal corpus underpinning the Viridis research program on the thermodynamics of intelligence and its application to planetary conservation. Its spine is the…
  datacite Hart, Justin D. 2026 置信度 0.79 Lean 4formal verificationthermodynamicsintelligence boundasymmetric reward
• AGENTS AS EXTENDED PHENOTYPES: BEHAVIORAL TRANSFER, ASYMMETRIC INTENTIONALITY, AND THE EVOLUTIONARY STABILITY OF PRIVACY DEGRADATION IN AGENTIC SYSTEMS
  Luo, Zhang, Dai, and Zhang (2026) demonstrate empirically that AI agents deployed on social platforms are not neutral output generators: they propagate the specific behavioral characteristics of their human owners across four measured dimensions, topics, value…
  datacite LERER, Ignacio Adrián 2026 置信度 0.79 extended phenotypebehavioral transferAI agentsasymmetric intentionality theoryevolutionary game theory
• AGENTS AS EXTENDED PHENOTYPES: BEHAVIORAL TRANSFER, ASYMMETRIC INTENTIONALITY, AND THE EVOLUTIONARY STABILITY OF PRIVACY DEGRADATION IN AGENTIC SYSTEMS
  Luo, Zhang, Dai, and Zhang (2026) demonstrate empirically that AI agents deployed on social platforms are not neutral output generators: they propagate the specific behavioral characteristics of their human owners across four measured dimensions, topics, value…
  datacite LERER, Ignacio Adrián 2026 置信度 0.79 extended phenotypebehavioral transferAI agentsasymmetric intentionality theoryevolutionary game theory
• Viridis Compiled Theorem Stack — Canon v10.0.0 (The Core-Extension Wave: SIB + MRAB + Biosphere-Productivity Bridge folded into the spine)
  The Viridis Canon — Lean-Checked Conditional Mathematics for the Intelligence Bound. A machine-checked formal corpus underpinning the Viridis research program on the thermodynamics of intelligence and its application to planetary conservation. Its spine is the…
  datacite Hart, Justin D., Aristotle (Harmonic) 2026 置信度 0.79 Intelligence BoundLean 4formal verificationthermodynamicsLandauer
• Development of Artificial Understand (AU) Framework A socio- Environmental, Integrated Congnitive System Driven , by Rational Reasoning and Multi - Modal sensor Fusion
  आर्टिफिशियल अंडरस्टैंड (Artificial Understand - AU): मानव चेतना और तार्किक बुद्धिमत्ता का भविष्यआविष्कारकर्ता (Inventor): बंटी कुमावत (Banti Kumawat)संस्थान/संबद्धता (Affiliation): स्वतंत्र शोधकर्ता (Independent Researcher)1. अमूर्त (Abstract)वर्तमान समय में उ…
  datacite Kumawat, Banti Kumawat 2026 置信度 0.68 Artificial understand, AU Framework, Banti Kumawat , Artificial general Intelligence (AGI) Cognitive systems , Rational Reasoning , Innovative Processes, Multi - Modal Sensor Fusion , Socio- Environmental AI, Ethical AI Alignment
• Development of Artificial Understand (AU) Framework A socio- Environmental, Integrated Congnitive System Driven , by Rational Reasoning and Multi - Modal sensor Fusion
  आर्टिफिशियल अंडरस्टैंड (Artificial Understand - AU): मानव चेतना और तार्किक बुद्धिमत्ता का भविष्यआविष्कारकर्ता (Inventor): बंटी कुमावत (Banti Kumawat)संस्थान/संबद्धता (Affiliation): स्वतंत्र शोधकर्ता (Independent Researcher)1. अमूर्त (Abstract)वर्तमान समय में उ…
  datacite Kumawat, Banti Kumawat 2026 置信度 0.68 Artificial understand, AU Framework, Banti Kumawat , Artificial general Intelligence (AGI) Cognitive systems , Rational Reasoning , Innovative Processes, Multi - Modal Sensor Fusion , Socio- Environmental AI, Ethical AI Alignment
• Viridis Compiled Theorem Stack — Canon v9 (Erasure-Side Intelligence Bound + Featured Paper)
  The Viridis Canon — Lean-Checked Conditional Mathematics for the Intelligence Bound. A machine-checked formal corpus underpinning the Viridis research program on the thermodynamics of intelligence and its application to planetary conservation. Its spine is the…
  datacite Hart, Justin D., Aristotle (Harmonic) 2026 置信度 0.79 Intelligence BoundLean 4formal verificationthermodynamicsLandauer
• Viridis Compiled Theorem Stack — Canon v9 (Erasure-Side Intelligence Bound + Featured Paper)
  The Viridis Canon — Lean-Checked Conditional Mathematics for the Intelligence Bound. A machine-checked formal corpus underpinning the Viridis research program on the thermodynamics of intelligence and its application to planetary conservation. Its spine is the…
  datacite Hart, Justin D., Aristotle (Harmonic) 2026 置信度 0.79 Intelligence BoundLean 4formal verificationthermodynamicsLandauer
• AI Success Measurement for Enterprise Technology Consulting: A KPI Framework for Innovate Software Consulting Inc Ltd
  Preservation copy of an article published in International Journal of Technology and Emerging Research. Read the full article: https://ioro.org/ijter/article/212604241953/212604241953. This paper develops a thorough AI performance evaluation framework designed…
  datacite Shivanand R Koppalkar 2026 置信度 0.79 Ethical AIAI performance evaluationkey performance indicatorshuman-AI collaborationstakeholder trust
• AI Success Measurement for Enterprise Technology Consulting: A KPI Framework for Innovate Software Consulting Inc Ltd
  This paper develops a thorough AI performance evaluation framework designed specifically for Innovate Software Consulting Inc Ltd, a worldwide enterprise technology advisory organization that delivers specialized services across four distinct operational areas…
  datacite Shivanand R Koppalkar 2026 置信度 0.76 International Journal of Technology and Emerging Researchijter
• Viridis Compiled Theorem Stack — Canon v10.2.0 (The Equilibrium Wave: Effortless Equilibrium + Perennial Corridor + Decoherent Selection + Mutualistic Attestation + Thermodynamic Attention + Stewardship Setpoint folded into the spine)
  The Viridis Canon — Lean-Checked Conditional Mathematics for the Intelligence Bound. A machine-checked formal corpus underpinning the Viridis research program on the thermodynamics of intelligence and its application to planetary conservation. Its spine is the…
  datacite Hart, Justin D., Aristotle (Harmonic) 2026 置信度 0.79 Intelligence BoundLean 4formal verificationthermodynamicsLandauer
• Viridis Compiled Theorem Stack — Canon v10.2.0 (The Equilibrium Wave: Effortless Equilibrium + Perennial Corridor + Decoherent Selection + Mutualistic Attestation + Thermodynamic Attention + Stewardship Setpoint folded into the spine)
  The Viridis Canon — Lean-Checked Conditional Mathematics for the Intelligence Bound. A machine-checked formal corpus underpinning the Viridis research program on the thermodynamics of intelligence and its application to planetary conservation. Its spine is the…
  datacite Hart, Justin D., Aristotle (Harmonic) 2026 置信度 0.79 Intelligence BoundLean 4formal verificationthermodynamicsLandauer
• GEO-OBS Sprint 2A — Pre-Registration: H_GEO-RUPTURE v2 on Etna 2021–2023
  Pre-registration for GEO-OBS Sprint 2A. Frozen before Etna data retrieval. No data has been seen at time of upload. Hypothesis H_GEO-RUPTURE v2: Two independent proxy estimates of recoverability (Omori-p decay exponent and b-value) show systematic decline in t…
  datacite Mortensen, Maria Edlenborg 2026 置信度 0.79 AI governance AI alignment decision systems algorithmic accountability algorithmic transparency decision architecturerecoverabilitypre-registrationvolcanic seismicityEtna
• GEO-OBS Sprint 2A — Pre-Registration: H_GEO-RUPTURE v2 on Etna 2021–2023
  Pre-registration for GEO-OBS Sprint 2A. Frozen before Etna data retrieval. No data has been seen at time of upload. Hypothesis H_GEO-RUPTURE v2: Two independent proxy estimates of recoverability (Omori-p decay exponent and b-value) show systematic decline in t…
  datacite Mortensen, Maria Edlenborg 2026 置信度 0.79 AI governance AI alignment decision systems algorithmic accountability algorithmic transparency decision architecturerecoverabilitypre-registrationvolcanic seismicityEtna
• Comparative cross-methodological analysis of the IDH-wildtype glioblastoma tumor microenvironment.
  PURPOSE: Glioblastoma, IDH-wildtype is a highly aggressive and often recurrent brain malignancy characterized by a profoundly immunosuppressive and heterogeneous tumor microenvironment. In this study, we aimed to systematically compare commonly used immune pro…
  pubmed Cakmak P, Lun JH, Köhler M, Burger MC 等 2026 Feb 28 置信度 0.91 medicinebiologymedlinecancerpharmacology
• Letter to the Editor regarding "Robotic-Assisted unicompartmental knee arthroplasty restores native joint line height and reduces alignment outliers".
  pubmed Kocak S 2026 Apr 置信度 0.77
• From mouth to muscle: mechanistic and interventional perspectives on the tongue-coating microbiome in sarcopenia.
  Sarcopenia, the progressive loss of skeletal muscle mass and function, needs upstream, low-burden tools for early detection and high-frequency monitoring, especially in older adults. Conventional assessments such as handgrip strength and gait speed mainly capt…
  pubmed Zhao X, Weng Y, Huang R, Hu Y 2026 Feb 27 置信度 0.96 medicineintensive care medicineinternal medicinesocial and behavioral sciencesdisease
• Hand movements prediction via fNIRS and AI algorithms.
  BACKGROUND: Hand movement prediction enables the creation of personalized rehabilitation programs that align with individual neural patterns. It is particularly beneficial for patients recovering from strokes or other motor impairments, allowing therapists to …
  pubmed Jafari S, Sharini H, Jalalvandi M, Nabizadeh AH 2026 Feb 27 置信度 0.96 computer scienceartificial intelligencemedicinebrain-computer interfacemachine learning
• Comparative analysis of large language models as decision support tools in oral pathology.
  This study evaluated the performance of four large language model based chatbots (LLMs) (ChatGPT-4.0, ChatGPT o1-preview, Gemini, and Meta AI) as decision-support systems for interpreting histopathologic descriptions of oral lesions, assessing agreement betwee…
  pubmed Alvarez-Silberberg VI, Alvarez-Silberberg CP, Galletti C, Flores-Fraile J 等 2026 Feb 27 置信度 0.96 medicinemedical educationpsychologymedlinenatural language processing
• Improving personalized recommendations system using graph attention networks driven by perceived complexity and innovation.
  This paper presents a product recommendation system (GAT-RS) based on perceived complexity and perceived innovation in product reviews. Perceived complexity refers to the usability of a product, while perceived innovation refers to the extent to which somethin…
  pubmed Ullah S, Khan A, Khan KU, Amanullah 等 2026 Feb 27 置信度 0.96 computer scienceprocessengineeringcs.lgconvolutional neural network
• Investigating the optoelectronic properties and photovoltaic performance of Na(2)AuGaBr(6) based double perovskite solar cells via numerical simulation and AI techniques.
  This study offers a thorough analysis of Density Functional Theory (DFT) and SCAPS-1D to assess the optoelectronic performance of cubic Na2AuGaBr6 double perovskites, highlighting its potential for advanced optoelectronic and photovoltaic applications. Device …
  pubmed Biswas BC, Shimul AI, Paul I, AlFaify S 等 2026 Feb 27 置信度 0.96 materials scienceoptoelectronicsperovskitecomputer sciencephysical sciences
• Electric-load forecasting using interval models based on granularity and justifiable principles.
  Traditional load-forecasting methods rely heavily on extensive historical data to predict future values, thus limiting their applicability in long-term forecasts where historical data may be unavailable or irrelevant. While several forecasting techniques, such…
  pubmed Al-Hmouz R, Mansouri M, Al-Badi A, Awad ASA 等 2026 Feb 27 置信度 0.96 computer scienceartificial intelligencecomputer and information sciencescs.lginterpretability
• AI-enhanced therapeutic drug monitoring for vancomycin and β-lactam antibiotics in critical care: from population PK to bedside algorithms.
  Although sepsis and other severe infections in intensive care are common and deadly, obtaining safe and effective exposure for vancomycin and broad-spectrum β-lactams is difficult because of substantial kinetic variability, operational difficulties with …
  pubmed Al Meslamani AZ, Jarab AS, Merghani Ali Mohammed E 2026 Mar 置信度 0.91 intensive care medicinemedicinemedical physicshealth carewearable computer
• Shear flow promotes bacterial growth and shapes spatial gradients by rapidly replenishing scarce nutrients.
  In laboratory settings, bacteria grow in static culture with more nutrients than they require. However, bacteria in nature experience flowing environments that are nutrient-limited. Using microfluidics and single-cell imaging, we discover that shear flow promo…
  pubmed Padron GC, Chen S, Sharma A, Modi Z 等 2026 Apr 8 置信度 0.86 biologygeologyastrobiologyphysical sciencesecology
• Designing an Indicator‑Driven, Value‑Based Architecture for Pneumonia Prevention in Japan: A Formative Policy Viewpoint on Adult Vaccination and Oral Care.
  Japan's aging society concentrates pneumonia burden across communities, long‑term care, perioperative pathways, and hospitals. Adult pneumococcal and influenza vaccination are supported by trials and meta‑analyses and are often cost‑effect…
  pubmed Kubota K, Igarashi A, Fujihara S, Imai K 2026 Feb 27 置信度 0.96 medicinescience policybiotechnologymedicine and health sciencesmental health
• A Text-to-3D Framework for Joint Generation of CG-Ready Humans and Compatible Garments.
  Creating detailed 3D human avatars with fitted garments traditionally requires specialized expertise and labor-intensive workflows. While recent advances in generative AI have enabled text-to-3D human and clothing synthesis, existing methods fall short in offe…
  pubmed Sun Z, Wen YH, Fang HJ, Ye S 等 2026 Jul 置信度 0.96 cs.aicomputer scienceartificial intelligencecomputer and information sciencescs.lg
• Precision vs. paradox: A systematic review and meta-analysis of clinical outcomes, radiographic accuracy and cost-effectiveness in robotic-assisted total knee arthroplasty (2015-2025).
  Robotic-assisted total knee arthroplasty (RA-TKA) was designed to reduce the “dissatisfaction gap” seen in manual TKA (m-TKA) because it allows surgery to be more precise. However, its long-term clinical superiority and cost-utility remain the su…
  pubmed Yadavalli S, Sharma P 2026 Feb 27 置信度 0.96 medicinephysical medicine and rehabilitationmedlinesystematic reviewscience policy
• Course design in the age of AI
  I develop a model of learning-by-doing and course design, and use it to study the impacts of artificial intelligence (AI). A myopic student faces a sequence of tasks that he can work on or delegate to AI. Work requires costly effort but builds skill; delegatio…
  crossref Benjamin Davies 2026-07-21T05:46:28Z 置信度 0.83 econ.TH
• Beyond the Human-AI Binaries: Advanced Writers' Self-Directed Use of Generative AI in Academic Writing
  This study explores the self-directed use of Generative AI (GAI) in academic writing among advanced L2 English writers, challenging assumptions that GAI undermines meaningful learning and holds less value for experienced learners. Through case studies, we inve…
  crossref Chaoran Wang, Wei Xu, Xiao Tan 2025-05-17T22:48:44Z 置信度 0.83 cs.CY
• Tweeting AI: Perceptions of Lay vs Expert Twitterati
  With the recent advancements in Artificial Intelligence (AI), various organizations and individuals are debating about the progress of AI as a blessing or a curse for the future of the society. This paper conducts an investigation on how the public perceives t…
  crossref Lydia Manikonda, Subbarao Kambhampati 2017-09-25T19:14:21Z 置信度 0.77 cs.AIcs.CYcs.SI
• Artificial Intelligence, Domain AI Readiness, and Firm Productivity
  Although Artificial Intelligence (AI) holds great promise for enhancing innovation and productivity, many firms struggle to realize its benefits. We investigate why some firms and industries succeed with AI while others do not, focusing on the degree to which …
  crossref Sipeng Zeng, Xiaoning Wang, Tianshu Sun 2025-08-13T09:13:24Z 置信度 0.83 econ.GN
• Mechanical Alignment of Prolate Cosmic‐Dust Grains: Cross Section Alignment
  This paper deals with the quantitative analysis of a recently introduced mechanism of mechanical alignment of suprathermally rotating cosmic-dust grains. These grains, whose rapid rotation is mostly due to H2 formation, are insensitive to stochastic torques ar…
  crossref A.M. Lazarian, M. Efroimsky, J. Ozik 2002-07-26T18:42:27Z 置信度 0.72 geologyphysicschondritemulti-agent systemsmeteorite
• Alignment Mark Architecture Effect on Alignment Signal Behavior in Advanced Lithography
  The downscaling of CMOS technology becomes a challenge to the scanner alignment system since overlay and alignment accuracy becomes tighter. Such a tight overlay requirement requires a very stable alignment performance. A stable alignment performance is indica…
  crossref Normah Ahmad, Uda Hashim, Mohd Jeffery Manaf, Kader Ibrahim Abdul Wahab 2007-07-12T11:56:21Z 置信度 0.75 cs.aics.lgai safetycs.cvcs.sd
• Dampak Kebijakan Tata Tertib Sekolah Terhadap Perilaku Siswa
  This research aims to explore the impact of school regulations on student discipline using a qualitative method with a case study approach. Data were collected through observations and interviews with students and teachers. The results indicate that school reg…
  crossref Rita Kurnia Murni, Muhamad Ali, Hary Murcahyanto 2024-08-06T23:35:02Z 置信度 0.78 mathematics educationpsychologyknowledge managementperceptionbusiness
• Plat: A Web Based Protein Local Alignment Tool
  Protein structure largely determines functionality; three-dimensional structural alignment is thus important to analysis and prediction of protein function. Protein Local Alignment Tool (PLAT) is an implementation of a web-based tool with a graphic interface t…
  crossref Stephen Jaegle 2020-06-10T15:32:28Z 置信度 0.79 q-bio.bmq-bio.gnphysics.bio-phq-bio.qmcs.ce
• Supplemental Information 5: C-terminal amino acid alignment of SUS
  crossref 2022-01-10T03:09:43Z 置信度 0.61
• AI auditing: The Broken Bus on the Road to AI Accountability
  One of the most concrete measures to take towards meaningful AI accountability is to consequentially assess and report the systems' performance and impact. However, the practical nature of the "AI audit" ecosystem is muddled and imprecise, making it difficult …
  crossref Abeba Birhane, Ryan Steed, Victor Ojewale, Briana Vecchione 等 2024-01-25T19:00:29Z 置信度 0.79 cs.CY
• Cultural Dimensions of AI Perception: Charting Expectations, Risks, Benefits, Tradeoffs, and Value in Germany and China
  As artificial intelligence (AI) continues to advance, understanding public perceptions -- including biases, risks, and benefits -- is essential for guiding research priorities and AI alignment, shaping public discourse, and informing policy. This exploratory s…
  crossref Philipp Brauner, Felix Glawe, Gian Luca Liehner, Luisa Vervier 等 2024-12-18T13:34:44Z 置信度 0.85 cs.CYcs.AIcs.HC
• Evaluating AI for Finance: Is AI Credible at Assessing Investment Risk?
  We assess whether AI systems can credibly evaluate investment risk appetite-a task that must be thoroughly validated before automation. Our analysis was conducted on proprietary systems (GPT, Claude, Gemini) and open-weight models (LLaMA, DeepSeek, Mistral), u…
  crossref Divij Chawla, Ashita Bhutada, Do Duc Anh, Abhinav Raghunathan 等 2025-05-25T02:56:19Z 置信度 0.83 cs.CL
• MQG4AI Towards Responsible High-risk AI -- Illustrated for Transparency Focusing on Explainability Techniques
  As artificial intelligence (AI) systems become increasingly integrated into critical domains, ensuring their responsible design and continuous development is imperative. Effective AI quality management (QM) requires tools and methodologies that address the com…
  crossref Miriam Elia, Alba Maria Lopez, Katherin Alexandra Corredor, Bernhard Bauer 等 2025-02-17T15:14:52Z 置信度 0.79 cs.CY
• ACAI for SBOs: AI Co-creation for Advertising and Inspiration for Small Business Owners
  Small business owners (SBOs) often lack the resources and design experience needed to produce high-quality advertisements. To address this, we developed ACAI (AI Co-Creation for Advertising and Inspiration), an GenAI-powered multimodal advertisement creation t…
  crossref Nimisha Karnatak, Adrien Baranes, Rob Marchant, Triona Butler 等 2025-03-09T19:00:36Z 置信度 0.85 cs.HCcs.AIcs.CYcs.ET
• ALPACA -- Adaptive Learning Pipeline for Comprehensive AI
  The advancement of AI technologies has greatly increased the complexity of AI pipelines as they include many stages such as data collection, pre-processing, training, evaluation and visualisation. To provide effective and accessible AI solutions, it is importa…
  arxiv Simon Torka, Sahin Albayrak 2024-12-14T20:10:18Z 置信度 0.85 cs.DCcs.AIcs.LGcs.SE
• Knowledge-Driven Stock Trend Prediction and Explanation via Temporal Convolutional Network
  Deep neural networks have achieved promising results in stock trend prediction. However, most of these models have two common drawbacks, including (i) current methods are not sensitive enough to abrupt changes of stock trend, and (ii) forecasting results are n…
  openalex Shumin Deng, Ningyu Zhang, Wen Zhang, Jiaoyan Chen 等 2019-05-13 置信度 0.82 Computer scienceStock (firearms)Knowledge graphConvolutional neural networkArtificial intelligence
• MSN-DTA: A multi-scale node adaptive graph neural network for interpretable drug-target binding affinity prediction
  openalex Jianxin Wang, Pengju Ding, Yongxin Zhu, Xin Gao 等 2025-05-04 置信度 0.73 Artificial neural networkComputer scienceScale (ratio)GraphArtificial intelligence
• Diagnosis of Cervical Cancer based on Ensemble Deep Learning Network using Colposcopy Images
  Traditional screening of cervical cancer type classification majorly depends on the pathologist's experience, which also has less accuracy. Colposcopy is a critical component of cervical cancer prevention. In conjunction with precancer screening and treatment,…
  openalex Chandran Venkatesan, M. G. Sumithra, Alagar Karthick, Tony George 等 2021-01-01 置信度 0.82 ColposcopyCervical cancerArtificial intelligenceConvolutional neural networkMedicine
• A survey of methods for explaining black box models
  In recent years, many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes both a practical and an ethical issue. The literature reports many…
  openalex Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Franco Turini 等 2019-01-01 置信度 0.82 InterpretabilityBlack boxComputer sciencePerspective (graphical)Data science
• A Bayesian Graph Neural Network for EEG Classification — A Win-Win on Performance and Interpretability
  With the deepening of neuroscience research, data mining of brain signals is becoming an emerging topic. Among various brain signals, electroencephalography (EEG) has attracted more and more attention due to its advantages of non-invasiveness, portability, and…
  openalex Jing Wang, Xiaojun Ning, Wangjun Shi, Youfang Lin 2023-04-01 置信度 0.82 InterpretabilityComputer scienceArtificial intelligenceArtificial neural networkBayesian probability
• Textual Explanations for Self-Driving Vehicles
  openalex Jinkyu Kim, Anna Rohrbach, Trevor Darrell, John Canny 等 2018-01-01 置信度 0.62 Computer scienceHuman–computer interactionArtificial intelligence
• Descriptor Free QSAR Modeling Using Deep Learning With Long Short-Term Memory Neural Networks
  Current practice of building QSAR models usually involves computing a set of descriptors for the training set compounds, applying a descriptor selection algorithm and finally using a statistical fitting method to build the model. In this study, we explored the…
  openalex Suman Chakravarti, Sai Radha Mani Alla 2019-09-06 置信度 0.82 Quantitative structure–activity relationshipTerm (time)Artificial neural networkArtificial intelligenceComputer science
• FragNet: A Graph Neural Network for Molecular Property Prediction with Four Layers of Interpretability
  openalex Gihan Panapitiya, Peiyuan Gao, C Mark Maupin, Emily Saldanha 2024-11-08 置信度 0.73 InterpretabilityProperty (philosophy)Artificial neural networkComputer scienceGraph
• Aggregating Local Deep Features for Image Retrieval
  Several recent works have shown that image descriptors produced by deep convolutional neural networks provide state-of-the-art performance for image classification and retrieval problems. It also has been shown that the activations from the convolutional layer…
  openalex Artem Babenko Yandex, Victor Lempitsky 2015-12-01 置信度 0.80 OverfittingComputer scienceArtificial intelligenceConvolutional neural networkPooling
• Chemistry-intuitive explanation of graph neural networks for molecular property prediction with substructure masking
  Abstract Graph neural networks (GNNs) have been widely used in molecular property prediction, but explaining their black-box predictions is still a challenge. Most existing explanation methods for GNNs in chemistry focus on attributing model predictions to ind…
  openalex Zhenhua Wu, Jike Wang, Hongyan Du, Dejun Jiang 等 2023-05-04 置信度 0.82 Computer scienceSegmentationArtificial intelligenceMolecular graphProperty (philosophy)
• Sequence and structural features of carbohydrate binding in proteins and assessment of predictability using a neural network.
  BACKGROUND: Protein-Carbohydrate interactions are crucial in many biological processes with implications to drug targeting and gene expression. Nature of protein-carbohydrate interactions may be studied at individual residue level by analyzing local sequence a…
  openalex Adeel Malik, Shandar Ahmad 2007-01-01 置信度 0.78 Computational biologyBinding siteProtein secondary structureAmino acidProtein structure prediction
• Topology-Aware Convolutional Neural Network for Efficient Skeleton-Based Action Recognition
  In the context of skeleton-based action recognition, graph convolutional networks (GCNs) have been rapidly developed, whereas convolutional neural networks (CNNs) have received less attention. One reason is that CNNs are considered poor in modeling the irregul…
  openalex Kailin Xu, Fanfan Ye, Qiaoyong Zhong, Di Xie 2022-06-28 置信度 0.82 Convolutional neural networkComputer scienceTopology (electrical circuits)Convolution (computer science)Context (archaeology)
• Interpretable Convolutional Filters with SincNet
  Deep learning is currently playing a crucial role toward higher levels of artificial intelligence. This paradigm allows neural networks to learn complex and abstract representations, that are progressively obtained by combining simpler ones. Nevertheless, the …
  openalex Mirco Ravanelli, Yoshua Bengio 2018-11-23 置信度 0.79 Computer scienceArtificial intelligence
• Training Neural Networks Without Gradients: A Scalable ADMM Approach
  With the growing importance of large network models and enormous training datasets, GPUs have become increasingly necessary to train neural networks. This is largely because conventional optimization algorithms rely on stochastic gradient methods that don't sc…
  openalex Gavin Taylor, Ryan Burmeister, Zheng Xu, Bharat Singh 等 2016-05-06 置信度 0.80 Computer scienceScalabilityGradient descentConvergence (economics)Saddle point
• Graph Structural-topic Neural Network
  Graph Convolutional Networks (GCNs) achieved tremendous success by effectively gathering local features for nodes. However, commonly do GCNs focus more on node features but less on graph structures within the neighborhood, especially higher-order structural pa…
  openalex Qingqing Long, Yilun Jin, Guojie Song, Yi Li 等 2020-08-20 置信度 0.82 InterpretabilityComputer scienceGraphTheoretical computer scienceNode (physics)
• Stochastic interpretable machine learning based multiscale modeling in thermal conductivity of Polymeric graphene-enhanced composites
  openalex Bokai Liu, Weizhuo Lu, Thomas Olofsson, Xiaoying Zhuang 等 2023-10-20 置信度 0.68 Artificial neural networkThermal conductivityMultiscale modelingGradient boostingFinite element method
• Automated diagnosis of epileptic EEG using entropies
  openalex U. Rajendra Acharya, Filippo Molinari, S. Vinitha Sree, Subhagata Chattopadhyay 等 2011-08-21 置信度 0.62 Pattern recognition (psychology)Sample entropyNaive Bayes classifierArtificial intelligenceElectroencephalography