{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MXQTO4WXWZ5WU5MTATLMBHZZYD","short_pith_number":"pith:MXQTO4WX","schema_version":"1.0","canonical_sha256":"65e13772d7b67b6a759304d6c09f39c0e1459711a404ca9300d750fdfcea6856","source":{"kind":"arxiv","id":"2512.06393","version":7},"attestation_state":"computed","paper":{"title":"Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A four-stage training pipeline makes LLMs check rules for contradictions before reasoning, fixing their tendency to follow inconsistent premises.","cross_cats":["cs.CL","cs.LG","cs.LO"],"primary_cat":"cs.AI","authors_text":"Michael Witbrock, Qiming Bao, Xiaoxuan Fu","submitted_at":"2025-12-06T10:49:50Z","abstract_excerpt":"Large language models (LLMs) achieve high accuracy on many reasoning benchmarks but remain brittle under structural perturbations of rule-based systems. We introduce a diagnostic framework with four stress tests -- redundant vs. essential rule deletion, contradictory-rule injection, logic-preserving rewrites, and multi-law stacking -- and use it to expose Logic Inertia: the tendency of generative LLMs (Qwen2/3, TinyLlama, GPT-4o, Gemma-3-4B-IT) and the encoder-only BERT baseline to persist along learned deductive trajectories under inconsistent premises. The collapse is sharp: untreated baseli"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"canonical_record":{"source":{"id":"2512.06393","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-12-06T10:49:50Z","cross_cats_sorted":["cs.CL","cs.LG","cs.LO"],"title_canon_sha256":"174223e13832395cc26d800e70f119f22c2332f40073368839b4628477570eff","abstract_canon_sha256":"10e7d04bf3e837bbb599f565529c91c66acdd6a96e9a88ef4d9d3ec71cea9221"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:19.407477Z","signature_b64":"SLweVWFYIP22ZJbD4g/qwVuhgjePwJBQ50cUkTkiy8U4X8j7P6aUirdgKojjit4Yfgu/M0qbVUQxU8hzo79HAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65e13772d7b67b6a759304d6c09f39c0e1459711a404ca9300d750fdfcea6856","last_reissued_at":"2026-05-26T01:03:19.406900Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:19.406900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A four-stage training pipeline makes LLMs check rules for contradictions before reasoning, fixing their tendency to follow inconsistent premises.","cross_cats":["cs.CL","cs.LG","cs.LO"],"primary_cat":"cs.AI","authors_text":"Michael Witbrock, Qiming Bao, Xiaoxuan Fu","submitted_at":"2025-12-06T10:49:50Z","abstract_excerpt":"Large language models (LLMs) achieve high accuracy on many reasoning benchmarks but remain brittle under structural perturbations of rule-based systems. We introduce a diagnostic framework with four stress tests -- redundant vs. essential rule deletion, contradictory-rule injection, logic-preserving rewrites, and multi-law stacking -- and use it to expose Logic Inertia: the tendency of generative LLMs (Qwen2/3, TinyLlama, GPT-4o, Gemma-3-4B-IT) and the encoder-only BERT baseline to persist along learned deductive trajectories under inconsistent premises. The collapse is sharp: untreated baseli"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The pipeline saturates all four primary stress tests for both 1.5B and 8B backbones. We further validate a Phase 2 extension that replaces the propositional oracle with a Lean 4 kernel, attaining 99.0% kernel agreement on the 105 classically-derivable (T) questions within a stratified 187-question Lean-translated sample (overall 71.7% across both polarities).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the four stress tests capture the relevant forms of logical inconsistency that arise in real-world LLM use, and that the symbolic forward-chaining engine (or Lean kernel) supplies rewards that do not embed their own unexamined biases or coverage gaps into the learned policy.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Conflict-Aware Fusion mitigates Logic Inertia in LLMs through a four-stage pipeline of SFT, DPO, logical invariance regularization, and reinforcement learning from a symbolic oracle, saturating four stress tests on rule contradictions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A four-stage training pipeline makes LLMs check rules for contradictions before reasoning, fixing their tendency to follow inconsistent premises.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3612cf4edbef4804ebd6e2f8040131b98825c0319488755a5287036837593de6"},"source":{"id":"2512.06393","kind":"arxiv","version":7},"verdict":{"id":"b5e5e1d1-0277-4db1-8f4b-96d3cc140796","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T01:05:09.434154Z","strongest_claim":"The pipeline saturates all four primary stress tests for both 1.5B and 8B backbones. We further validate a Phase 2 extension that replaces the propositional oracle with a Lean 4 kernel, attaining 99.0% kernel agreement on the 105 classically-derivable (T) questions within a stratified 187-question Lean-translated sample (overall 71.7% across both polarities).","one_line_summary":"Conflict-Aware Fusion mitigates Logic Inertia in LLMs through a four-stage pipeline of SFT, DPO, logical invariance regularization, and reinforcement learning from a symbolic oracle, saturating four stress tests on rule contradictions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the four stress tests capture the relevant forms of logical inconsistency that arise in real-world LLM use, and that the symbolic forward-chaining engine (or Lean kernel) supplies rewards that do not embed their own unexamined biases or coverage gaps into the learned policy.","pith_extraction_headline":"A four-stage training pipeline makes LLMs check rules for contradictions before reasoning, fixing their tendency to follow inconsistent premises."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.06393/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"2e79b3fce7d1bc5803778319a7763cc2ee386c5580d081416245cd9eec7c3e83"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2512.06393","created_at":"2026-05-26T01:03:19.406972+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.06393v7","created_at":"2026-05-26T01:03:19.406972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.06393","created_at":"2026-05-26T01:03:19.406972+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXQTO4WXWZ5W","created_at":"2026-05-26T01:03:19.406972+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXQTO4WXWZ5WU5MT","created_at":"2026-05-26T01:03:19.406972+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXQTO4WX","created_at":"2026-05-26T01:03:19.406972+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MXQTO4WXWZ5WU5MTATLMBHZZYD","json":"https://pith.science/pith/MXQTO4WXWZ5WU5MTATLMBHZZYD.json","graph_json":"https://pith.science/api/pith-number/MXQTO4WXWZ5WU5MTATLMBHZZYD/graph.json","events_json":"https://pith.science/api/pith-number/MXQTO4WXWZ5WU5MTATLMBHZZYD/events.json","paper":"https://pith.science/paper/MXQTO4WX"},"agent_actions":{"view_html":"https://pith.science/pith/MXQTO4WXWZ5WU5MTATLMBHZZYD","download_json":"https://pith.science/pith/MXQTO4WXWZ5WU5MTATLMBHZZYD.json","view_paper":"https://pith.science/paper/MXQTO4WX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.06393&json=true","fetch_graph":"https://pith.science/api/pith-number/MXQTO4WXWZ5WU5MTATLMBHZZYD/graph.json","fetch_events":"https://pith.science/api/pith-number/MXQTO4WXWZ5WU5MTATLMBHZZYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXQTO4WXWZ5WU5MTATLMBHZZYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXQTO4WXWZ5WU5MTATLMBHZZYD/action/storage_attestation","attest_author":"https://pith.science/pith/MXQTO4WXWZ5WU5MTATLMBHZZYD/action/author_attestation","sign_citation":"https://pith.science/pith/MXQTO4WXWZ5WU5MTATLMBHZZYD/action/citation_signature","submit_replication":"https://pith.science/pith/MXQTO4WXWZ5WU5MTATLMBHZZYD/action/replication_record"}},"created_at":"2026-05-26T01:03:19.406972+00:00","updated_at":"2026-05-26T01:03:19.406972+00:00"}