{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZTNOI2MA6LW5QXZ3TIFQ3UAGJT","short_pith_number":"pith:ZTNOI2MA","canonical_record":{"source":{"id":"2603.29025","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-30T21:36:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8a1d9c502100298aa25330f6715b65790937ccf05d273e7a888216b72f0ca37e","abstract_canon_sha256":"cea0c5463bbeb30c6ff2b5991a92f2f5a98170f80d935c0e485882b516924a57"},"schema_version":"1.0"},"canonical_sha256":"ccdae46980f2edd85f3b9a0b0dd0064cf33c03b7ca3b0baa4bf4f24a48b92c76","source":{"kind":"arxiv","id":"2603.29025","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.29025","created_at":"2026-06-10T01:11:00Z"},{"alias_kind":"arxiv_version","alias_value":"2603.29025v3","created_at":"2026-06-10T01:11:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.29025","created_at":"2026-06-10T01:11:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZTNOI2MA6LW5","created_at":"2026-06-10T01:11:00Z"},{"alias_kind":"pith_short_16","alias_value":"ZTNOI2MA6LW5QXZ3","created_at":"2026-06-10T01:11:00Z"},{"alias_kind":"pith_short_8","alias_value":"ZTNOI2MA","created_at":"2026-06-10T01:11:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZTNOI2MA6LW5QXZ3TIFQ3UAGJT","target":"record","payload":{"canonical_record":{"source":{"id":"2603.29025","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-30T21:36:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8a1d9c502100298aa25330f6715b65790937ccf05d273e7a888216b72f0ca37e","abstract_canon_sha256":"cea0c5463bbeb30c6ff2b5991a92f2f5a98170f80d935c0e485882b516924a57"},"schema_version":"1.0"},"canonical_sha256":"ccdae46980f2edd85f3b9a0b0dd0064cf33c03b7ca3b0baa4bf4f24a48b92c76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:11:00.302599Z","signature_b64":"3McrmDt9+KDVOZSX1txtuZZ4VXQU8fWwrMtV5uzzkYAjHDNRqbqBJyJeOZj78Ov8IY2csUSgopI/7ZXQ8owHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccdae46980f2edd85f3b9a0b0dd0064cf33c03b7ca3b0baa4bf4f24a48b92c76","last_reissued_at":"2026-06-10T01:11:00.301484Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:11:00.301484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.29025","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T01:11:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UAGBB7hIP2ZnAxV91dA3NazW5/gtl9+E1ftH5SvExLplwsddlkBBgj0e4iFkdaS4+bNIbzn5lQOuAIRgyWqoDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T11:18:57.745716Z"},"content_sha256":"50e05a8aba236ce54702d8edb454f432b0125edf103c433434152984b07ddc7b","schema_version":"1.0","event_id":"sha256:50e05a8aba236ce54702d8edb454f432b0125edf103c433434152984b07ddc7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZTNOI2MA6LW5QXZ3TIFQ3UAGJT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Surface distance cues override implicit feasibility constraints in large language models, causing systematic reasoning failures.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lu Zhang, Ramayya Krishnan, Rema Padman, Tianchong Jiang, Yubo Li","submitted_at":"2026-03-30T21:36:09Z","abstract_excerpt":"Large language models fail when a salient surface cue conflicts with an unstated feasibility constraint. We introduce the Heuristic Override Benchmark (HOB): 500 instances spanning 4 heuristic families and 5 constraint families, with minimal pairs and explicitness gradients. We pair HOB with a falsifiable behavioral characterization following a diagnose-measure-bridge-treat arc. Causal-behavioral analysis of the car wash problem across six models reveals context-independent sigmoid heuristics: the distance cue has 8.7 to 38 times more influence than the goal, and attribution better matches key"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Causal-behavioral analysis of the car wash problem across six models reveals approximately context-independent sigmoid heuristics: the distance cue exerts 8.7 to 38 times more influence than the goal.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That minimal pairs and explicitness gradients in the HOB benchmark successfully isolate heuristic override from other factors such as knowledge gaps or prompt formatting effects.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LLMs prioritize surface heuristics such as distance cues over implicit constraints in reasoning tasks, with the new HOB benchmark showing no model exceeds 75% strict accuracy and hints recovering performance.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Surface distance cues override implicit feasibility constraints in large language models, causing systematic reasoning failures.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f4176ba450c4737151aedc50faaac3f204cf3134f55e729b0e0cd9c01a71e615"},"source":{"id":"2603.29025","kind":"arxiv","version":3},"verdict":{"id":"5cd1875d-14d2-4a54-b211-bcd6569bbc1a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T21:03:13.023690Z","strongest_claim":"Causal-behavioral analysis of the car wash problem across six models reveals approximately context-independent sigmoid heuristics: the distance cue exerts 8.7 to 38 times more influence than the goal.","one_line_summary":"LLMs prioritize surface heuristics such as distance cues over implicit constraints in reasoning tasks, with the new HOB benchmark showing no model exceeds 75% strict accuracy and hints recovering performance.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That minimal pairs and explicitness gradients in the HOB benchmark successfully isolate heuristic override from other factors such as knowledge gaps or prompt formatting effects.","pith_extraction_headline":"Surface distance cues override implicit feasibility constraints in large language models, causing systematic reasoning failures."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.29025/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":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"5cd1875d-14d2-4a54-b211-bcd6569bbc1a"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T01:11:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J3h2s9WWYZw7AxFT20JN/Ai3TSafQkVEEq40iPzdypv0W6JeRvoOtwPhs54odsMcWZ4q02n2FtQZSBaoz33WCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T11:18:57.746726Z"},"content_sha256":"6a52af008446a99166810e50016288781bc9c0ca26bb5daec7a731d17994ae2d","schema_version":"1.0","event_id":"sha256:6a52af008446a99166810e50016288781bc9c0ca26bb5daec7a731d17994ae2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZTNOI2MA6LW5QXZ3TIFQ3UAGJT/bundle.json","state_url":"https://pith.science/pith/ZTNOI2MA6LW5QXZ3TIFQ3UAGJT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZTNOI2MA6LW5QXZ3TIFQ3UAGJT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-10T11:18:57Z","links":{"resolver":"https://pith.science/pith/ZTNOI2MA6LW5QXZ3TIFQ3UAGJT","bundle":"https://pith.science/pith/ZTNOI2MA6LW5QXZ3TIFQ3UAGJT/bundle.json","state":"https://pith.science/pith/ZTNOI2MA6LW5QXZ3TIFQ3UAGJT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZTNOI2MA6LW5QXZ3TIFQ3UAGJT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZTNOI2MA6LW5QXZ3TIFQ3UAGJT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cea0c5463bbeb30c6ff2b5991a92f2f5a98170f80d935c0e485882b516924a57","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-30T21:36:09Z","title_canon_sha256":"8a1d9c502100298aa25330f6715b65790937ccf05d273e7a888216b72f0ca37e"},"schema_version":"1.0","source":{"id":"2603.29025","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.29025","created_at":"2026-06-10T01:11:00Z"},{"alias_kind":"arxiv_version","alias_value":"2603.29025v3","created_at":"2026-06-10T01:11:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.29025","created_at":"2026-06-10T01:11:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZTNOI2MA6LW5","created_at":"2026-06-10T01:11:00Z"},{"alias_kind":"pith_short_16","alias_value":"ZTNOI2MA6LW5QXZ3","created_at":"2026-06-10T01:11:00Z"},{"alias_kind":"pith_short_8","alias_value":"ZTNOI2MA","created_at":"2026-06-10T01:11:00Z"}],"graph_snapshots":[{"event_id":"sha256:6a52af008446a99166810e50016288781bc9c0ca26bb5daec7a731d17994ae2d","target":"graph","created_at":"2026-06-10T01:11:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Causal-behavioral analysis of the car wash problem across six models reveals approximately context-independent sigmoid heuristics: the distance cue exerts 8.7 to 38 times more influence than the goal."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That minimal pairs and explicitness gradients in the HOB benchmark successfully isolate heuristic override from other factors such as knowledge gaps or prompt formatting effects."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"LLMs prioritize surface heuristics such as distance cues over implicit constraints in reasoning tasks, with the new HOB benchmark showing no model exceeds 75% strict accuracy and hints recovering performance."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Surface distance cues override implicit feasibility constraints in large language models, causing systematic reasoning failures."}],"snapshot_sha256":"f4176ba450c4737151aedc50faaac3f204cf3134f55e729b0e0cd9c01a71e615"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.29025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models fail when a salient surface cue conflicts with an unstated feasibility constraint. We introduce the Heuristic Override Benchmark (HOB): 500 instances spanning 4 heuristic families and 5 constraint families, with minimal pairs and explicitness gradients. We pair HOB with a falsifiable behavioral characterization following a diagnose-measure-bridge-treat arc. Causal-behavioral analysis of the car wash problem across six models reveals context-independent sigmoid heuristics: the distance cue has 8.7 to 38 times more influence than the goal, and attribution better matches key","authors_text":"Lu Zhang, Ramayya Krishnan, Rema Padman, Tianchong Jiang, Yubo Li","cross_cats":["cs.AI"],"headline":"Surface distance cues override implicit feasibility constraints in large language models, causing systematic reasoning failures.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-30T21:36:09Z","title":"The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.29025","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-14T21:03:13.023690Z","id":"5cd1875d-14d2-4a54-b211-bcd6569bbc1a","model_set":{"reader":"grok-4.3"},"one_line_summary":"LLMs prioritize surface heuristics such as distance cues over implicit constraints in reasoning tasks, with the new HOB benchmark showing no model exceeds 75% strict accuracy and hints recovering performance.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Surface distance cues override implicit feasibility constraints in large language models, causing systematic reasoning failures.","strongest_claim":"Causal-behavioral analysis of the car wash problem across six models reveals approximately context-independent sigmoid heuristics: the distance cue exerts 8.7 to 38 times more influence than the goal.","weakest_assumption":"That minimal pairs and explicitness gradients in the HOB benchmark successfully isolate heuristic override from other factors such as knowledge gaps or prompt formatting effects."}},"verdict_id":"5cd1875d-14d2-4a54-b211-bcd6569bbc1a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:50e05a8aba236ce54702d8edb454f432b0125edf103c433434152984b07ddc7b","target":"record","created_at":"2026-06-10T01:11:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cea0c5463bbeb30c6ff2b5991a92f2f5a98170f80d935c0e485882b516924a57","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-30T21:36:09Z","title_canon_sha256":"8a1d9c502100298aa25330f6715b65790937ccf05d273e7a888216b72f0ca37e"},"schema_version":"1.0","source":{"id":"2603.29025","kind":"arxiv","version":3}},"canonical_sha256":"ccdae46980f2edd85f3b9a0b0dd0064cf33c03b7ca3b0baa4bf4f24a48b92c76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccdae46980f2edd85f3b9a0b0dd0064cf33c03b7ca3b0baa4bf4f24a48b92c76","first_computed_at":"2026-06-10T01:11:00.301484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:11:00.301484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3McrmDt9+KDVOZSX1txtuZZ4VXQU8fWwrMtV5uzzkYAjHDNRqbqBJyJeOZj78Ov8IY2csUSgopI/7ZXQ8owHCA==","signature_status":"signed_v1","signed_at":"2026-06-10T01:11:00.302599Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.29025","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50e05a8aba236ce54702d8edb454f432b0125edf103c433434152984b07ddc7b","sha256:6a52af008446a99166810e50016288781bc9c0ca26bb5daec7a731d17994ae2d"],"state_sha256":"e3c7fd5a4a38731b6ce8e64dbeed0b75054e9a106e22d4c8c02eb5c8894b626f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6lPk14cmpGMd2r15wU/wrLrjsZPABebqFqgFCilkqTOc1h/Go9zDa4wxrcN5q1b2I5Jdr1dyC0NYH1uPaxu/AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T11:18:57.751165Z","bundle_sha256":"9a22cd33bba34c20364d7ac66603ab3fe4f638804c2da2f7c6de1a71a2817a81"}}