{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PNQSUVJ4XZUBGY4WJ6L7IXY6K5","short_pith_number":"pith:PNQSUVJ4","canonical_record":{"source":{"id":"2402.11442","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T03:38:51Z","cross_cats_sorted":[],"title_canon_sha256":"6bc264df08d162c41526fa48d93d149e1a88c9f8db0694f2999bc95d6a67cc96","abstract_canon_sha256":"4a79b0f993c0db36166a88552dbca63846bfef666c1506c9e609b93b30587f0d"},"schema_version":"1.0"},"canonical_sha256":"7b612a553cbe681363964f97f45f1e5746fb441e8444696a5bcdd85d16166209","source":{"kind":"arxiv","id":"2402.11442","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11442","created_at":"2026-07-05T08:35:00Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11442v3","created_at":"2026-07-05T08:35:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11442","created_at":"2026-07-05T08:35:00Z"},{"alias_kind":"pith_short_12","alias_value":"PNQSUVJ4XZUB","created_at":"2026-07-05T08:35:00Z"},{"alias_kind":"pith_short_16","alias_value":"PNQSUVJ4XZUBGY4W","created_at":"2026-07-05T08:35:00Z"},{"alias_kind":"pith_short_8","alias_value":"PNQSUVJ4","created_at":"2026-07-05T08:35:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PNQSUVJ4XZUBGY4WJ6L7IXY6K5","target":"record","payload":{"canonical_record":{"source":{"id":"2402.11442","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T03:38:51Z","cross_cats_sorted":[],"title_canon_sha256":"6bc264df08d162c41526fa48d93d149e1a88c9f8db0694f2999bc95d6a67cc96","abstract_canon_sha256":"4a79b0f993c0db36166a88552dbca63846bfef666c1506c9e609b93b30587f0d"},"schema_version":"1.0"},"canonical_sha256":"7b612a553cbe681363964f97f45f1e5746fb441e8444696a5bcdd85d16166209","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:00.195385Z","signature_b64":"WEfRQVjsJa1OeJpMeHkhIK0OcoL3FrLfPYQ8FbZzmSUYu3/r4c3hUhHNO+F/YMCct+Uyak2Bwl0K85AgcGHFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b612a553cbe681363964f97f45f1e5746fb441e8444696a5bcdd85d16166209","last_reissued_at":"2026-07-05T08:35:00.194902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:00.194902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.11442","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":"2026-07-05T08:35:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Eq7FmU8czI/cF3xjnFghWLCtMuxP/Zlv05zQRpvcQqJJUXpKaEBOn2ukTAT/cQKisn464G16/s1+SOM2xwhfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T21:38:39.190343Z"},"content_sha256":"cbce899b168306c49ed4072abfbb6ccd5a110b40d83c5f7774ab783005ae5c3e","schema_version":"1.0","event_id":"sha256:cbce899b168306c49ed4072abfbb6ccd5a110b40d83c5f7774ab783005ae5c3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PNQSUVJ4XZUBGY4WJ6L7IXY6K5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Siyuan Wang, Xiang Ren, Yejin Choi, Zhongyu Wei","submitted_at":"2024-02-18T03:38:51Z","abstract_excerpt":"Large language models (LLMs) have achieved impressive human-like performance across various reasoning tasks. However, their mastery of underlying inferential rules still falls short of human capabilities. To investigate this, we propose a logic scaffolding inferential rule generation framework, to construct an inferential rule base, ULogic, comprising both primitive and compositional rules across five domains. Our analysis of GPT-series models over a rule subset reveals significant gaps in LLMs' logic understanding compared to human performance, especially in compositional and structural compl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11442","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.11442/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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:35:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rHzjSMtz5UA9xqKUq4BN4FPV8SdOJ1Pu0TOgMzDkQPPkv2IObplskZbU9svFr/iTT3U3M+vKxWqEU2LGUqs8Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T21:38:39.190842Z"},"content_sha256":"13ab33570a87246af6adbbad24da0c495f021121757877acb474587203f7857d","schema_version":"1.0","event_id":"sha256:13ab33570a87246af6adbbad24da0c495f021121757877acb474587203f7857d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PNQSUVJ4XZUBGY4WJ6L7IXY6K5/bundle.json","state_url":"https://pith.science/pith/PNQSUVJ4XZUBGY4WJ6L7IXY6K5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PNQSUVJ4XZUBGY4WJ6L7IXY6K5/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":"2026-08-23T21:38:39Z","links":{"resolver":"https://pith.science/pith/PNQSUVJ4XZUBGY4WJ6L7IXY6K5","bundle":"https://pith.science/pith/PNQSUVJ4XZUBGY4WJ6L7IXY6K5/bundle.json","state":"https://pith.science/pith/PNQSUVJ4XZUBGY4WJ6L7IXY6K5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PNQSUVJ4XZUBGY4WJ6L7IXY6K5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PNQSUVJ4XZUBGY4WJ6L7IXY6K5","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":"4a79b0f993c0db36166a88552dbca63846bfef666c1506c9e609b93b30587f0d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T03:38:51Z","title_canon_sha256":"6bc264df08d162c41526fa48d93d149e1a88c9f8db0694f2999bc95d6a67cc96"},"schema_version":"1.0","source":{"id":"2402.11442","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11442","created_at":"2026-07-05T08:35:00Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11442v3","created_at":"2026-07-05T08:35:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11442","created_at":"2026-07-05T08:35:00Z"},{"alias_kind":"pith_short_12","alias_value":"PNQSUVJ4XZUB","created_at":"2026-07-05T08:35:00Z"},{"alias_kind":"pith_short_16","alias_value":"PNQSUVJ4XZUBGY4W","created_at":"2026-07-05T08:35:00Z"},{"alias_kind":"pith_short_8","alias_value":"PNQSUVJ4","created_at":"2026-07-05T08:35:00Z"}],"graph_snapshots":[{"event_id":"sha256:13ab33570a87246af6adbbad24da0c495f021121757877acb474587203f7857d","target":"graph","created_at":"2026-07-05T08:35:00Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.11442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have achieved impressive human-like performance across various reasoning tasks. However, their mastery of underlying inferential rules still falls short of human capabilities. To investigate this, we propose a logic scaffolding inferential rule generation framework, to construct an inferential rule base, ULogic, comprising both primitive and compositional rules across five domains. Our analysis of GPT-series models over a rule subset reveals significant gaps in LLMs' logic understanding compared to human performance, especially in compositional and structural compl","authors_text":"Siyuan Wang, Xiang Ren, Yejin Choi, Zhongyu Wei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T03:38:51Z","title":"Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11442","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cbce899b168306c49ed4072abfbb6ccd5a110b40d83c5f7774ab783005ae5c3e","target":"record","created_at":"2026-07-05T08:35:00Z","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":"4a79b0f993c0db36166a88552dbca63846bfef666c1506c9e609b93b30587f0d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T03:38:51Z","title_canon_sha256":"6bc264df08d162c41526fa48d93d149e1a88c9f8db0694f2999bc95d6a67cc96"},"schema_version":"1.0","source":{"id":"2402.11442","kind":"arxiv","version":3}},"canonical_sha256":"7b612a553cbe681363964f97f45f1e5746fb441e8444696a5bcdd85d16166209","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b612a553cbe681363964f97f45f1e5746fb441e8444696a5bcdd85d16166209","first_computed_at":"2026-07-05T08:35:00.194902Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:00.194902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WEfRQVjsJa1OeJpMeHkhIK0OcoL3FrLfPYQ8FbZzmSUYu3/r4c3hUhHNO+F/YMCct+Uyak2Bwl0K85AgcGHFCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:00.195385Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11442","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cbce899b168306c49ed4072abfbb6ccd5a110b40d83c5f7774ab783005ae5c3e","sha256:13ab33570a87246af6adbbad24da0c495f021121757877acb474587203f7857d"],"state_sha256":"8f84e2378a303490362a32e20bea550642799ad736036995a69d1db73139230c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"noo1cdxcsqwx/atcL7VVdIl1/4zC0Uop1Tm3Arn287z/wLbvxzR/oBq/2/we4NhpMMgHfBJUkPg4oJzOsFJcAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T21:38:39.196724Z","bundle_sha256":"f21f3f315a918a35ae78e6d7e65c10d36a0519366b23568fa20f3e93e9d40165"}}