{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AFTLOFBDHEX74UQ542JXXZIMVD","short_pith_number":"pith:AFTLOFBD","schema_version":"1.0","canonical_sha256":"0166b71423392ffe521de6937be50ca8c09872f025bcbbcff5c480644543f149","source":{"kind":"arxiv","id":"2406.19764","version":2},"attestation_state":"computed","paper":{"title":"Belief Revision: The Adaptability of Large Language Models Reasoning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bryan Wilie, Etsuko Ishii, Junxian He, Pascale Fung, Samuel Cahyawijaya","submitted_at":"2024-06-28T09:09:36Z","abstract_excerpt":"The capability to reason from text is crucial for real-world NLP applications. Real-world scenarios often involve incomplete or evolving data. In response, individuals update their beliefs and understandings accordingly. However, most existing evaluations assume that language models (LMs) operate with consistent information. We introduce Belief-R, a new dataset designed to test LMs' belief revision ability when presented with new evidence. Inspired by how humans suppress prior inferences, this task assesses LMs within the newly proposed delta reasoning ($\\Delta R$) framework. Belief-R features"},"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":false},"canonical_record":{"source":{"id":"2406.19764","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T09:09:36Z","cross_cats_sorted":[],"title_canon_sha256":"3c1cfde42c2867ab738061016ea23041d1abf37a235629cf4b7ba8560ff58b7f","abstract_canon_sha256":"b2233f9dbff11617e37089552446c3fdab360d682816910af085dafc99666aa1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:46.417280Z","signature_b64":"OKAOrH+YlYbrztlOGuXSXkAiPrY3EfNNXyzJkJNPAV+VXU7QKxYNOFOH2pnM4sgdn2P9ZhCbjahnqN2YHk09AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0166b71423392ffe521de6937be50ca8c09872f025bcbbcff5c480644543f149","last_reissued_at":"2026-07-05T09:21:46.416797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:46.416797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Belief Revision: The Adaptability of Large Language Models Reasoning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bryan Wilie, Etsuko Ishii, Junxian He, Pascale Fung, Samuel Cahyawijaya","submitted_at":"2024-06-28T09:09:36Z","abstract_excerpt":"The capability to reason from text is crucial for real-world NLP applications. Real-world scenarios often involve incomplete or evolving data. In response, individuals update their beliefs and understandings accordingly. However, most existing evaluations assume that language models (LMs) operate with consistent information. We introduce Belief-R, a new dataset designed to test LMs' belief revision ability when presented with new evidence. Inspired by how humans suppress prior inferences, this task assesses LMs within the newly proposed delta reasoning ($\\Delta R$) framework. Belief-R features"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19764","kind":"arxiv","version":2},"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/2406.19764/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.19764","created_at":"2026-07-05T09:21:46.416856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.19764v2","created_at":"2026-07-05T09:21:46.416856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19764","created_at":"2026-07-05T09:21:46.416856+00:00"},{"alias_kind":"pith_short_12","alias_value":"AFTLOFBDHEX7","created_at":"2026-07-05T09:21:46.416856+00:00"},{"alias_kind":"pith_short_16","alias_value":"AFTLOFBDHEX74UQ5","created_at":"2026-07-05T09:21:46.416856+00:00"},{"alias_kind":"pith_short_8","alias_value":"AFTLOFBD","created_at":"2026-07-05T09:21:46.416856+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03255","citing_title":"Do LLMs have core beliefs?","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AFTLOFBDHEX74UQ542JXXZIMVD","json":"https://pith.science/pith/AFTLOFBDHEX74UQ542JXXZIMVD.json","graph_json":"https://pith.science/api/pith-number/AFTLOFBDHEX74UQ542JXXZIMVD/graph.json","events_json":"https://pith.science/api/pith-number/AFTLOFBDHEX74UQ542JXXZIMVD/events.json","paper":"https://pith.science/paper/AFTLOFBD"},"agent_actions":{"view_html":"https://pith.science/pith/AFTLOFBDHEX74UQ542JXXZIMVD","download_json":"https://pith.science/pith/AFTLOFBDHEX74UQ542JXXZIMVD.json","view_paper":"https://pith.science/paper/AFTLOFBD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.19764&json=true","fetch_graph":"https://pith.science/api/pith-number/AFTLOFBDHEX74UQ542JXXZIMVD/graph.json","fetch_events":"https://pith.science/api/pith-number/AFTLOFBDHEX74UQ542JXXZIMVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AFTLOFBDHEX74UQ542JXXZIMVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AFTLOFBDHEX74UQ542JXXZIMVD/action/storage_attestation","attest_author":"https://pith.science/pith/AFTLOFBDHEX74UQ542JXXZIMVD/action/author_attestation","sign_citation":"https://pith.science/pith/AFTLOFBDHEX74UQ542JXXZIMVD/action/citation_signature","submit_replication":"https://pith.science/pith/AFTLOFBDHEX74UQ542JXXZIMVD/action/replication_record"}},"created_at":"2026-07-05T09:21:46.416856+00:00","updated_at":"2026-07-05T09:21:46.416856+00:00"}