{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BZFWQ64TZRKEAGHNJPYULY27UI","short_pith_number":"pith:BZFWQ64T","schema_version":"1.0","canonical_sha256":"0e4b687b93cc544018ed4bf145e35fa230357ec8271bfa63795802e9ab6abf74","source":{"kind":"arxiv","id":"2507.04189","version":2},"attestation_state":"computed","paper":{"title":"SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Bin Liang, Hainiu Xu, Lin Gui, Qinglin Zhu, Runcong Zhao, Yulan He","submitted_at":"2025-07-05T23:46:35Z","abstract_excerpt":"Understanding character relationships is essential for interpreting complex narratives and conducting socially grounded AI research. However, manual annotation is time-consuming and low in coverage, while large language models (LLMs) often produce hallucinated or logically inconsistent outputs. We present SymbolicThought, a human-in-the-loop framework that combines LLM-based extraction with symbolic reasoning. The system constructs editable character relationship graphs, refines them using seven types of logical constraints, and enables real-time validation and conflict resolution through an i"},"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":"2507.04189","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-05T23:46:35Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"934c4ede4ef851a63234105cb3486e55a4f3483eb6bef94accdad452f195aec4","abstract_canon_sha256":"154fe5f7db30b79579f049b4bf1fa74410bad4f63570ec8f57bf5fcea0291732"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:34.382282Z","signature_b64":"CBx8I77oeuSDprCjd4OFVOawOFgRSDttL9DWNq+ZIdvLYkLgINRZEppfuv6ihu855ZKDmRJVrtecXnEykv7HDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e4b687b93cc544018ed4bf145e35fa230357ec8271bfa63795802e9ab6abf74","last_reissued_at":"2026-07-05T11:36:34.381836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:34.381836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Bin Liang, Hainiu Xu, Lin Gui, Qinglin Zhu, Runcong Zhao, Yulan He","submitted_at":"2025-07-05T23:46:35Z","abstract_excerpt":"Understanding character relationships is essential for interpreting complex narratives and conducting socially grounded AI research. However, manual annotation is time-consuming and low in coverage, while large language models (LLMs) often produce hallucinated or logically inconsistent outputs. We present SymbolicThought, a human-in-the-loop framework that combines LLM-based extraction with symbolic reasoning. The system constructs editable character relationship graphs, refines them using seven types of logical constraints, and enables real-time validation and conflict resolution through an i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04189","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/2507.04189/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":"2507.04189","created_at":"2026-07-05T11:36:34.381890+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04189v2","created_at":"2026-07-05T11:36:34.381890+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04189","created_at":"2026-07-05T11:36:34.381890+00:00"},{"alias_kind":"pith_short_12","alias_value":"BZFWQ64TZRKE","created_at":"2026-07-05T11:36:34.381890+00:00"},{"alias_kind":"pith_short_16","alias_value":"BZFWQ64TZRKEAGHN","created_at":"2026-07-05T11:36:34.381890+00:00"},{"alias_kind":"pith_short_8","alias_value":"BZFWQ64T","created_at":"2026-07-05T11:36:34.381890+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BZFWQ64TZRKEAGHNJPYULY27UI","json":"https://pith.science/pith/BZFWQ64TZRKEAGHNJPYULY27UI.json","graph_json":"https://pith.science/api/pith-number/BZFWQ64TZRKEAGHNJPYULY27UI/graph.json","events_json":"https://pith.science/api/pith-number/BZFWQ64TZRKEAGHNJPYULY27UI/events.json","paper":"https://pith.science/paper/BZFWQ64T"},"agent_actions":{"view_html":"https://pith.science/pith/BZFWQ64TZRKEAGHNJPYULY27UI","download_json":"https://pith.science/pith/BZFWQ64TZRKEAGHNJPYULY27UI.json","view_paper":"https://pith.science/paper/BZFWQ64T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04189&json=true","fetch_graph":"https://pith.science/api/pith-number/BZFWQ64TZRKEAGHNJPYULY27UI/graph.json","fetch_events":"https://pith.science/api/pith-number/BZFWQ64TZRKEAGHNJPYULY27UI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BZFWQ64TZRKEAGHNJPYULY27UI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BZFWQ64TZRKEAGHNJPYULY27UI/action/storage_attestation","attest_author":"https://pith.science/pith/BZFWQ64TZRKEAGHNJPYULY27UI/action/author_attestation","sign_citation":"https://pith.science/pith/BZFWQ64TZRKEAGHNJPYULY27UI/action/citation_signature","submit_replication":"https://pith.science/pith/BZFWQ64TZRKEAGHNJPYULY27UI/action/replication_record"}},"created_at":"2026-07-05T11:36:34.381890+00:00","updated_at":"2026-07-05T11:36:34.381890+00:00"}