{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MG27FO3SIAH5BFPV5I4WJU6HZO","short_pith_number":"pith:MG27FO3S","schema_version":"1.0","canonical_sha256":"61b5f2bb72400fd095f5ea3964d3c7cb859fc8009536d0c31280f3db29b0a003","source":{"kind":"arxiv","id":"2608.05630","version":1},"attestation_state":"computed","paper":{"title":"Human-Like Anaphor Resolution in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Keane Zhang, Raj Sanjay Shah, Sashank Varma, Varshini Chinta","submitted_at":"2026-08-06T05:57:01Z","abstract_excerpt":"Anaphors are expressions that refer to other expressions, called antecedents. The process of connecting the two is called resolution. Cognitive science has identified multiple factors that affect the speed and success of anaphor resolution, including discourse structure, situation-model properties, and semantic factors. Here, we investigate whether these factors also affect anaphor resolution in five Large Language Models (LLMs) with open weights: GPT-2-XL, Llama-3.1-8B, Pythia-12B, Mistral-7B, and Mistral-24B. To model processing difficulty, we adopt the standard linking hypothesis that relat"},"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":"2608.05630","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-06T05:57:01Z","cross_cats_sorted":[],"title_canon_sha256":"8d2d2936f62fe06fb55b5f90eaff3da001224f2e21693d28ae41aa598089c80b","abstract_canon_sha256":"92125a51bac22cffc3666acdc3ca935eb03f86b8ed24ab200c2a6048c3502449"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:50:30.255879Z","signature_b64":"yDjCPCq2YD+Ro34WXD3trws+nw+KPnXZNrr56ZQMgNsavUmMhJndNgvyYaBuFtOQuqjWDbvd3ytALlhvk5zTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61b5f2bb72400fd095f5ea3964d3c7cb859fc8009536d0c31280f3db29b0a003","last_reissued_at":"2026-08-07T00:50:30.254476Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:50:30.254476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-Like Anaphor Resolution in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Keane Zhang, Raj Sanjay Shah, Sashank Varma, Varshini Chinta","submitted_at":"2026-08-06T05:57:01Z","abstract_excerpt":"Anaphors are expressions that refer to other expressions, called antecedents. The process of connecting the two is called resolution. Cognitive science has identified multiple factors that affect the speed and success of anaphor resolution, including discourse structure, situation-model properties, and semantic factors. Here, we investigate whether these factors also affect anaphor resolution in five Large Language Models (LLMs) with open weights: GPT-2-XL, Llama-3.1-8B, Pythia-12B, Mistral-7B, and Mistral-24B. To model processing difficulty, we adopt the standard linking hypothesis that relat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05630","kind":"arxiv","version":1},"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/2608.05630/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":"2608.05630","created_at":"2026-08-07T00:50:30.255904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05630v1","created_at":"2026-08-07T00:50:30.255904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05630","created_at":"2026-08-07T00:50:30.255904+00:00"},{"alias_kind":"pith_short_12","alias_value":"MG27FO3SIAH5","created_at":"2026-08-07T00:50:30.255904+00:00"},{"alias_kind":"pith_short_16","alias_value":"MG27FO3SIAH5BFPV","created_at":"2026-08-07T00:50:30.255904+00:00"},{"alias_kind":"pith_short_8","alias_value":"MG27FO3S","created_at":"2026-08-07T00:50:30.255904+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/MG27FO3SIAH5BFPV5I4WJU6HZO","json":"https://pith.science/pith/MG27FO3SIAH5BFPV5I4WJU6HZO.json","graph_json":"https://pith.science/api/pith-number/MG27FO3SIAH5BFPV5I4WJU6HZO/graph.json","events_json":"https://pith.science/api/pith-number/MG27FO3SIAH5BFPV5I4WJU6HZO/events.json","paper":"https://pith.science/paper/MG27FO3S"},"agent_actions":{"view_html":"https://pith.science/pith/MG27FO3SIAH5BFPV5I4WJU6HZO","download_json":"https://pith.science/pith/MG27FO3SIAH5BFPV5I4WJU6HZO.json","view_paper":"https://pith.science/paper/MG27FO3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05630&json=true","fetch_graph":"https://pith.science/api/pith-number/MG27FO3SIAH5BFPV5I4WJU6HZO/graph.json","fetch_events":"https://pith.science/api/pith-number/MG27FO3SIAH5BFPV5I4WJU6HZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MG27FO3SIAH5BFPV5I4WJU6HZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MG27FO3SIAH5BFPV5I4WJU6HZO/action/storage_attestation","attest_author":"https://pith.science/pith/MG27FO3SIAH5BFPV5I4WJU6HZO/action/author_attestation","sign_citation":"https://pith.science/pith/MG27FO3SIAH5BFPV5I4WJU6HZO/action/citation_signature","submit_replication":"https://pith.science/pith/MG27FO3SIAH5BFPV5I4WJU6HZO/action/replication_record"}},"created_at":"2026-08-07T00:50:30.255904+00:00","updated_at":"2026-08-07T00:50:30.255904+00:00"}