{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PXYTXKODH6MUEDHFLSGREWC7LG","short_pith_number":"pith:PXYTXKOD","schema_version":"1.0","canonical_sha256":"7df13ba9c33f99420ce55c8d12585f599a58fd1ebb7bb6b2c9966becd6790a66","source":{"kind":"arxiv","id":"2411.07466","version":2},"attestation_state":"computed","paper":{"title":"IdentifyMe: A Challenging Long-Context Mention Resolution Benchmark for LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Kawshik Manikantan, Makarand Tapaswi, Shubham Toshniwal, Vineet Gandhi","submitted_at":"2024-11-12T01:05:55Z","abstract_excerpt":"Recent evaluations of LLMs on coreference resolution have revealed that traditional output formats and evaluation metrics do not fully capture the models' referential understanding. To address this, we introduce IdentifyMe, a new benchmark for mention resolution presented in a multiple-choice question (MCQ) format, commonly used for evaluating LLMs. IdentifyMe features long narratives and employs heuristics to exclude easily identifiable mentions, creating a more challenging task. The benchmark also consists of a curated mixture of different mention types and corresponding entities, allowing f"},"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":"2411.07466","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-12T01:05:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"addda184eaf4c8cfcbd3ed6d586ee35760ebd3965757a5733ba33e884d6950f4","abstract_canon_sha256":"1d16cf9d886d960d252ef337a1d64f09ba5ac3c61f8f800ad430b8bbd3716bae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:10.359967Z","signature_b64":"PtsTkyzqA+qKwdCvHpXZStwTEhe3xQgkfWFPVI/8q4WIScJwWEcsimegMYZVw86fw04hvYFhJZIMF/J/ZKbjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7df13ba9c33f99420ce55c8d12585f599a58fd1ebb7bb6b2c9966becd6790a66","last_reissued_at":"2026-07-05T10:50:10.359489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:10.359489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IdentifyMe: A Challenging Long-Context Mention Resolution Benchmark for LLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Kawshik Manikantan, Makarand Tapaswi, Shubham Toshniwal, Vineet Gandhi","submitted_at":"2024-11-12T01:05:55Z","abstract_excerpt":"Recent evaluations of LLMs on coreference resolution have revealed that traditional output formats and evaluation metrics do not fully capture the models' referential understanding. To address this, we introduce IdentifyMe, a new benchmark for mention resolution presented in a multiple-choice question (MCQ) format, commonly used for evaluating LLMs. IdentifyMe features long narratives and employs heuristics to exclude easily identifiable mentions, creating a more challenging task. The benchmark also consists of a curated mixture of different mention types and corresponding entities, allowing f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07466","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/2411.07466/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":"2411.07466","created_at":"2026-07-05T10:50:10.359550+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07466v2","created_at":"2026-07-05T10:50:10.359550+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07466","created_at":"2026-07-05T10:50:10.359550+00:00"},{"alias_kind":"pith_short_12","alias_value":"PXYTXKODH6MU","created_at":"2026-07-05T10:50:10.359550+00:00"},{"alias_kind":"pith_short_16","alias_value":"PXYTXKODH6MUEDHF","created_at":"2026-07-05T10:50:10.359550+00:00"},{"alias_kind":"pith_short_8","alias_value":"PXYTXKOD","created_at":"2026-07-05T10:50:10.359550+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/PXYTXKODH6MUEDHFLSGREWC7LG","json":"https://pith.science/pith/PXYTXKODH6MUEDHFLSGREWC7LG.json","graph_json":"https://pith.science/api/pith-number/PXYTXKODH6MUEDHFLSGREWC7LG/graph.json","events_json":"https://pith.science/api/pith-number/PXYTXKODH6MUEDHFLSGREWC7LG/events.json","paper":"https://pith.science/paper/PXYTXKOD"},"agent_actions":{"view_html":"https://pith.science/pith/PXYTXKODH6MUEDHFLSGREWC7LG","download_json":"https://pith.science/pith/PXYTXKODH6MUEDHFLSGREWC7LG.json","view_paper":"https://pith.science/paper/PXYTXKOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07466&json=true","fetch_graph":"https://pith.science/api/pith-number/PXYTXKODH6MUEDHFLSGREWC7LG/graph.json","fetch_events":"https://pith.science/api/pith-number/PXYTXKODH6MUEDHFLSGREWC7LG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PXYTXKODH6MUEDHFLSGREWC7LG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PXYTXKODH6MUEDHFLSGREWC7LG/action/storage_attestation","attest_author":"https://pith.science/pith/PXYTXKODH6MUEDHFLSGREWC7LG/action/author_attestation","sign_citation":"https://pith.science/pith/PXYTXKODH6MUEDHFLSGREWC7LG/action/citation_signature","submit_replication":"https://pith.science/pith/PXYTXKODH6MUEDHFLSGREWC7LG/action/replication_record"}},"created_at":"2026-07-05T10:50:10.359550+00:00","updated_at":"2026-07-05T10:50:10.359550+00:00"}