{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PXYTXKODH6MUEDHFLSGREWC7LG","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":"1d16cf9d886d960d252ef337a1d64f09ba5ac3c61f8f800ad430b8bbd3716bae","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-12T01:05:55Z","title_canon_sha256":"addda184eaf4c8cfcbd3ed6d586ee35760ebd3965757a5733ba33e884d6950f4"},"schema_version":"1.0","source":{"id":"2411.07466","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07466","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07466v2","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07466","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"pith_short_12","alias_value":"PXYTXKODH6MU","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"pith_short_16","alias_value":"PXYTXKODH6MUEDHF","created_at":"2026-07-05T10:50:10Z"},{"alias_kind":"pith_short_8","alias_value":"PXYTXKOD","created_at":"2026-07-05T10:50:10Z"}],"graph_snapshots":[{"event_id":"sha256:e583faf02d89c4f176b7624ede9efece914ec35c5012b935ef469eee415aaa44","target":"graph","created_at":"2026-07-05T10:50:10Z","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/2411.07466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kawshik Manikantan, Makarand Tapaswi, Shubham Toshniwal, Vineet Gandhi","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-12T01:05:55Z","title":"IdentifyMe: A Challenging Long-Context Mention Resolution Benchmark for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07466","kind":"arxiv","version":2},"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":"sha256:95d877c12acb5ca25b46e76ef59ad8a073450de1c3084badcc85d93a4953810b","target":"record","created_at":"2026-07-05T10:50:10Z","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":"1d16cf9d886d960d252ef337a1d64f09ba5ac3c61f8f800ad430b8bbd3716bae","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-12T01:05:55Z","title_canon_sha256":"addda184eaf4c8cfcbd3ed6d586ee35760ebd3965757a5733ba33e884d6950f4"},"schema_version":"1.0","source":{"id":"2411.07466","kind":"arxiv","version":2}},"canonical_sha256":"7df13ba9c33f99420ce55c8d12585f599a58fd1ebb7bb6b2c9966becd6790a66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7df13ba9c33f99420ce55c8d12585f599a58fd1ebb7bb6b2c9966becd6790a66","first_computed_at":"2026-07-05T10:50:10.359489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:10.359489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PtsTkyzqA+qKwdCvHpXZStwTEhe3xQgkfWFPVI/8q4WIScJwWEcsimegMYZVw86fw04hvYFhJZIMF/J/ZKbjCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:10.359967Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.07466","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95d877c12acb5ca25b46e76ef59ad8a073450de1c3084badcc85d93a4953810b","sha256:e583faf02d89c4f176b7624ede9efece914ec35c5012b935ef469eee415aaa44"],"state_sha256":"d82e06c9b9dd65777c76c7251546e052e04976bde21652aeee0e97006dd5a9ae"}