{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4U54PIA4CGJYYJFMNRIROUCDFP","short_pith_number":"pith:4U54PIA4","canonical_record":{"source":{"id":"2506.02701","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T09:55:21Z","cross_cats_sorted":[],"title_canon_sha256":"fad45b358a0b4372b503c303cac6d1ef4ed07966cd65bed860fff6aa6d41d793","abstract_canon_sha256":"dbfd136aaffb15504815bb8edd80ce534d9bb8ca97054f11bccece2e73f25b81"},"schema_version":"1.0"},"canonical_sha256":"e53bc7a01c11938c24ac6c511750432bdd7b17a8861b4ca0b44650b422c9a20f","source":{"kind":"arxiv","id":"2506.02701","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02701","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02701v4","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02701","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_12","alias_value":"4U54PIA4CGJY","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_16","alias_value":"4U54PIA4CGJYYJFM","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_8","alias_value":"4U54PIA4","created_at":"2026-07-05T11:39:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4U54PIA4CGJYYJFMNRIROUCDFP","target":"record","payload":{"canonical_record":{"source":{"id":"2506.02701","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T09:55:21Z","cross_cats_sorted":[],"title_canon_sha256":"fad45b358a0b4372b503c303cac6d1ef4ed07966cd65bed860fff6aa6d41d793","abstract_canon_sha256":"dbfd136aaffb15504815bb8edd80ce534d9bb8ca97054f11bccece2e73f25b81"},"schema_version":"1.0"},"canonical_sha256":"e53bc7a01c11938c24ac6c511750432bdd7b17a8861b4ca0b44650b422c9a20f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:54.705100Z","signature_b64":"4aE9gNwxnjbB2T9uEu/Z8leu2pwQYMXJ9HGMZfvwvE9rXL6N1CTB8JlIBqq+LiiC/e4+L0ATT9F6sJV+Mjo8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e53bc7a01c11938c24ac6c511750432bdd7b17a8861b4ca0b44650b422c9a20f","last_reissued_at":"2026-07-05T11:39:54.704630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:54.704630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.02701","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:39:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"psdBEhTYPIyel9JRoo3x+y4jn5Y0wxiUiRn4ZH0WQf01HWkAJ47CjHlH6hfmmjOKVoinAG1XhNvnRXcNMjrGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:16:01.755923Z"},"content_sha256":"1070ec8c087755f56b3e7f84590a05233e758aef9d8b205fcd976e55d39688e8","schema_version":"1.0","event_id":"sha256:1070ec8c087755f56b3e7f84590a05233e758aef9d8b205fcd976e55d39688e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4U54PIA4CGJYYJFMNRIROUCDFP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Entity Identification in Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Heinzerling, Kentaro Inui, Masaki Sakata, Sho Yokoi, Takumi Ito","submitted_at":"2025-06-03T09:55:21Z","abstract_excerpt":"We analyze the extent to which internal representations of language models (LMs) identify and distinguish mentions of named entities, focusing on the many-to-many correspondence between entities and their mentions. We first formulate two problems of entity mentions -- ambiguity and variability -- and propose a framework analogous to clustering quality metrics. Specifically, we quantify through cluster analysis of LM internal representations the extent to which mentions of the same entity cluster together and mentions of different entities remain separated. Our experiments examine five Transfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02701","kind":"arxiv","version":4},"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/2506.02701/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:39:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zqp0io886YEdr8slUUl2MFOYyU1k4mM7jBZmOa+NIjojD9YRflx8S2k4zJB/BcXz2Myi+sxTtP0GBkuZDfrACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:16:01.756420Z"},"content_sha256":"aa27e4b4b82aa19c9826320d59002e37700387e9e12881a987c6eed3dc21a69a","schema_version":"1.0","event_id":"sha256:aa27e4b4b82aa19c9826320d59002e37700387e9e12881a987c6eed3dc21a69a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4U54PIA4CGJYYJFMNRIROUCDFP/bundle.json","state_url":"https://pith.science/pith/4U54PIA4CGJYYJFMNRIROUCDFP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4U54PIA4CGJYYJFMNRIROUCDFP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T19:16:01Z","links":{"resolver":"https://pith.science/pith/4U54PIA4CGJYYJFMNRIROUCDFP","bundle":"https://pith.science/pith/4U54PIA4CGJYYJFMNRIROUCDFP/bundle.json","state":"https://pith.science/pith/4U54PIA4CGJYYJFMNRIROUCDFP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4U54PIA4CGJYYJFMNRIROUCDFP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4U54PIA4CGJYYJFMNRIROUCDFP","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":"dbfd136aaffb15504815bb8edd80ce534d9bb8ca97054f11bccece2e73f25b81","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T09:55:21Z","title_canon_sha256":"fad45b358a0b4372b503c303cac6d1ef4ed07966cd65bed860fff6aa6d41d793"},"schema_version":"1.0","source":{"id":"2506.02701","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02701","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02701v4","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02701","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_12","alias_value":"4U54PIA4CGJY","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_16","alias_value":"4U54PIA4CGJYYJFM","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_8","alias_value":"4U54PIA4","created_at":"2026-07-05T11:39:54Z"}],"graph_snapshots":[{"event_id":"sha256:aa27e4b4b82aa19c9826320d59002e37700387e9e12881a987c6eed3dc21a69a","target":"graph","created_at":"2026-07-05T11:39:54Z","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/2506.02701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We analyze the extent to which internal representations of language models (LMs) identify and distinguish mentions of named entities, focusing on the many-to-many correspondence between entities and their mentions. We first formulate two problems of entity mentions -- ambiguity and variability -- and propose a framework analogous to clustering quality metrics. Specifically, we quantify through cluster analysis of LM internal representations the extent to which mentions of the same entity cluster together and mentions of different entities remain separated. Our experiments examine five Transfor","authors_text":"Benjamin Heinzerling, Kentaro Inui, Masaki Sakata, Sho Yokoi, Takumi Ito","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T09:55:21Z","title":"On Entity Identification in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02701","kind":"arxiv","version":4},"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":"sha256:1070ec8c087755f56b3e7f84590a05233e758aef9d8b205fcd976e55d39688e8","target":"record","created_at":"2026-07-05T11:39:54Z","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":"dbfd136aaffb15504815bb8edd80ce534d9bb8ca97054f11bccece2e73f25b81","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T09:55:21Z","title_canon_sha256":"fad45b358a0b4372b503c303cac6d1ef4ed07966cd65bed860fff6aa6d41d793"},"schema_version":"1.0","source":{"id":"2506.02701","kind":"arxiv","version":4}},"canonical_sha256":"e53bc7a01c11938c24ac6c511750432bdd7b17a8861b4ca0b44650b422c9a20f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e53bc7a01c11938c24ac6c511750432bdd7b17a8861b4ca0b44650b422c9a20f","first_computed_at":"2026-07-05T11:39:54.704630Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:54.704630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4aE9gNwxnjbB2T9uEu/Z8leu2pwQYMXJ9HGMZfvwvE9rXL6N1CTB8JlIBqq+LiiC/e4+L0ATT9F6sJV+Mjo8AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:54.705100Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02701","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1070ec8c087755f56b3e7f84590a05233e758aef9d8b205fcd976e55d39688e8","sha256:aa27e4b4b82aa19c9826320d59002e37700387e9e12881a987c6eed3dc21a69a"],"state_sha256":"dadb5b8740696cb381fe7efb14d07375ef6508718028357772fb919791c8e952"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AU/I38o+AYLxyT/NM/lxCkHOY0G+XbJ6hNKZXrwe2l51+zrVmCnDfNVgX8AuYt/YE3xek9+WJk75QWupIfnXAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:16:01.761145Z","bundle_sha256":"34a48f4d8137ca69e400725558eba0ac61dd7889c5ec5eaa5b09152dd77ac06d"}}