{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:QO7LCW4CY4UDRB5GIBN75LQ5MM","short_pith_number":"pith:QO7LCW4C","canonical_record":{"source":{"id":"2207.02824","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-06T17:29:30Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"50b542b24a49b0b723672abb7b9f3948fe08e2a81f2d566c41e18a2e4d9dbf5a","abstract_canon_sha256":"b3e408470ba83936c8e94bf6e279f4b5efd6361ea003c16f272da0246df8cbde"},"schema_version":"1.0"},"canonical_sha256":"83beb15b82c7283887a6405bfeae1d6326c64e950f158471e02768765526095a","source":{"kind":"arxiv","id":"2207.02824","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.02824","created_at":"2026-07-05T04:38:08Z"},{"alias_kind":"arxiv_version","alias_value":"2207.02824v1","created_at":"2026-07-05T04:38:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.02824","created_at":"2026-07-05T04:38:08Z"},{"alias_kind":"pith_short_12","alias_value":"QO7LCW4CY4UD","created_at":"2026-07-05T04:38:08Z"},{"alias_kind":"pith_short_16","alias_value":"QO7LCW4CY4UDRB5G","created_at":"2026-07-05T04:38:08Z"},{"alias_kind":"pith_short_8","alias_value":"QO7LCW4C","created_at":"2026-07-05T04:38:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:QO7LCW4CY4UDRB5GIBN75LQ5MM","target":"record","payload":{"canonical_record":{"source":{"id":"2207.02824","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-06T17:29:30Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"50b542b24a49b0b723672abb7b9f3948fe08e2a81f2d566c41e18a2e4d9dbf5a","abstract_canon_sha256":"b3e408470ba83936c8e94bf6e279f4b5efd6361ea003c16f272da0246df8cbde"},"schema_version":"1.0"},"canonical_sha256":"83beb15b82c7283887a6405bfeae1d6326c64e950f158471e02768765526095a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:08.238414Z","signature_b64":"lHrhAYCfwR4heLcTV20rBOL0RGTT0GiDUiQPS5L434pbPNO0XFu3tLiXCyIhf7hp5sd+2x+R9muOJgtOCoQ6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83beb15b82c7283887a6405bfeae1d6326c64e950f158471e02768765526095a","last_reissued_at":"2026-07-05T04:38:08.237954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:08.237954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.02824","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:38:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mgk8UVCF9+9ymhA3kbsBjZ6vMrYIjxsubYpbmk1e8jigAj0DRJMutAoSjROWu5BtsVugnrAhzOYailsf0RFSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:52:21.745061Z"},"content_sha256":"18c937d9813ba9e48e4a24bf894e58fa6b28b4bd2db2e6f2090f4833efbf2523","schema_version":"1.0","event_id":"sha256:18c937d9813ba9e48e4a24bf894e58fa6b28b4bd2db2e6f2090f4833efbf2523"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:QO7LCW4CY4UDRB5GIBN75LQ5MM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Strong Heuristics for Named Entity Linking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Akhil Arora, Andreas Spitz, Marko \\v{C}uljak, Robert West","submitted_at":"2022-07-06T17:29:30Z","abstract_excerpt":"Named entity linking (NEL) in news is a challenging endeavour due to the frequency of unseen and emerging entities, which necessitates the use of unsupervised or zero-shot methods. However, such methods tend to come with caveats, such as no integration of suitable knowledge bases (like Wikidata) for emerging entities, a lack of scalability, and poor interpretability. Here, we consider person disambiguation in Quotebank, a massive corpus of speaker-attributed quotations from the news, and investigate the suitability of intuitive, lightweight, and scalable heuristics for NEL in web-scale corpora"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.02824","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/2207.02824/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":"2026-07-05T04:38:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+NLhOOvVXe+riatus2Xjov0GyTwyqqZTIqZMW/BiHIkoV9Yr8FukoMY0CLErNzmhalae/R+tLcEH03GnZjZ+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:52:21.745726Z"},"content_sha256":"bf8f9b401177da1e4a91b184d9fe18e940220a6485080dbf7e27ea70ad2fbd58","schema_version":"1.0","event_id":"sha256:bf8f9b401177da1e4a91b184d9fe18e940220a6485080dbf7e27ea70ad2fbd58"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QO7LCW4CY4UDRB5GIBN75LQ5MM/bundle.json","state_url":"https://pith.science/pith/QO7LCW4CY4UDRB5GIBN75LQ5MM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QO7LCW4CY4UDRB5GIBN75LQ5MM/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":"2026-08-06T19:52:21Z","links":{"resolver":"https://pith.science/pith/QO7LCW4CY4UDRB5GIBN75LQ5MM","bundle":"https://pith.science/pith/QO7LCW4CY4UDRB5GIBN75LQ5MM/bundle.json","state":"https://pith.science/pith/QO7LCW4CY4UDRB5GIBN75LQ5MM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QO7LCW4CY4UDRB5GIBN75LQ5MM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QO7LCW4CY4UDRB5GIBN75LQ5MM","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":"b3e408470ba83936c8e94bf6e279f4b5efd6361ea003c16f272da0246df8cbde","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-06T17:29:30Z","title_canon_sha256":"50b542b24a49b0b723672abb7b9f3948fe08e2a81f2d566c41e18a2e4d9dbf5a"},"schema_version":"1.0","source":{"id":"2207.02824","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.02824","created_at":"2026-07-05T04:38:08Z"},{"alias_kind":"arxiv_version","alias_value":"2207.02824v1","created_at":"2026-07-05T04:38:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.02824","created_at":"2026-07-05T04:38:08Z"},{"alias_kind":"pith_short_12","alias_value":"QO7LCW4CY4UD","created_at":"2026-07-05T04:38:08Z"},{"alias_kind":"pith_short_16","alias_value":"QO7LCW4CY4UDRB5G","created_at":"2026-07-05T04:38:08Z"},{"alias_kind":"pith_short_8","alias_value":"QO7LCW4C","created_at":"2026-07-05T04:38:08Z"}],"graph_snapshots":[{"event_id":"sha256:bf8f9b401177da1e4a91b184d9fe18e940220a6485080dbf7e27ea70ad2fbd58","target":"graph","created_at":"2026-07-05T04:38:08Z","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/2207.02824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Named entity linking (NEL) in news is a challenging endeavour due to the frequency of unseen and emerging entities, which necessitates the use of unsupervised or zero-shot methods. However, such methods tend to come with caveats, such as no integration of suitable knowledge bases (like Wikidata) for emerging entities, a lack of scalability, and poor interpretability. Here, we consider person disambiguation in Quotebank, a massive corpus of speaker-attributed quotations from the news, and investigate the suitability of intuitive, lightweight, and scalable heuristics for NEL in web-scale corpora","authors_text":"Akhil Arora, Andreas Spitz, Marko \\v{C}uljak, Robert West","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-06T17:29:30Z","title":"Strong Heuristics for Named Entity Linking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.02824","kind":"arxiv","version":1},"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":"sha256:18c937d9813ba9e48e4a24bf894e58fa6b28b4bd2db2e6f2090f4833efbf2523","target":"record","created_at":"2026-07-05T04:38:08Z","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":"b3e408470ba83936c8e94bf6e279f4b5efd6361ea003c16f272da0246df8cbde","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-06T17:29:30Z","title_canon_sha256":"50b542b24a49b0b723672abb7b9f3948fe08e2a81f2d566c41e18a2e4d9dbf5a"},"schema_version":"1.0","source":{"id":"2207.02824","kind":"arxiv","version":1}},"canonical_sha256":"83beb15b82c7283887a6405bfeae1d6326c64e950f158471e02768765526095a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83beb15b82c7283887a6405bfeae1d6326c64e950f158471e02768765526095a","first_computed_at":"2026-07-05T04:38:08.237954Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:38:08.237954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lHrhAYCfwR4heLcTV20rBOL0RGTT0GiDUiQPS5L434pbPNO0XFu3tLiXCyIhf7hp5sd+2x+R9muOJgtOCoQ6Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:38:08.238414Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.02824","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18c937d9813ba9e48e4a24bf894e58fa6b28b4bd2db2e6f2090f4833efbf2523","sha256:bf8f9b401177da1e4a91b184d9fe18e940220a6485080dbf7e27ea70ad2fbd58"],"state_sha256":"46932dcd2224621656bad92266b71a909113ff932f3a93122ca5d2eccab9ad37"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eQrraulDHvt+Do6vXn6dRMOdb/AsFymPdqDoXjqKlSkHqVB8m7ghnHL8hKsNavD4iuciLlVhli2LXt+sGRDYCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:52:21.752011Z","bundle_sha256":"aab9a8ae082d592b14f55edbc15741d641e121a121c3b80634368a3edc849066"}}