{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ASPRFIBDK4FR5J63KO4IRCH4L2","short_pith_number":"pith:ASPRFIBD","canonical_record":{"source":{"id":"2310.16225","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T22:34:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a3817d430259dbff9b42d5552f9ed13223e168efc28c47bef760c07f39bec3e3","abstract_canon_sha256":"863a4b36123951659e408fef82c5eb7259cd692f9d343a9ec850acbdbf62fc57"},"schema_version":"1.0"},"canonical_sha256":"049f12a023570b1ea7db53b88888fc5eb71225f49da884d9900f5f7944ed6a8e","source":{"kind":"arxiv","id":"2310.16225","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16225","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16225v1","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16225","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"ASPRFIBDK4FR","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"ASPRFIBDK4FR5J63","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"ASPRFIBD","created_at":"2026-07-05T07:04:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ASPRFIBDK4FR5J63KO4IRCH4L2","target":"record","payload":{"canonical_record":{"source":{"id":"2310.16225","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T22:34:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a3817d430259dbff9b42d5552f9ed13223e168efc28c47bef760c07f39bec3e3","abstract_canon_sha256":"863a4b36123951659e408fef82c5eb7259cd692f9d343a9ec850acbdbf62fc57"},"schema_version":"1.0"},"canonical_sha256":"049f12a023570b1ea7db53b88888fc5eb71225f49da884d9900f5f7944ed6a8e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:54.169963Z","signature_b64":"zuiMwXTNhKG8JyKEmJUk+2k5K1jr8i1SFfdex9J5ls9PlMGtI3e2CDG/KnnX6KDS73r8dtFBbW2AlGqTM0gmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"049f12a023570b1ea7db53b88888fc5eb71225f49da884d9900f5f7944ed6a8e","last_reissued_at":"2026-07-05T07:04:54.169577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:54.169577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.16225","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":"2026-07-05T07:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nGyIX9l0V7utG6vKs+8D1xpxdW670Q3BIsB+PV0AGldKP6kGYjXHvn/ldMpjMRbYXd+IziSq8lBIpkWVbOUAAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:48:41.882091Z"},"content_sha256":"31bcb59150d472244da24e3ec08b02a6e79ea09410bd0fab87b9030abbedc2f8","schema_version":"1.0","event_id":"sha256:31bcb59150d472244da24e3ec08b02a6e79ea09410bd0fab87b9030abbedc2f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ASPRFIBDK4FR5J63KO4IRCH4L2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CleanCoNLL: A Nearly Noise-Free Named Entity Recognition Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alan Akbik, Susanna R\\\"ucker","submitted_at":"2023-10-24T22:34:43Z","abstract_excerpt":"The CoNLL-03 corpus is arguably the most well-known and utilized benchmark dataset for named entity recognition (NER). However, prior works found significant numbers of annotation errors, incompleteness, and inconsistencies in the data. This poses challenges to objectively comparing NER approaches and analyzing their errors, as current state-of-the-art models achieve F1-scores that are comparable to or even exceed the estimated noise level in CoNLL-03. To address this issue, we present a comprehensive relabeling effort assisted by automatic consistency checking that corrects 7.0% of all labels"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16225","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/2310.16225/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":"2026-07-05T07:04:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bcWSWEp1wuGjLi4FoikohYPa0LlT+/cTVh9dkEQyYrPJ5lxZVR52jR5uveA3291LdaHaDkFO+Zmk2fIL5+j8Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:48:41.882481Z"},"content_sha256":"7e4092e1893da07a444d36c32eadc87f6ea03d3c1de05a53a1399f73fc9fbcaf","schema_version":"1.0","event_id":"sha256:7e4092e1893da07a444d36c32eadc87f6ea03d3c1de05a53a1399f73fc9fbcaf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ASPRFIBDK4FR5J63KO4IRCH4L2/bundle.json","state_url":"https://pith.science/pith/ASPRFIBDK4FR5J63KO4IRCH4L2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ASPRFIBDK4FR5J63KO4IRCH4L2/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":"2026-08-07T23:48:41Z","links":{"resolver":"https://pith.science/pith/ASPRFIBDK4FR5J63KO4IRCH4L2","bundle":"https://pith.science/pith/ASPRFIBDK4FR5J63KO4IRCH4L2/bundle.json","state":"https://pith.science/pith/ASPRFIBDK4FR5J63KO4IRCH4L2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ASPRFIBDK4FR5J63KO4IRCH4L2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ASPRFIBDK4FR5J63KO4IRCH4L2","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":"863a4b36123951659e408fef82c5eb7259cd692f9d343a9ec850acbdbf62fc57","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T22:34:43Z","title_canon_sha256":"a3817d430259dbff9b42d5552f9ed13223e168efc28c47bef760c07f39bec3e3"},"schema_version":"1.0","source":{"id":"2310.16225","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16225","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16225v1","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16225","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"ASPRFIBDK4FR","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"ASPRFIBDK4FR5J63","created_at":"2026-07-05T07:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"ASPRFIBD","created_at":"2026-07-05T07:04:54Z"}],"graph_snapshots":[{"event_id":"sha256:7e4092e1893da07a444d36c32eadc87f6ea03d3c1de05a53a1399f73fc9fbcaf","target":"graph","created_at":"2026-07-05T07:04:54Z","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/2310.16225/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The CoNLL-03 corpus is arguably the most well-known and utilized benchmark dataset for named entity recognition (NER). However, prior works found significant numbers of annotation errors, incompleteness, and inconsistencies in the data. This poses challenges to objectively comparing NER approaches and analyzing their errors, as current state-of-the-art models achieve F1-scores that are comparable to or even exceed the estimated noise level in CoNLL-03. To address this issue, we present a comprehensive relabeling effort assisted by automatic consistency checking that corrects 7.0% of all labels","authors_text":"Alan Akbik, Susanna R\\\"ucker","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T22:34:43Z","title":"CleanCoNLL: A Nearly Noise-Free Named Entity Recognition Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16225","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":"sha256:31bcb59150d472244da24e3ec08b02a6e79ea09410bd0fab87b9030abbedc2f8","target":"record","created_at":"2026-07-05T07:04:54Z","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":"863a4b36123951659e408fef82c5eb7259cd692f9d343a9ec850acbdbf62fc57","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T22:34:43Z","title_canon_sha256":"a3817d430259dbff9b42d5552f9ed13223e168efc28c47bef760c07f39bec3e3"},"schema_version":"1.0","source":{"id":"2310.16225","kind":"arxiv","version":1}},"canonical_sha256":"049f12a023570b1ea7db53b88888fc5eb71225f49da884d9900f5f7944ed6a8e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"049f12a023570b1ea7db53b88888fc5eb71225f49da884d9900f5f7944ed6a8e","first_computed_at":"2026-07-05T07:04:54.169577Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:54.169577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zuiMwXTNhKG8JyKEmJUk+2k5K1jr8i1SFfdex9J5ls9PlMGtI3e2CDG/KnnX6KDS73r8dtFBbW2AlGqTM0gmBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:54.169963Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16225","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31bcb59150d472244da24e3ec08b02a6e79ea09410bd0fab87b9030abbedc2f8","sha256:7e4092e1893da07a444d36c32eadc87f6ea03d3c1de05a53a1399f73fc9fbcaf"],"state_sha256":"85a6cdfd8bdb49517639f3bfe69d41033058c4d8034ca9c0c56ab93c08d282fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6dqBPJ8xJFrTa7Rf19kEJfJSrIt1juY4WNav2qNzvfhdGW8Z1ouUNpXKHuc1zrX+UN9xTnTM1D86JT7ONVIIBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:48:41.885180Z","bundle_sha256":"ab15cb89b279efd65d0d6becee84b020ea37c38e5af77d0a63b5d1b19a788698"}}