{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:N3I75TNCSALP3T2YFLNIZNLQTI","short_pith_number":"pith:N3I75TNC","canonical_record":{"source":{"id":"2208.14565","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-30T23:19:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"483345edba81f598d7bbdf8ed720e999613a7266ef17115ad44c4d86be86d626","abstract_canon_sha256":"507d0341fda11cd46d1b9b58730bf42a2ea89ef2384df3480b866ad86bdcaa44"},"schema_version":"1.0"},"canonical_sha256":"6ed1fecda29016fdcf582ada8cb5709a13bf90c344e6756bbc81ba7ec50b76ff","source":{"kind":"arxiv","id":"2208.14565","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.14565","created_at":"2026-07-05T05:44:50Z"},{"alias_kind":"arxiv_version","alias_value":"2208.14565v2","created_at":"2026-07-05T05:44:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.14565","created_at":"2026-07-05T05:44:50Z"},{"alias_kind":"pith_short_12","alias_value":"N3I75TNCSALP","created_at":"2026-07-05T05:44:50Z"},{"alias_kind":"pith_short_16","alias_value":"N3I75TNCSALP3T2Y","created_at":"2026-07-05T05:44:50Z"},{"alias_kind":"pith_short_8","alias_value":"N3I75TNC","created_at":"2026-07-05T05:44:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:N3I75TNCSALP3T2YFLNIZNLQTI","target":"record","payload":{"canonical_record":{"source":{"id":"2208.14565","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-30T23:19:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"483345edba81f598d7bbdf8ed720e999613a7266ef17115ad44c4d86be86d626","abstract_canon_sha256":"507d0341fda11cd46d1b9b58730bf42a2ea89ef2384df3480b866ad86bdcaa44"},"schema_version":"1.0"},"canonical_sha256":"6ed1fecda29016fdcf582ada8cb5709a13bf90c344e6756bbc81ba7ec50b76ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:44:50.030423Z","signature_b64":"Om9RysClHE78af9RuSjE6Fx750Qd2nSo+MYCYAPs3wWqKei0I7DkEhdBeQPFIs9w0+B6eCA79tY2kAGeQg1kDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ed1fecda29016fdcf582ada8cb5709a13bf90c344e6756bbc81ba7ec50b76ff","last_reissued_at":"2026-07-05T05:44:50.029985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:44:50.029985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.14565","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:44:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BR4B852xoFav+AMN2IbdaI/Mat/MFltnFnOkx7Dx5pvSFPpVUCOx1h7N6AfFyneWlzYubNbTXgiVbFMV/yDcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:35:19.021853Z"},"content_sha256":"37b26d148c66f56d21b6035825ff815acdde0a33b9741ecee1e941ce59f4324c","schema_version":"1.0","event_id":"sha256:37b26d148c66f56d21b6035825ff815acdde0a33b9741ecee1e941ce59f4324c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:N3I75TNCSALP3T2YFLNIZNLQTI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hao Cheng, Hoifung Poon, Jianfeng Gao, Sheng Zhang","submitted_at":"2022-08-30T23:19:04Z","abstract_excerpt":"We present a bi-encoder framework for named entity recognition (NER), which applies contrastive learning to map candidate text spans and entity types into the same vector representation space. Prior work predominantly approaches NER as sequence labeling or span classification. We instead frame NER as a representation learning problem that maximizes the similarity between the vector representations of an entity mention and its type. This makes it easy to handle nested and flat NER alike, and can better leverage noisy self-supervision signals. A major challenge to this bi-encoder formulation for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.14565","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/2208.14565/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":"2026-07-05T05:44:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FIc+1wPpOarzTaOuykOIV4iO8f+ybOkQYIyiutuis9yK9yio6OjLnu2Tfv/lvPy3FLAbXGM8rC3jL4eCCF8GBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:35:19.022341Z"},"content_sha256":"a486dd55270240a08b6e78a12e3a6af4f2ba29e44a833e91782e82cb7a0f1bd8","schema_version":"1.0","event_id":"sha256:a486dd55270240a08b6e78a12e3a6af4f2ba29e44a833e91782e82cb7a0f1bd8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N3I75TNCSALP3T2YFLNIZNLQTI/bundle.json","state_url":"https://pith.science/pith/N3I75TNCSALP3T2YFLNIZNLQTI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N3I75TNCSALP3T2YFLNIZNLQTI/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":"2026-08-06T16:35:19Z","links":{"resolver":"https://pith.science/pith/N3I75TNCSALP3T2YFLNIZNLQTI","bundle":"https://pith.science/pith/N3I75TNCSALP3T2YFLNIZNLQTI/bundle.json","state":"https://pith.science/pith/N3I75TNCSALP3T2YFLNIZNLQTI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N3I75TNCSALP3T2YFLNIZNLQTI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:N3I75TNCSALP3T2YFLNIZNLQTI","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":"507d0341fda11cd46d1b9b58730bf42a2ea89ef2384df3480b866ad86bdcaa44","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-30T23:19:04Z","title_canon_sha256":"483345edba81f598d7bbdf8ed720e999613a7266ef17115ad44c4d86be86d626"},"schema_version":"1.0","source":{"id":"2208.14565","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.14565","created_at":"2026-07-05T05:44:50Z"},{"alias_kind":"arxiv_version","alias_value":"2208.14565v2","created_at":"2026-07-05T05:44:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.14565","created_at":"2026-07-05T05:44:50Z"},{"alias_kind":"pith_short_12","alias_value":"N3I75TNCSALP","created_at":"2026-07-05T05:44:50Z"},{"alias_kind":"pith_short_16","alias_value":"N3I75TNCSALP3T2Y","created_at":"2026-07-05T05:44:50Z"},{"alias_kind":"pith_short_8","alias_value":"N3I75TNC","created_at":"2026-07-05T05:44:50Z"}],"graph_snapshots":[{"event_id":"sha256:a486dd55270240a08b6e78a12e3a6af4f2ba29e44a833e91782e82cb7a0f1bd8","target":"graph","created_at":"2026-07-05T05:44:50Z","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/2208.14565/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a bi-encoder framework for named entity recognition (NER), which applies contrastive learning to map candidate text spans and entity types into the same vector representation space. Prior work predominantly approaches NER as sequence labeling or span classification. We instead frame NER as a representation learning problem that maximizes the similarity between the vector representations of an entity mention and its type. This makes it easy to handle nested and flat NER alike, and can better leverage noisy self-supervision signals. A major challenge to this bi-encoder formulation for","authors_text":"Hao Cheng, Hoifung Poon, Jianfeng Gao, Sheng Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-30T23:19:04Z","title":"Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.14565","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":"sha256:37b26d148c66f56d21b6035825ff815acdde0a33b9741ecee1e941ce59f4324c","target":"record","created_at":"2026-07-05T05:44:50Z","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":"507d0341fda11cd46d1b9b58730bf42a2ea89ef2384df3480b866ad86bdcaa44","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-30T23:19:04Z","title_canon_sha256":"483345edba81f598d7bbdf8ed720e999613a7266ef17115ad44c4d86be86d626"},"schema_version":"1.0","source":{"id":"2208.14565","kind":"arxiv","version":2}},"canonical_sha256":"6ed1fecda29016fdcf582ada8cb5709a13bf90c344e6756bbc81ba7ec50b76ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ed1fecda29016fdcf582ada8cb5709a13bf90c344e6756bbc81ba7ec50b76ff","first_computed_at":"2026-07-05T05:44:50.029985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:44:50.029985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Om9RysClHE78af9RuSjE6Fx750Qd2nSo+MYCYAPs3wWqKei0I7DkEhdBeQPFIs9w0+B6eCA79tY2kAGeQg1kDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:44:50.030423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.14565","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37b26d148c66f56d21b6035825ff815acdde0a33b9741ecee1e941ce59f4324c","sha256:a486dd55270240a08b6e78a12e3a6af4f2ba29e44a833e91782e82cb7a0f1bd8"],"state_sha256":"c8b5950a650d8a13ad0be3201159b2b90aca74a860435b1983712ca3d82eb278"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fUehzCHng877cWKksPeF9T3+1UY80ybSAawJVwbjgxvj9738n55Id0gDfIFJwzIywMBt8BxdjpJ+R92OEVtXAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:35:19.026661Z","bundle_sha256":"3da6eb48d796763fd66ec46d322581411f463f35587ea007dc9d214a71fc0a49"}}