{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XCPS4RAQPHUXTDOS7IQGT4SNJH","short_pith_number":"pith:XCPS4RAQ","canonical_record":{"source":{"id":"2105.12848","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-26T21:18:48Z","cross_cats_sorted":[],"title_canon_sha256":"ff715d0fcb35dd383b7d03cd1073256c56ae877082a62bcf87112024388c2c71","abstract_canon_sha256":"709627bc4bdfffcb64e479e0e958f27d073af28ab513e67c3a2e27e0ef1bd11d"},"schema_version":"1.0"},"canonical_sha256":"b89f2e441079e9798dd2fa2069f24d49e2ec545f141b5295ea1d8e0784ec8796","source":{"kind":"arxiv","id":"2105.12848","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.12848","created_at":"2026-07-05T02:44:38Z"},{"alias_kind":"arxiv_version","alias_value":"2105.12848v2","created_at":"2026-07-05T02:44:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.12848","created_at":"2026-07-05T02:44:38Z"},{"alias_kind":"pith_short_12","alias_value":"XCPS4RAQPHUX","created_at":"2026-07-05T02:44:38Z"},{"alias_kind":"pith_short_16","alias_value":"XCPS4RAQPHUXTDOS","created_at":"2026-07-05T02:44:38Z"},{"alias_kind":"pith_short_8","alias_value":"XCPS4RAQ","created_at":"2026-07-05T02:44:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XCPS4RAQPHUXTDOS7IQGT4SNJH","target":"record","payload":{"canonical_record":{"source":{"id":"2105.12848","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-26T21:18:48Z","cross_cats_sorted":[],"title_canon_sha256":"ff715d0fcb35dd383b7d03cd1073256c56ae877082a62bcf87112024388c2c71","abstract_canon_sha256":"709627bc4bdfffcb64e479e0e958f27d073af28ab513e67c3a2e27e0ef1bd11d"},"schema_version":"1.0"},"canonical_sha256":"b89f2e441079e9798dd2fa2069f24d49e2ec545f141b5295ea1d8e0784ec8796","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:38.142811Z","signature_b64":"0yOWEOQf0+MGDQ/0+xhWNY8m9WU8UkQSz6N1aaqYlQSF/BflMQmdi7B5oXyc7GVrn4r8mVAnLsMZABBkMdvmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b89f2e441079e9798dd2fa2069f24d49e2ec545f141b5295ea1d8e0784ec8796","last_reissued_at":"2026-07-05T02:44:38.142288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:38.142288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.12848","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":"2026-07-05T02:44:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HatuxK9KOYhgUKrkJKtM4uOo62lgFAOREMRKLb7HtzaGqjKqtOjaAR+QZI/dTRKeLHstpFAU1mP9BNdubvlXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:43:16.576255Z"},"content_sha256":"8268d522cc0324bce709a18e442cf4393a7766e0e19ec4248dc22f1608d34c2b","schema_version":"1.0","event_id":"sha256:8268d522cc0324bce709a18e442cf4393a7766e0e19ec4248dc22f1608d34c2b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XCPS4RAQPHUXTDOS7IQGT4SNJH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Zhang, Le Song, Lucas Liu, Pranav Shetty, Yinghao Li","submitted_at":"2021-05-26T21:18:48Z","abstract_excerpt":"We study the problem of learning a named entity recognition (NER) tagger using noisy labels from multiple weak supervision sources. Though cheap to obtain, the labels from weak supervision sources are often incomplete, inaccurate, and contradictory, making it difficult to learn an accurate NER model. To address this challenge, we propose a conditional hidden Markov model (CHMM), which can effectively infer true labels from multi-source noisy labels in an unsupervised way. CHMM enhances the classic hidden Markov model with the contextual representation power of pre-trained language models. Spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.12848","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/2105.12848/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":"2026-07-05T02:44:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l6v19cYZqJv8I8WMTyyNu7DOsM5v+Xpaegc0qEhlY3xoFzQKsjUdOPFy1MprIn+mlXsWFXIYQiRV3WGnERdSDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:43:16.576655Z"},"content_sha256":"fd1af7bf0b364aebeaf8d7a57071b7dfed01f385b4ed9083dcfc1b85d0e0efa1","schema_version":"1.0","event_id":"sha256:fd1af7bf0b364aebeaf8d7a57071b7dfed01f385b4ed9083dcfc1b85d0e0efa1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XCPS4RAQPHUXTDOS7IQGT4SNJH/bundle.json","state_url":"https://pith.science/pith/XCPS4RAQPHUXTDOS7IQGT4SNJH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XCPS4RAQPHUXTDOS7IQGT4SNJH/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":"2026-07-06T17:43:16Z","links":{"resolver":"https://pith.science/pith/XCPS4RAQPHUXTDOS7IQGT4SNJH","bundle":"https://pith.science/pith/XCPS4RAQPHUXTDOS7IQGT4SNJH/bundle.json","state":"https://pith.science/pith/XCPS4RAQPHUXTDOS7IQGT4SNJH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XCPS4RAQPHUXTDOS7IQGT4SNJH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XCPS4RAQPHUXTDOS7IQGT4SNJH","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":"709627bc4bdfffcb64e479e0e958f27d073af28ab513e67c3a2e27e0ef1bd11d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-26T21:18:48Z","title_canon_sha256":"ff715d0fcb35dd383b7d03cd1073256c56ae877082a62bcf87112024388c2c71"},"schema_version":"1.0","source":{"id":"2105.12848","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.12848","created_at":"2026-07-05T02:44:38Z"},{"alias_kind":"arxiv_version","alias_value":"2105.12848v2","created_at":"2026-07-05T02:44:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.12848","created_at":"2026-07-05T02:44:38Z"},{"alias_kind":"pith_short_12","alias_value":"XCPS4RAQPHUX","created_at":"2026-07-05T02:44:38Z"},{"alias_kind":"pith_short_16","alias_value":"XCPS4RAQPHUXTDOS","created_at":"2026-07-05T02:44:38Z"},{"alias_kind":"pith_short_8","alias_value":"XCPS4RAQ","created_at":"2026-07-05T02:44:38Z"}],"graph_snapshots":[{"event_id":"sha256:fd1af7bf0b364aebeaf8d7a57071b7dfed01f385b4ed9083dcfc1b85d0e0efa1","target":"graph","created_at":"2026-07-05T02:44:38Z","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/2105.12848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of learning a named entity recognition (NER) tagger using noisy labels from multiple weak supervision sources. Though cheap to obtain, the labels from weak supervision sources are often incomplete, inaccurate, and contradictory, making it difficult to learn an accurate NER model. To address this challenge, we propose a conditional hidden Markov model (CHMM), which can effectively infer true labels from multi-source noisy labels in an unsupervised way. CHMM enhances the classic hidden Markov model with the contextual representation power of pre-trained language models. Spec","authors_text":"Chao Zhang, Le Song, Lucas Liu, Pranav Shetty, Yinghao Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-26T21:18:48Z","title":"BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.12848","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":"sha256:8268d522cc0324bce709a18e442cf4393a7766e0e19ec4248dc22f1608d34c2b","target":"record","created_at":"2026-07-05T02:44:38Z","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":"709627bc4bdfffcb64e479e0e958f27d073af28ab513e67c3a2e27e0ef1bd11d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-26T21:18:48Z","title_canon_sha256":"ff715d0fcb35dd383b7d03cd1073256c56ae877082a62bcf87112024388c2c71"},"schema_version":"1.0","source":{"id":"2105.12848","kind":"arxiv","version":2}},"canonical_sha256":"b89f2e441079e9798dd2fa2069f24d49e2ec545f141b5295ea1d8e0784ec8796","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b89f2e441079e9798dd2fa2069f24d49e2ec545f141b5295ea1d8e0784ec8796","first_computed_at":"2026-07-05T02:44:38.142288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:44:38.142288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0yOWEOQf0+MGDQ/0+xhWNY8m9WU8UkQSz6N1aaqYlQSF/BflMQmdi7B5oXyc7GVrn4r8mVAnLsMZABBkMdvmCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:44:38.142811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.12848","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8268d522cc0324bce709a18e442cf4393a7766e0e19ec4248dc22f1608d34c2b","sha256:fd1af7bf0b364aebeaf8d7a57071b7dfed01f385b4ed9083dcfc1b85d0e0efa1"],"state_sha256":"7585a2918aad2a8a58fcae7e61b3e42f7bb1bbc4baf2a077e1d0cb6e30ff69ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kQimB2zjkIP88ziaz96ZqZbqygIWQ7x9QGSk/Be1u/eONVeqZWDP47qSx84pvsiQFSD97zp3zG98gSTe9GBwCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:43:16.578897Z","bundle_sha256":"8ebe55d3d9ebab7be9a9eee16359907739434874c4f6b8acafd5282897146a33"}}