{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RJUYEOKJEQCVZ4QGYQS4DQIWE3","short_pith_number":"pith:RJUYEOKJ","canonical_record":{"source":{"id":"2204.09589","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-03T17:55:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ac710e8c8f2e32bc58ad9e184fc0f4a79340687b374d6b40629f56b50b82de3c","abstract_canon_sha256":"fba10813027d23b454208340d86bc0d71eac823206d0dec91af7b26067815beb"},"schema_version":"1.0"},"canonical_sha256":"8a6982394924055cf206c425c1c11626d3b5497ecddbbca2fe85400c7d64aca1","source":{"kind":"arxiv","id":"2204.09589","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.09589","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"arxiv_version","alias_value":"2204.09589v1","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.09589","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"pith_short_12","alias_value":"RJUYEOKJEQCV","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"pith_short_16","alias_value":"RJUYEOKJEQCVZ4QG","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"pith_short_8","alias_value":"RJUYEOKJ","created_at":"2026-07-05T04:16:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RJUYEOKJEQCVZ4QGYQS4DQIWE3","target":"record","payload":{"canonical_record":{"source":{"id":"2204.09589","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-03T17:55:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ac710e8c8f2e32bc58ad9e184fc0f4a79340687b374d6b40629f56b50b82de3c","abstract_canon_sha256":"fba10813027d23b454208340d86bc0d71eac823206d0dec91af7b26067815beb"},"schema_version":"1.0"},"canonical_sha256":"8a6982394924055cf206c425c1c11626d3b5497ecddbbca2fe85400c7d64aca1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:31.940664Z","signature_b64":"iZm6FNGhvgs8ZtNwkcbAxzvj1OPxZI8s1h1fk68EgqOCckWyS+SszpVoIcDolomaAzNjZWR6GF9A5QFvt9dyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a6982394924055cf206c425c1c11626d3b5497ecddbbca2fe85400c7d64aca1","last_reissued_at":"2026-07-05T04:16:31.940261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:31.940261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.09589","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":"2026-07-05T04:16:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kTzln7wEe+H52GpfJ1yVbLlJfaRG565pHlPqlRtSjV8nTNn1wF1B6wVWjFsWrUKWU3Wa/Zzd4+Nv4yBH+a7VAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:37:59.060345Z"},"content_sha256":"aecbc4d4b0dc2e82c5db46edb77dc8734b7e2b9d1254d412357d2f36a29c2e4c","schema_version":"1.0","event_id":"sha256:aecbc4d4b0dc2e82c5db46edb77dc8734b7e2b9d1254d412357d2f36a29c2e4c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RJUYEOKJEQCVZ4QGYQS4DQIWE3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Kang Zhou, Qi Li, Yuepei Li","submitted_at":"2022-03-03T17:55:35Z","abstract_excerpt":"In this paper, we study the named entity recognition (NER) problem under distant supervision. Due to the incompleteness of the external dictionaries and/or knowledge bases, such distantly annotated training data usually suffer from a high false negative rate. To this end, we formulate the Distantly Supervised NER (DS-NER) problem via Multi-class Positive and Unlabeled (MPU) learning and propose a theoretically and practically novel CONFidence-based MPU (Conf-MPU) approach. To handle the incomplete annotations, Conf-MPU consists of two steps. First, a confidence score is estimated for each toke"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.09589","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/2204.09589/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":"2026-07-05T04:16:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OKc9Z1mOGO+yjJwpkv/4kltfws457v6ZkjC1i2qEVT0YGjjPd5lNAwxszvzHf2uKI3D2ZuVG/GHYfoM5w/uFAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:37:59.060995Z"},"content_sha256":"ca6f0e7364f46873088a504d21ed51febb405163a0246dd9ba773ba5c19bcf0a","schema_version":"1.0","event_id":"sha256:ca6f0e7364f46873088a504d21ed51febb405163a0246dd9ba773ba5c19bcf0a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJUYEOKJEQCVZ4QGYQS4DQIWE3/bundle.json","state_url":"https://pith.science/pith/RJUYEOKJEQCVZ4QGYQS4DQIWE3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJUYEOKJEQCVZ4QGYQS4DQIWE3/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":"2026-08-19T08:37:59Z","links":{"resolver":"https://pith.science/pith/RJUYEOKJEQCVZ4QGYQS4DQIWE3","bundle":"https://pith.science/pith/RJUYEOKJEQCVZ4QGYQS4DQIWE3/bundle.json","state":"https://pith.science/pith/RJUYEOKJEQCVZ4QGYQS4DQIWE3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJUYEOKJEQCVZ4QGYQS4DQIWE3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RJUYEOKJEQCVZ4QGYQS4DQIWE3","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":"fba10813027d23b454208340d86bc0d71eac823206d0dec91af7b26067815beb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-03T17:55:35Z","title_canon_sha256":"ac710e8c8f2e32bc58ad9e184fc0f4a79340687b374d6b40629f56b50b82de3c"},"schema_version":"1.0","source":{"id":"2204.09589","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.09589","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"arxiv_version","alias_value":"2204.09589v1","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.09589","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"pith_short_12","alias_value":"RJUYEOKJEQCV","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"pith_short_16","alias_value":"RJUYEOKJEQCVZ4QG","created_at":"2026-07-05T04:16:31Z"},{"alias_kind":"pith_short_8","alias_value":"RJUYEOKJ","created_at":"2026-07-05T04:16:31Z"}],"graph_snapshots":[{"event_id":"sha256:ca6f0e7364f46873088a504d21ed51febb405163a0246dd9ba773ba5c19bcf0a","target":"graph","created_at":"2026-07-05T04:16:31Z","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/2204.09589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study the named entity recognition (NER) problem under distant supervision. Due to the incompleteness of the external dictionaries and/or knowledge bases, such distantly annotated training data usually suffer from a high false negative rate. To this end, we formulate the Distantly Supervised NER (DS-NER) problem via Multi-class Positive and Unlabeled (MPU) learning and propose a theoretically and practically novel CONFidence-based MPU (Conf-MPU) approach. To handle the incomplete annotations, Conf-MPU consists of two steps. First, a confidence score is estimated for each toke","authors_text":"Kang Zhou, Qi Li, Yuepei Li","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-03T17:55:35Z","title":"Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.09589","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:aecbc4d4b0dc2e82c5db46edb77dc8734b7e2b9d1254d412357d2f36a29c2e4c","target":"record","created_at":"2026-07-05T04:16:31Z","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":"fba10813027d23b454208340d86bc0d71eac823206d0dec91af7b26067815beb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-03T17:55:35Z","title_canon_sha256":"ac710e8c8f2e32bc58ad9e184fc0f4a79340687b374d6b40629f56b50b82de3c"},"schema_version":"1.0","source":{"id":"2204.09589","kind":"arxiv","version":1}},"canonical_sha256":"8a6982394924055cf206c425c1c11626d3b5497ecddbbca2fe85400c7d64aca1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a6982394924055cf206c425c1c11626d3b5497ecddbbca2fe85400c7d64aca1","first_computed_at":"2026-07-05T04:16:31.940261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:16:31.940261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iZm6FNGhvgs8ZtNwkcbAxzvj1OPxZI8s1h1fk68EgqOCckWyS+SszpVoIcDolomaAzNjZWR6GF9A5QFvt9dyDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:16:31.940664Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.09589","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aecbc4d4b0dc2e82c5db46edb77dc8734b7e2b9d1254d412357d2f36a29c2e4c","sha256:ca6f0e7364f46873088a504d21ed51febb405163a0246dd9ba773ba5c19bcf0a"],"state_sha256":"157daac1bc60e08a0e6bc1612bd4e1622cce478b54ba2812e5500698915ef33b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gSYDQaRDXw43Od6mKthnoQenjlbLghvVZIR1Of4SX7KhdvgEumqf84AqBdOjf/Hj8Ghtc8zxw9RGVBLLPSMDCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T08:37:59.065604Z","bundle_sha256":"98c05a0e9bb277e4ea01bfbbd697fd293df967f9b367d4fc068361822c54b4a4"}}