{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RWJPHC6XQCXKKTYAQZLY25VLXN","short_pith_number":"pith:RWJPHC6X","canonical_record":{"source":{"id":"2305.13191","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T16:23:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e134e9ed79eb482f971e59a95af5269a211d03557af91825e0ac9870fd710da1","abstract_canon_sha256":"f44e30a74325a4230475fa02694aa9982d9d31eabc0efbc700512a9716e0f02e"},"schema_version":"1.0"},"canonical_sha256":"8d92f38bd780aea54f0086578d76abbb478d86a62d084561281dff7b211c3ec6","source":{"kind":"arxiv","id":"2305.13191","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13191","created_at":"2026-07-05T06:12:27Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13191v1","created_at":"2026-07-05T06:12:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13191","created_at":"2026-07-05T06:12:27Z"},{"alias_kind":"pith_short_12","alias_value":"RWJPHC6XQCXK","created_at":"2026-07-05T06:12:27Z"},{"alias_kind":"pith_short_16","alias_value":"RWJPHC6XQCXKKTYA","created_at":"2026-07-05T06:12:27Z"},{"alias_kind":"pith_short_8","alias_value":"RWJPHC6X","created_at":"2026-07-05T06:12:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RWJPHC6XQCXKKTYAQZLY25VLXN","target":"record","payload":{"canonical_record":{"source":{"id":"2305.13191","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T16:23:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e134e9ed79eb482f971e59a95af5269a211d03557af91825e0ac9870fd710da1","abstract_canon_sha256":"f44e30a74325a4230475fa02694aa9982d9d31eabc0efbc700512a9716e0f02e"},"schema_version":"1.0"},"canonical_sha256":"8d92f38bd780aea54f0086578d76abbb478d86a62d084561281dff7b211c3ec6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:27.350549Z","signature_b64":"7iNxLLEEJTYdFX5GZBsqPux9/Rm4PHPQHCo5rn9Neo5rKjbZQJKcMNmZz3tOYBxkg4fXEnrePAC1pV2nHY8GAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d92f38bd780aea54f0086578d76abbb478d86a62d084561281dff7b211c3ec6","last_reissued_at":"2026-07-05T06:12:27.350095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:27.350095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.13191","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":"2026-07-05T06:12:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bX1J3SB2ALnzeRgDPpSDOzEfnLf9Jxs22XoN+cI2fztZdQTCuNu/QdMZ38ezDzQ9bi3qTSzZS8zqQ4zptVg9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:12:31.924093Z"},"content_sha256":"f7f4e9b998e66e7f6de00a01448304c4e44dbb318ff930460dc6ab183e1b9fab","schema_version":"1.0","event_id":"sha256:f7f4e9b998e66e7f6de00a01448304c4e44dbb318ff930460dc6ab183e1b9fab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RWJPHC6XQCXKKTYAQZLY25VLXN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Taxonomy Expansion for Named Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dan Roth, Giovanni Paolini, Jie Ma, Karthikeyan K, Miguel Ballesteros, Neha Anna John, Shuai Wang, Vittorio Castelli, Yassine Benajiba, Yogarshi Vyas","submitted_at":"2023-05-22T16:23:46Z","abstract_excerpt":"Training a Named Entity Recognition (NER) model often involves fixing a taxonomy of entity types. However, requirements evolve and we might need the NER model to recognize additional entity types. A simple approach is to re-annotate entire dataset with both existing and additional entity types and then train the model on the re-annotated dataset. However, this is an extremely laborious task. To remedy this, we propose a novel approach called Partial Label Model (PLM) that uses only partially annotated datasets. We experiment with 6 diverse datasets and show that PLM consistently performs bette"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13191","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/2305.13191/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":"2026-07-05T06:12:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wiXK/+C1ePfvEhibiz+SgIw7YkS5A38KriRhdgdjgB8//cFj9jZ/vaYzIaGsSPVV5B7n6msa66+ctr28SzyZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:12:31.924588Z"},"content_sha256":"96256c9c8fd12ac0d62b2bda9ad561db88f7ca8477cf0f6d3827bac080348561","schema_version":"1.0","event_id":"sha256:96256c9c8fd12ac0d62b2bda9ad561db88f7ca8477cf0f6d3827bac080348561"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RWJPHC6XQCXKKTYAQZLY25VLXN/bundle.json","state_url":"https://pith.science/pith/RWJPHC6XQCXKKTYAQZLY25VLXN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RWJPHC6XQCXKKTYAQZLY25VLXN/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":"2026-08-19T14:12:31Z","links":{"resolver":"https://pith.science/pith/RWJPHC6XQCXKKTYAQZLY25VLXN","bundle":"https://pith.science/pith/RWJPHC6XQCXKKTYAQZLY25VLXN/bundle.json","state":"https://pith.science/pith/RWJPHC6XQCXKKTYAQZLY25VLXN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RWJPHC6XQCXKKTYAQZLY25VLXN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RWJPHC6XQCXKKTYAQZLY25VLXN","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":"f44e30a74325a4230475fa02694aa9982d9d31eabc0efbc700512a9716e0f02e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T16:23:46Z","title_canon_sha256":"e134e9ed79eb482f971e59a95af5269a211d03557af91825e0ac9870fd710da1"},"schema_version":"1.0","source":{"id":"2305.13191","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13191","created_at":"2026-07-05T06:12:27Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13191v1","created_at":"2026-07-05T06:12:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13191","created_at":"2026-07-05T06:12:27Z"},{"alias_kind":"pith_short_12","alias_value":"RWJPHC6XQCXK","created_at":"2026-07-05T06:12:27Z"},{"alias_kind":"pith_short_16","alias_value":"RWJPHC6XQCXKKTYA","created_at":"2026-07-05T06:12:27Z"},{"alias_kind":"pith_short_8","alias_value":"RWJPHC6X","created_at":"2026-07-05T06:12:27Z"}],"graph_snapshots":[{"event_id":"sha256:96256c9c8fd12ac0d62b2bda9ad561db88f7ca8477cf0f6d3827bac080348561","target":"graph","created_at":"2026-07-05T06:12:27Z","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/2305.13191/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training a Named Entity Recognition (NER) model often involves fixing a taxonomy of entity types. However, requirements evolve and we might need the NER model to recognize additional entity types. A simple approach is to re-annotate entire dataset with both existing and additional entity types and then train the model on the re-annotated dataset. However, this is an extremely laborious task. To remedy this, we propose a novel approach called Partial Label Model (PLM) that uses only partially annotated datasets. We experiment with 6 diverse datasets and show that PLM consistently performs bette","authors_text":"Dan Roth, Giovanni Paolini, Jie Ma, Karthikeyan K, Miguel Ballesteros, Neha Anna John, Shuai Wang, Vittorio Castelli, Yassine Benajiba, Yogarshi Vyas","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T16:23:46Z","title":"Taxonomy Expansion for Named Entity Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13191","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:f7f4e9b998e66e7f6de00a01448304c4e44dbb318ff930460dc6ab183e1b9fab","target":"record","created_at":"2026-07-05T06:12:27Z","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":"f44e30a74325a4230475fa02694aa9982d9d31eabc0efbc700512a9716e0f02e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-22T16:23:46Z","title_canon_sha256":"e134e9ed79eb482f971e59a95af5269a211d03557af91825e0ac9870fd710da1"},"schema_version":"1.0","source":{"id":"2305.13191","kind":"arxiv","version":1}},"canonical_sha256":"8d92f38bd780aea54f0086578d76abbb478d86a62d084561281dff7b211c3ec6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d92f38bd780aea54f0086578d76abbb478d86a62d084561281dff7b211c3ec6","first_computed_at":"2026-07-05T06:12:27.350095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:27.350095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7iNxLLEEJTYdFX5GZBsqPux9/Rm4PHPQHCo5rn9Neo5rKjbZQJKcMNmZz3tOYBxkg4fXEnrePAC1pV2nHY8GAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:27.350549Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13191","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7f4e9b998e66e7f6de00a01448304c4e44dbb318ff930460dc6ab183e1b9fab","sha256:96256c9c8fd12ac0d62b2bda9ad561db88f7ca8477cf0f6d3827bac080348561"],"state_sha256":"d5dd41c75c33e0325cf30d8d82ac1397c6d06535940bc99c3761ddf79d6743ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5xGOtgI/9jCkq+YYj4LOnPMzPt73nAQ6FZHbPcNtfhjPFvAq0IgXZXyCYv245nacl4MeOd394fxZUUQs9VuQCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T14:12:31.929296Z","bundle_sha256":"417237f58f21ce53007ff5881c559598ffdfe05ffde7f9df05c7fbdc21f9f1d4"}}