{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NXXG4UKHFVQXUH4TA5LDX4BJFB","short_pith_number":"pith:NXXG4UKH","canonical_record":{"source":{"id":"1906.02124","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T10:33:08Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f8f29883c4217f22f12a5f365f40477ef4174dcbefbec1a3d2927f7974311f82","abstract_canon_sha256":"8d4af2f7ea9da11591563b416396af373908726d4c6367ccd97bf67f35932cc5"},"schema_version":"1.0"},"canonical_sha256":"6dee6e51472d617a1f9307563bf0292856a395a9c3740fa3edb2c88807e9ddb7","source":{"kind":"arxiv","id":"1906.02124","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.02124","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"arxiv_version","alias_value":"1906.02124v2","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02124","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"pith_short_12","alias_value":"NXXG4UKHFVQX","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NXXG4UKHFVQXUH4T","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NXXG4UKH","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NXXG4UKHFVQXUH4TA5LDX4BJFB","target":"record","payload":{"canonical_record":{"source":{"id":"1906.02124","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T10:33:08Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f8f29883c4217f22f12a5f365f40477ef4174dcbefbec1a3d2927f7974311f82","abstract_canon_sha256":"8d4af2f7ea9da11591563b416396af373908726d4c6367ccd97bf67f35932cc5"},"schema_version":"1.0"},"canonical_sha256":"6dee6e51472d617a1f9307563bf0292856a395a9c3740fa3edb2c88807e9ddb7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:52.887522Z","signature_b64":"mEyl6kxh+wR0Dslqlard+1y2LibfJDmICf5vy4Y3iJZYNpSy3V3jQ+cwyKqsi8sptn15iK6KSVtUuZqoQv8QBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dee6e51472d617a1f9307563bf0292856a395a9c3740fa3edb2c88807e9ddb7","last_reissued_at":"2026-05-17T23:41:52.887018Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:52.887018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.02124","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":"2026-05-17T23:41:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dx9RInD9Js6SGExhLIeXY7ZrVKNPNfUmbII1dtmkFCJyNqy7LVa/5Tcgl6Mbiyd3EsAyocAGKPagK7gGIZOVCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T04:06:48.232588Z"},"content_sha256":"d75d4a82100b090c4a28039e70ca340d2ff964c1e18c59544bc0237d6f073562","schema_version":"1.0","event_id":"sha256:d75d4a82100b090c4a28039e70ca340d2ff964c1e18c59544bc0237d6f073562"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NXXG4UKHFVQXUH4TA5LDX4BJFB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PatentBERT: Patent Classification with Fine-Tuning a pre-trained BERT Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Jieh Hsiang, Jieh-Sheng Lee","submitted_at":"2019-05-14T10:33:08Z","abstract_excerpt":"In this work we focus on fine-tuning a pre-trained BERT model and applying it to patent classification. When applied to large datasets of over two millions patents, our approach outperforms the state of the art by an approach using CNN with word embeddings. In addition, we focus on patent claims without other parts in patent documents. Our contributions include: (1) a new state-of-the-art method based on pre-trained BERT model and fine-tuning for patent classification, (2) a large dataset USPTO-3M at the CPC subclass level with SQL statements that can be used by future researchers, (3) showing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02124","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":""},"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":"2026-05-17T23:41:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W8EOK094RVSfKCLPUS9BzX5BvY3J06UmC0pwhOsK2cfeGghDX0ds0HCxC9MhmsJ9lhaDdbcR55q+BLYgSYm0CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T04:06:48.232994Z"},"content_sha256":"15e0c3d046c037fe3afd38f0e4bea1231a2deb812e11b3f58a59ed841bf2163b","schema_version":"1.0","event_id":"sha256:15e0c3d046c037fe3afd38f0e4bea1231a2deb812e11b3f58a59ed841bf2163b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NXXG4UKHFVQXUH4TA5LDX4BJFB/bundle.json","state_url":"https://pith.science/pith/NXXG4UKHFVQXUH4TA5LDX4BJFB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NXXG4UKHFVQXUH4TA5LDX4BJFB/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":"2026-06-03T04:06:48Z","links":{"resolver":"https://pith.science/pith/NXXG4UKHFVQXUH4TA5LDX4BJFB","bundle":"https://pith.science/pith/NXXG4UKHFVQXUH4TA5LDX4BJFB/bundle.json","state":"https://pith.science/pith/NXXG4UKHFVQXUH4TA5LDX4BJFB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NXXG4UKHFVQXUH4TA5LDX4BJFB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NXXG4UKHFVQXUH4TA5LDX4BJFB","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":"8d4af2f7ea9da11591563b416396af373908726d4c6367ccd97bf67f35932cc5","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T10:33:08Z","title_canon_sha256":"f8f29883c4217f22f12a5f365f40477ef4174dcbefbec1a3d2927f7974311f82"},"schema_version":"1.0","source":{"id":"1906.02124","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.02124","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"arxiv_version","alias_value":"1906.02124v2","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02124","created_at":"2026-05-17T23:41:52Z"},{"alias_kind":"pith_short_12","alias_value":"NXXG4UKHFVQX","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NXXG4UKHFVQXUH4T","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NXXG4UKH","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:15e0c3d046c037fe3afd38f0e4bea1231a2deb812e11b3f58a59ed841bf2163b","target":"graph","created_at":"2026-05-17T23:41:52Z","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"},"paper":{"abstract_excerpt":"In this work we focus on fine-tuning a pre-trained BERT model and applying it to patent classification. When applied to large datasets of over two millions patents, our approach outperforms the state of the art by an approach using CNN with word embeddings. In addition, we focus on patent claims without other parts in patent documents. Our contributions include: (1) a new state-of-the-art method based on pre-trained BERT model and fine-tuning for patent classification, (2) a large dataset USPTO-3M at the CPC subclass level with SQL statements that can be used by future researchers, (3) showing","authors_text":"Jieh Hsiang, Jieh-Sheng Lee","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T10:33:08Z","title":"PatentBERT: Patent Classification with Fine-Tuning a pre-trained BERT Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02124","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:d75d4a82100b090c4a28039e70ca340d2ff964c1e18c59544bc0237d6f073562","target":"record","created_at":"2026-05-17T23:41:52Z","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":"8d4af2f7ea9da11591563b416396af373908726d4c6367ccd97bf67f35932cc5","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-14T10:33:08Z","title_canon_sha256":"f8f29883c4217f22f12a5f365f40477ef4174dcbefbec1a3d2927f7974311f82"},"schema_version":"1.0","source":{"id":"1906.02124","kind":"arxiv","version":2}},"canonical_sha256":"6dee6e51472d617a1f9307563bf0292856a395a9c3740fa3edb2c88807e9ddb7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6dee6e51472d617a1f9307563bf0292856a395a9c3740fa3edb2c88807e9ddb7","first_computed_at":"2026-05-17T23:41:52.887018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:52.887018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mEyl6kxh+wR0Dslqlard+1y2LibfJDmICf5vy4Y3iJZYNpSy3V3jQ+cwyKqsi8sptn15iK6KSVtUuZqoQv8QBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:52.887522Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.02124","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d75d4a82100b090c4a28039e70ca340d2ff964c1e18c59544bc0237d6f073562","sha256:15e0c3d046c037fe3afd38f0e4bea1231a2deb812e11b3f58a59ed841bf2163b"],"state_sha256":"081b70784026e2324f604872da6f255bb6314b2b8aa21ea4ae316a30b3fec327"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hmgQiPdPWASxB+MXairFp70glrDI66HZGbB+nIRKzJFI5WLkkVI2R7SVun7C8wszFvQJe5A+r0ElIRH9bOayCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T04:06:48.236925Z","bundle_sha256":"60a6173e62df56eb6a2f8d8d5a0834e13c58a812a1022220f79c494d13848f71"}}