{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:RZL2AYFJVJQIF25AJLFS7I4YIV","short_pith_number":"pith:RZL2AYFJ","canonical_record":{"source":{"id":"1903.10676","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-26T05:11:46Z","cross_cats_sorted":[],"title_canon_sha256":"7eb82fa0d870de51f73017b764dde7e6f921b4cd47928a4dd973bb56395e916a","abstract_canon_sha256":"3f38e7d3c9b8f211234c157a5069919d9e74d2e394d8845b1cf007a089071ac4"},"schema_version":"1.0"},"canonical_sha256":"8e57a060a9aa6082eba04acb2fa398455b1f294688228d9671ea6ff3b56d0ca4","source":{"kind":"arxiv","id":"1903.10676","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.10676","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"arxiv_version","alias_value":"1903.10676v3","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10676","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"pith_short_12","alias_value":"RZL2AYFJVJQI","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"pith_short_16","alias_value":"RZL2AYFJVJQIF25A","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"pith_short_8","alias_value":"RZL2AYFJ","created_at":"2026-07-05T00:03:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:RZL2AYFJVJQIF25AJLFS7I4YIV","target":"record","payload":{"canonical_record":{"source":{"id":"1903.10676","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-26T05:11:46Z","cross_cats_sorted":[],"title_canon_sha256":"7eb82fa0d870de51f73017b764dde7e6f921b4cd47928a4dd973bb56395e916a","abstract_canon_sha256":"3f38e7d3c9b8f211234c157a5069919d9e74d2e394d8845b1cf007a089071ac4"},"schema_version":"1.0"},"canonical_sha256":"8e57a060a9aa6082eba04acb2fa398455b1f294688228d9671ea6ff3b56d0ca4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:55.820636Z","signature_b64":"r17QLEUpFMpWUTC4M3QKipB6A6fTbWiMnT47rlVp0TjLYggTGfncPW4xEnOEj/33r58mg5t5DOPStPf1MtS/BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e57a060a9aa6082eba04acb2fa398455b1f294688228d9671ea6ff3b56d0ca4","last_reissued_at":"2026-07-05T00:03:55.820214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:55.820214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.10676","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:03:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"421dpwyYw/GyqOnQ7XFudfjSVGSLtZAL7i5ue/ChyBg1OOen//s5NC5FWHwQlu2pcYZkFkIxXJ/LGFKis4lYBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T02:39:55.092180Z"},"content_sha256":"9a8863c1cd199157ea0f87b2de73c252472365dffcced61fabb28480da7d3663","schema_version":"1.0","event_id":"sha256:9a8863c1cd199157ea0f87b2de73c252472365dffcced61fabb28480da7d3663"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:RZL2AYFJVJQIF25AJLFS7I4YIV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SciBERT: A Pretrained Language Model for Scientific Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Iz Beltagy, Kyle Lo","submitted_at":"2019-03-26T05:11:46Z","abstract_excerpt":"Obtaining large-scale annotated data for NLP tasks in the scientific domain is challenging and expensive. We release SciBERT, a pretrained language model based on BERT (Devlin et al., 2018) to address the lack of high-quality, large-scale labeled scientific data. SciBERT leverages unsupervised pretraining on a large multi-domain corpus of scientific publications to improve performance on downstream scientific NLP tasks. We evaluate on a suite of tasks including sequence tagging, sentence classification and dependency parsing, with datasets from a variety of scientific domains. We demonstrate s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10676","kind":"arxiv","version":3},"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/1903.10676/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":"2026-07-05T00:03:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l+zrPg8EOdg6dAzNPSJX65slbv1E+oFfUvl2faRyPXcL203So2jCEorMErNzv6rpKg1peDJzRWNnwXhzhgZhAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T02:39:55.092689Z"},"content_sha256":"0114c23caa42e66006087cdbdb51b7423fff3d5b2ba87240bc26582cac2d9204","schema_version":"1.0","event_id":"sha256:0114c23caa42e66006087cdbdb51b7423fff3d5b2ba87240bc26582cac2d9204"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RZL2AYFJVJQIF25AJLFS7I4YIV/bundle.json","state_url":"https://pith.science/pith/RZL2AYFJVJQIF25AJLFS7I4YIV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RZL2AYFJVJQIF25AJLFS7I4YIV/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":"2026-08-04T02:39:55Z","links":{"resolver":"https://pith.science/pith/RZL2AYFJVJQIF25AJLFS7I4YIV","bundle":"https://pith.science/pith/RZL2AYFJVJQIF25AJLFS7I4YIV/bundle.json","state":"https://pith.science/pith/RZL2AYFJVJQIF25AJLFS7I4YIV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RZL2AYFJVJQIF25AJLFS7I4YIV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RZL2AYFJVJQIF25AJLFS7I4YIV","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":"3f38e7d3c9b8f211234c157a5069919d9e74d2e394d8845b1cf007a089071ac4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-26T05:11:46Z","title_canon_sha256":"7eb82fa0d870de51f73017b764dde7e6f921b4cd47928a4dd973bb56395e916a"},"schema_version":"1.0","source":{"id":"1903.10676","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.10676","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"arxiv_version","alias_value":"1903.10676v3","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10676","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"pith_short_12","alias_value":"RZL2AYFJVJQI","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"pith_short_16","alias_value":"RZL2AYFJVJQIF25A","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"pith_short_8","alias_value":"RZL2AYFJ","created_at":"2026-07-05T00:03:55Z"}],"graph_snapshots":[{"event_id":"sha256:0114c23caa42e66006087cdbdb51b7423fff3d5b2ba87240bc26582cac2d9204","target":"graph","created_at":"2026-07-05T00:03:55Z","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/1903.10676/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Obtaining large-scale annotated data for NLP tasks in the scientific domain is challenging and expensive. We release SciBERT, a pretrained language model based on BERT (Devlin et al., 2018) to address the lack of high-quality, large-scale labeled scientific data. SciBERT leverages unsupervised pretraining on a large multi-domain corpus of scientific publications to improve performance on downstream scientific NLP tasks. We evaluate on a suite of tasks including sequence tagging, sentence classification and dependency parsing, with datasets from a variety of scientific domains. We demonstrate s","authors_text":"Arman Cohan, Iz Beltagy, Kyle Lo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-26T05:11:46Z","title":"SciBERT: A Pretrained Language Model for Scientific Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10676","kind":"arxiv","version":3},"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":"sha256:9a8863c1cd199157ea0f87b2de73c252472365dffcced61fabb28480da7d3663","target":"record","created_at":"2026-07-05T00:03:55Z","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":"3f38e7d3c9b8f211234c157a5069919d9e74d2e394d8845b1cf007a089071ac4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-26T05:11:46Z","title_canon_sha256":"7eb82fa0d870de51f73017b764dde7e6f921b4cd47928a4dd973bb56395e916a"},"schema_version":"1.0","source":{"id":"1903.10676","kind":"arxiv","version":3}},"canonical_sha256":"8e57a060a9aa6082eba04acb2fa398455b1f294688228d9671ea6ff3b56d0ca4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e57a060a9aa6082eba04acb2fa398455b1f294688228d9671ea6ff3b56d0ca4","first_computed_at":"2026-07-05T00:03:55.820214Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:03:55.820214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r17QLEUpFMpWUTC4M3QKipB6A6fTbWiMnT47rlVp0TjLYggTGfncPW4xEnOEj/33r58mg5t5DOPStPf1MtS/BA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:03:55.820636Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.10676","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a8863c1cd199157ea0f87b2de73c252472365dffcced61fabb28480da7d3663","sha256:0114c23caa42e66006087cdbdb51b7423fff3d5b2ba87240bc26582cac2d9204"],"state_sha256":"f82e6d87f99b03fc17fd54aa3d13ad17fb48ae6c1edb79c2dd959b35ba7c8597"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y537g3aZz3NIYlVem3P532z+KwQh3kBWm0n3LO82spwEI8y7p/s4ov62NzmHwK2xDRjV3YHxNDA3HsqOtT44BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T02:39:55.097957Z","bundle_sha256":"42ff85ebcbb1ebd64801b624a4d7920ed80a06e179b7aa309cc78a12b4d267ca"}}