{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SHYOGQSKYNIZFHXP7Y4OK7F6YS","short_pith_number":"pith:SHYOGQSK","canonical_record":{"source":{"id":"1904.08398","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-17T17:55:18Z","cross_cats_sorted":[],"title_canon_sha256":"128534c48837fe5af84e4c3d5330edd7c21b3ffc8a83de8eb5f5923f96ff4e57","abstract_canon_sha256":"f304869af141de77f2d1b6cbe5ff7be2f3e37db0261e2b683cabdc6acb73f9ca"},"schema_version":"1.0"},"canonical_sha256":"91f0e3424ac351929eeffe38e57cbec49ac4bb5695727f5326ebadc7eb1a398c","source":{"kind":"arxiv","id":"1904.08398","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.08398","created_at":"2026-07-04T23:59:06Z"},{"alias_kind":"arxiv_version","alias_value":"1904.08398v3","created_at":"2026-07-04T23:59:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.08398","created_at":"2026-07-04T23:59:06Z"},{"alias_kind":"pith_short_12","alias_value":"SHYOGQSKYNIZ","created_at":"2026-07-04T23:59:06Z"},{"alias_kind":"pith_short_16","alias_value":"SHYOGQSKYNIZFHXP","created_at":"2026-07-04T23:59:06Z"},{"alias_kind":"pith_short_8","alias_value":"SHYOGQSK","created_at":"2026-07-04T23:59:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SHYOGQSKYNIZFHXP7Y4OK7F6YS","target":"record","payload":{"canonical_record":{"source":{"id":"1904.08398","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-17T17:55:18Z","cross_cats_sorted":[],"title_canon_sha256":"128534c48837fe5af84e4c3d5330edd7c21b3ffc8a83de8eb5f5923f96ff4e57","abstract_canon_sha256":"f304869af141de77f2d1b6cbe5ff7be2f3e37db0261e2b683cabdc6acb73f9ca"},"schema_version":"1.0"},"canonical_sha256":"91f0e3424ac351929eeffe38e57cbec49ac4bb5695727f5326ebadc7eb1a398c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:06.985540Z","signature_b64":"97HaGg176pQWoBWCNqs09AIgaGKIDGbl/94pSgV0mcfvq716Q6egsyFfxVQvaGjZHbFVl5VOvRJg5kx1Qa2kCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91f0e3424ac351929eeffe38e57cbec49ac4bb5695727f5326ebadc7eb1a398c","last_reissued_at":"2026-07-04T23:59:06.984941Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:06.984941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.08398","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":"2026-07-04T23:59:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"doY93VXSWS/WW7OMRh53W0KJnW4TZuKtvlmCxtXtOVcEajWfXVbgGVjQudLMQSqTQxZ+n7HGK6RdEfEQJPfjDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:43:49.211432Z"},"content_sha256":"086bfc45ebb70fe11bee7bb321b99673de24394b20cba2b3ab5980a3a9a7427c","schema_version":"1.0","event_id":"sha256:086bfc45ebb70fe11bee7bb321b99673de24394b20cba2b3ab5980a3a9a7427c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SHYOGQSKYNIZFHXP7Y4OK7F6YS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DocBERT: BERT for Document Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Achyudh Ram, Ashutosh Adhikari, Jimmy Lin, Raphael Tang","submitted_at":"2019-04-17T17:55:18Z","abstract_excerpt":"We present, to our knowledge, the first application of BERT to document classification. A few characteristics of the task might lead one to think that BERT is not the most appropriate model: syntactic structures matter less for content categories, documents can often be longer than typical BERT input, and documents often have multiple labels. Nevertheless, we show that a straightforward classification model using BERT is able to achieve the state of the art across four popular datasets. To address the computational expense associated with BERT inference, we distill knowledge from BERT-large to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.08398","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/1904.08398/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":"2026-07-04T23:59:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3ln2MmTl1ep3/AMnECHyqmy1ORUOPQzooacGp70ZOpprjgeZLjCKMxNcME6x9OV1bW9I86giHazdYIht2EBwAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:43:49.212484Z"},"content_sha256":"fec7de0174f9616b8bded01ed74f52d89a4b6a3a373e6e4eef1e0c85a15844d6","schema_version":"1.0","event_id":"sha256:fec7de0174f9616b8bded01ed74f52d89a4b6a3a373e6e4eef1e0c85a15844d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SHYOGQSKYNIZFHXP7Y4OK7F6YS/bundle.json","state_url":"https://pith.science/pith/SHYOGQSKYNIZFHXP7Y4OK7F6YS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SHYOGQSKYNIZFHXP7Y4OK7F6YS/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":"2026-08-08T03:43:49Z","links":{"resolver":"https://pith.science/pith/SHYOGQSKYNIZFHXP7Y4OK7F6YS","bundle":"https://pith.science/pith/SHYOGQSKYNIZFHXP7Y4OK7F6YS/bundle.json","state":"https://pith.science/pith/SHYOGQSKYNIZFHXP7Y4OK7F6YS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SHYOGQSKYNIZFHXP7Y4OK7F6YS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SHYOGQSKYNIZFHXP7Y4OK7F6YS","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":"f304869af141de77f2d1b6cbe5ff7be2f3e37db0261e2b683cabdc6acb73f9ca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-17T17:55:18Z","title_canon_sha256":"128534c48837fe5af84e4c3d5330edd7c21b3ffc8a83de8eb5f5923f96ff4e57"},"schema_version":"1.0","source":{"id":"1904.08398","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.08398","created_at":"2026-07-04T23:59:06Z"},{"alias_kind":"arxiv_version","alias_value":"1904.08398v3","created_at":"2026-07-04T23:59:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.08398","created_at":"2026-07-04T23:59:06Z"},{"alias_kind":"pith_short_12","alias_value":"SHYOGQSKYNIZ","created_at":"2026-07-04T23:59:06Z"},{"alias_kind":"pith_short_16","alias_value":"SHYOGQSKYNIZFHXP","created_at":"2026-07-04T23:59:06Z"},{"alias_kind":"pith_short_8","alias_value":"SHYOGQSK","created_at":"2026-07-04T23:59:06Z"}],"graph_snapshots":[{"event_id":"sha256:fec7de0174f9616b8bded01ed74f52d89a4b6a3a373e6e4eef1e0c85a15844d6","target":"graph","created_at":"2026-07-04T23:59:06Z","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/1904.08398/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present, to our knowledge, the first application of BERT to document classification. A few characteristics of the task might lead one to think that BERT is not the most appropriate model: syntactic structures matter less for content categories, documents can often be longer than typical BERT input, and documents often have multiple labels. Nevertheless, we show that a straightforward classification model using BERT is able to achieve the state of the art across four popular datasets. To address the computational expense associated with BERT inference, we distill knowledge from BERT-large to","authors_text":"Achyudh Ram, Ashutosh Adhikari, Jimmy Lin, Raphael Tang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-17T17:55:18Z","title":"DocBERT: BERT for Document Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.08398","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":"sha256:086bfc45ebb70fe11bee7bb321b99673de24394b20cba2b3ab5980a3a9a7427c","target":"record","created_at":"2026-07-04T23:59:06Z","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":"f304869af141de77f2d1b6cbe5ff7be2f3e37db0261e2b683cabdc6acb73f9ca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-17T17:55:18Z","title_canon_sha256":"128534c48837fe5af84e4c3d5330edd7c21b3ffc8a83de8eb5f5923f96ff4e57"},"schema_version":"1.0","source":{"id":"1904.08398","kind":"arxiv","version":3}},"canonical_sha256":"91f0e3424ac351929eeffe38e57cbec49ac4bb5695727f5326ebadc7eb1a398c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91f0e3424ac351929eeffe38e57cbec49ac4bb5695727f5326ebadc7eb1a398c","first_computed_at":"2026-07-04T23:59:06.984941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:59:06.984941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"97HaGg176pQWoBWCNqs09AIgaGKIDGbl/94pSgV0mcfvq716Q6egsyFfxVQvaGjZHbFVl5VOvRJg5kx1Qa2kCQ==","signature_status":"signed_v1","signed_at":"2026-07-04T23:59:06.985540Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.08398","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:086bfc45ebb70fe11bee7bb321b99673de24394b20cba2b3ab5980a3a9a7427c","sha256:fec7de0174f9616b8bded01ed74f52d89a4b6a3a373e6e4eef1e0c85a15844d6"],"state_sha256":"d86ba1f1a32cd66472199fa6b3a14f7b66ff91084b1fb933657b19dd719b5872"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kbFF01tM7OE9pKPRS7chlR/hjy5PfZ9+35Lc1Ko9rIajuZ4V/JXg6F84L1+Iz2UBxIKWZkTW+lhwVuq5OY3vBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:43:49.217781Z","bundle_sha256":"3c62ad7723e7e7467f8fc018a4dfd783913e8339a105dfbea002412e87496421"}}