{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7LNZDTDF2F6JGL6QV6OMI5TF3V","short_pith_number":"pith:7LNZDTDF","schema_version":"1.0","canonical_sha256":"fadb91cc65d17c932fd0af9cc47665dd7d703777510e48857200d966fa49c118","source":{"kind":"arxiv","id":"1910.10781","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Transformers for Long Document Classification","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Jes\\'us Villalba, Najim Dehak, Piotr \\.Zelasko, Raghavendra Pappagari, Yishay Carmiel","submitted_at":"2019-10-23T19:51:50Z","abstract_excerpt":"BERT, which stands for Bidirectional Encoder Representations from Transformers, is a recently introduced language representation model based upon the transfer learning paradigm. We extend its fine-tuning procedure to address one of its major limitations - applicability to inputs longer than a few hundred words, such as transcripts of human call conversations. Our method is conceptually simple. We segment the input into smaller chunks and feed each of them into the base model. Then, we propagate each output through a single recurrent layer, or another transformer, followed by a softmax activati"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1910.10781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-23T19:51:50Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"d17e8bb78df8200b7307736f8e3045aae6f3360e0c49d7367e79cdf1e8928f64","abstract_canon_sha256":"6e59c8df3e33278afc479e4ca6291e37f56e0aa89cd5456dbcc5ad417b3fea4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:14:35.479366Z","signature_b64":"lI5nR46nw93iWOPaUFvB8qo5kKw7KdfV5GPHIq+aBvexzVQEd/waLqEqnR76opFnav12LYRsC7vtlwB3a7hZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fadb91cc65d17c932fd0af9cc47665dd7d703777510e48857200d966fa49c118","last_reissued_at":"2026-07-05T00:14:35.478846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:14:35.478846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Transformers for Long Document Classification","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Jes\\'us Villalba, Najim Dehak, Piotr \\.Zelasko, Raghavendra Pappagari, Yishay Carmiel","submitted_at":"2019-10-23T19:51:50Z","abstract_excerpt":"BERT, which stands for Bidirectional Encoder Representations from Transformers, is a recently introduced language representation model based upon the transfer learning paradigm. We extend its fine-tuning procedure to address one of its major limitations - applicability to inputs longer than a few hundred words, such as transcripts of human call conversations. Our method is conceptually simple. We segment the input into smaller chunks and feed each of them into the base model. Then, we propagate each output through a single recurrent layer, or another transformer, followed by a softmax activati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.10781","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/1910.10781/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1910.10781","created_at":"2026-07-05T00:14:35.478922+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.10781v1","created_at":"2026-07-05T00:14:35.478922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.10781","created_at":"2026-07-05T00:14:35.478922+00:00"},{"alias_kind":"pith_short_12","alias_value":"7LNZDTDF2F6J","created_at":"2026-07-05T00:14:35.478922+00:00"},{"alias_kind":"pith_short_16","alias_value":"7LNZDTDF2F6JGL6Q","created_at":"2026-07-05T00:14:35.478922+00:00"},{"alias_kind":"pith_short_8","alias_value":"7LNZDTDF","created_at":"2026-07-05T00:14:35.478922+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.05952","citing_title":"MOGO: Residual Quantized Hierarchical Causal Transformer for High-Quality and Real-Time 3D Human Motion Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2602.07303","citing_title":"KRONE: Scalable LLM-Augmented Log Anomaly Detection via Hierarchical Abstraction","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7LNZDTDF2F6JGL6QV6OMI5TF3V","json":"https://pith.science/pith/7LNZDTDF2F6JGL6QV6OMI5TF3V.json","graph_json":"https://pith.science/api/pith-number/7LNZDTDF2F6JGL6QV6OMI5TF3V/graph.json","events_json":"https://pith.science/api/pith-number/7LNZDTDF2F6JGL6QV6OMI5TF3V/events.json","paper":"https://pith.science/paper/7LNZDTDF"},"agent_actions":{"view_html":"https://pith.science/pith/7LNZDTDF2F6JGL6QV6OMI5TF3V","download_json":"https://pith.science/pith/7LNZDTDF2F6JGL6QV6OMI5TF3V.json","view_paper":"https://pith.science/paper/7LNZDTDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.10781&json=true","fetch_graph":"https://pith.science/api/pith-number/7LNZDTDF2F6JGL6QV6OMI5TF3V/graph.json","fetch_events":"https://pith.science/api/pith-number/7LNZDTDF2F6JGL6QV6OMI5TF3V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7LNZDTDF2F6JGL6QV6OMI5TF3V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7LNZDTDF2F6JGL6QV6OMI5TF3V/action/storage_attestation","attest_author":"https://pith.science/pith/7LNZDTDF2F6JGL6QV6OMI5TF3V/action/author_attestation","sign_citation":"https://pith.science/pith/7LNZDTDF2F6JGL6QV6OMI5TF3V/action/citation_signature","submit_replication":"https://pith.science/pith/7LNZDTDF2F6JGL6QV6OMI5TF3V/action/replication_record"}},"created_at":"2026-07-05T00:14:35.478922+00:00","updated_at":"2026-07-05T00:14:35.478922+00:00"}