{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:TPVHHPEM5VNV3EZ32QHB6XLBVG","short_pith_number":"pith:TPVHHPEM","canonical_record":{"source":{"id":"1901.09128","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-26T00:35:35Z","cross_cats_sorted":[],"title_canon_sha256":"cb763ae99959acdba4ee09c6398ec7f582c2dde1d11b69f534a6d135739a413c","abstract_canon_sha256":"bc534f56e943821b0b5fa0f8107c81154a184401350195176262c8776d53f6a5"},"schema_version":"1.0"},"canonical_sha256":"9bea73bc8ced5b5d933bd40e1f5d61a99782e45f945a9ba8ea55c579d6a17d0c","source":{"kind":"arxiv","id":"1901.09128","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.09128","created_at":"2026-05-17T23:55:30Z"},{"alias_kind":"arxiv_version","alias_value":"1901.09128v1","created_at":"2026-05-17T23:55:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09128","created_at":"2026-05-17T23:55:30Z"},{"alias_kind":"pith_short_12","alias_value":"TPVHHPEM5VNV","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"TPVHHPEM5VNV3EZ3","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"TPVHHPEM","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:TPVHHPEM5VNV3EZ32QHB6XLBVG","target":"record","payload":{"canonical_record":{"source":{"id":"1901.09128","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-26T00:35:35Z","cross_cats_sorted":[],"title_canon_sha256":"cb763ae99959acdba4ee09c6398ec7f582c2dde1d11b69f534a6d135739a413c","abstract_canon_sha256":"bc534f56e943821b0b5fa0f8107c81154a184401350195176262c8776d53f6a5"},"schema_version":"1.0"},"canonical_sha256":"9bea73bc8ced5b5d933bd40e1f5d61a99782e45f945a9ba8ea55c579d6a17d0c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:30.475432Z","signature_b64":"oeKdx/hnWpIed4UtBmFsa1JF830U9Z01fAmn6tVQ88jmu+hJ0RaRY8gPat6yBYVBsto9ycMIrB1ZcioV+cK/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bea73bc8ced5b5d933bd40e1f5d61a99782e45f945a9ba8ea55c579d6a17d0c","last_reissued_at":"2026-05-17T23:55:30.474985Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:30.474985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.09128","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":"2026-05-17T23:55:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OAjXsaHpRd7GGUB26DOdekvytbsDq0ei82IbPkikmOgIYmos4RlucTeCDB48NsS/HpB5+Pr5doRQdMwS8ThHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T07:01:00.003803Z"},"content_sha256":"f38a31695cc1ccf111391161a3e8204a570aa84238e629d44d8798a7d2cf4c8d","schema_version":"1.0","event_id":"sha256:f38a31695cc1ccf111391161a3e8204a570aa84238e629d44d8798a7d2cf4c8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:TPVHHPEM5VNV3EZ32QHB6XLBVG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Model Pre-training for Hierarchical Document Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jacob Devlin, Kenton Lee, Kristina Toutanova, Ming-Wei Chang","submitted_at":"2019-01-26T00:35:35Z","abstract_excerpt":"Hierarchical neural architectures are often used to capture long-distance dependencies and have been applied to many document-level tasks such as summarization, document segmentation, and sentiment analysis. However, effective usage of such a large context can be difficult to learn, especially in the case where there is limited labeled data available. Building on the recent success of language model pretraining methods for learning flat representations of text, we propose algorithms for pre-training hierarchical document representations from unlabeled data. Unlike prior work, which has focused"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09128","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":""},"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":"2026-05-17T23:55:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o3tzLhlmMga+vXmUD5j9rFzVlkBoWc2AjXe76l/7lvHfsDdeDxptDbtCyww/04vtQsgiugXzocRPZ5YRI7hWAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T07:01:00.004430Z"},"content_sha256":"dbd154e61faddbf5bf151204d1be00c02cff75c9d56a10fdb0a45ad79b8ca492","schema_version":"1.0","event_id":"sha256:dbd154e61faddbf5bf151204d1be00c02cff75c9d56a10fdb0a45ad79b8ca492"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TPVHHPEM5VNV3EZ32QHB6XLBVG/bundle.json","state_url":"https://pith.science/pith/TPVHHPEM5VNV3EZ32QHB6XLBVG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TPVHHPEM5VNV3EZ32QHB6XLBVG/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":"2026-06-07T07:01:00Z","links":{"resolver":"https://pith.science/pith/TPVHHPEM5VNV3EZ32QHB6XLBVG","bundle":"https://pith.science/pith/TPVHHPEM5VNV3EZ32QHB6XLBVG/bundle.json","state":"https://pith.science/pith/TPVHHPEM5VNV3EZ32QHB6XLBVG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TPVHHPEM5VNV3EZ32QHB6XLBVG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TPVHHPEM5VNV3EZ32QHB6XLBVG","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":"bc534f56e943821b0b5fa0f8107c81154a184401350195176262c8776d53f6a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-26T00:35:35Z","title_canon_sha256":"cb763ae99959acdba4ee09c6398ec7f582c2dde1d11b69f534a6d135739a413c"},"schema_version":"1.0","source":{"id":"1901.09128","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.09128","created_at":"2026-05-17T23:55:30Z"},{"alias_kind":"arxiv_version","alias_value":"1901.09128v1","created_at":"2026-05-17T23:55:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09128","created_at":"2026-05-17T23:55:30Z"},{"alias_kind":"pith_short_12","alias_value":"TPVHHPEM5VNV","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"TPVHHPEM5VNV3EZ3","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"TPVHHPEM","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:dbd154e61faddbf5bf151204d1be00c02cff75c9d56a10fdb0a45ad79b8ca492","target":"graph","created_at":"2026-05-17T23:55:30Z","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":"Hierarchical neural architectures are often used to capture long-distance dependencies and have been applied to many document-level tasks such as summarization, document segmentation, and sentiment analysis. However, effective usage of such a large context can be difficult to learn, especially in the case where there is limited labeled data available. Building on the recent success of language model pretraining methods for learning flat representations of text, we propose algorithms for pre-training hierarchical document representations from unlabeled data. Unlike prior work, which has focused","authors_text":"Jacob Devlin, Kenton Lee, Kristina Toutanova, Ming-Wei Chang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-26T00:35:35Z","title":"Language Model Pre-training for Hierarchical Document Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09128","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:f38a31695cc1ccf111391161a3e8204a570aa84238e629d44d8798a7d2cf4c8d","target":"record","created_at":"2026-05-17T23:55:30Z","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":"bc534f56e943821b0b5fa0f8107c81154a184401350195176262c8776d53f6a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-26T00:35:35Z","title_canon_sha256":"cb763ae99959acdba4ee09c6398ec7f582c2dde1d11b69f534a6d135739a413c"},"schema_version":"1.0","source":{"id":"1901.09128","kind":"arxiv","version":1}},"canonical_sha256":"9bea73bc8ced5b5d933bd40e1f5d61a99782e45f945a9ba8ea55c579d6a17d0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9bea73bc8ced5b5d933bd40e1f5d61a99782e45f945a9ba8ea55c579d6a17d0c","first_computed_at":"2026-05-17T23:55:30.474985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:30.474985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oeKdx/hnWpIed4UtBmFsa1JF830U9Z01fAmn6tVQ88jmu+hJ0RaRY8gPat6yBYVBsto9ycMIrB1ZcioV+cK/AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:30.475432Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.09128","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f38a31695cc1ccf111391161a3e8204a570aa84238e629d44d8798a7d2cf4c8d","sha256:dbd154e61faddbf5bf151204d1be00c02cff75c9d56a10fdb0a45ad79b8ca492"],"state_sha256":"22812e273d0a9599eb63903ede73bd8355959d0cf6b44a0ce05b88c1ccc9da57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eAqVdY2LmqmVIIrjGvggu5FpYqbicwk3NoIDndK/R5fhRBBAnriMRwuW3Tz+0r8MGKgTDKNnIzKgjYUl+ksKDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T07:01:00.007822Z","bundle_sha256":"2f3a228016282d9d45cbebfd1d7765bd3f37a552eb664b11161ccef5cf77126f"}}