{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:L5BZ62R6LT6HHNAT3ESSRDD3UC","short_pith_number":"pith:L5BZ62R6","canonical_record":{"source":{"id":"1905.06566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-16T07:20:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1057a236a347f8d5eac77c52c76a3d9786e864e529a46bee9803ea68ea32c1dd","abstract_canon_sha256":"b2517ba1e0cfddc0bd459cfdb314ac6fa237fb6688258439ebac8a9673f8fa44"},"schema_version":"1.0"},"canonical_sha256":"5f439f6a3e5cfc73b413d925288c7ba0abce1b94c0194024aa0f1b64d68ecae8","source":{"kind":"arxiv","id":"1905.06566","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06566","created_at":"2026-05-17T23:46:01Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06566v1","created_at":"2026-05-17T23:46:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06566","created_at":"2026-05-17T23:46:01Z"},{"alias_kind":"pith_short_12","alias_value":"L5BZ62R6LT6H","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"L5BZ62R6LT6HHNAT","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"L5BZ62R6","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:L5BZ62R6LT6HHNAT3ESSRDD3UC","target":"record","payload":{"canonical_record":{"source":{"id":"1905.06566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-16T07:20:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1057a236a347f8d5eac77c52c76a3d9786e864e529a46bee9803ea68ea32c1dd","abstract_canon_sha256":"b2517ba1e0cfddc0bd459cfdb314ac6fa237fb6688258439ebac8a9673f8fa44"},"schema_version":"1.0"},"canonical_sha256":"5f439f6a3e5cfc73b413d925288c7ba0abce1b94c0194024aa0f1b64d68ecae8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:01.858884Z","signature_b64":"SAy9AbWK/PJqXRc4+ZyxO+AehJFr0d44h1l6/oo9CNCRvVby5h/ZPLwiB9CkYYcjcuDxuQjZtAy9V5AUitSsDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f439f6a3e5cfc73b413d925288c7ba0abce1b94c0194024aa0f1b64d68ecae8","last_reissued_at":"2026-05-17T23:46:01.858140Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:01.858140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.06566","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":"2026-05-17T23:46:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nythD5RWZVqrzZCKt4qZOa92xh2O7ygzdHla3gG7boaG7n4JMUUJtTyjrTL8bxLDm5jn17LGo/TBZQPdxhxOAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T23:08:08.466243Z"},"content_sha256":"e55b5793678f705ac99f6921c449f4225486fee344165c3000d32110e077bb29","schema_version":"1.0","event_id":"sha256:e55b5793678f705ac99f6921c449f4225486fee344165c3000d32110e077bb29"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:L5BZ62R6LT6HHNAT3ESSRDD3UC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Furu Wei, Ming Zhou, Xingxing Zhang","submitted_at":"2019-05-16T07:20:21Z","abstract_excerpt":"Neural extractive summarization models usually employ a hierarchical encoder for document encoding and they are trained using sentence-level labels, which are created heuristically using rule-based methods. Training the hierarchical encoder with these \\emph{inaccurate} labels is challenging. Inspired by the recent work on pre-training transformer sentence encoders \\cite{devlin:2018:arxiv}, we propose {\\sc Hibert} (as shorthand for {\\bf HI}erachical {\\bf B}idirectional {\\bf E}ncoder {\\bf R}epresentations from {\\bf T}ransformers) for document encoding and a method to pre-train it using unlabeled"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06566","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":"2026-05-17T23:46:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1gouEPfBUtxj73sn7lLhm7A+hiIq01qm4XH4urhAUyJRKrvZdUH9563KO/1aAxJ9a0Y8WI5GHRQ3MVAOdjLaCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T23:08:08.466918Z"},"content_sha256":"27c7ecda3d018a3ad04235ff6d85f8c986d2384dccf08b3cdf6071721bfca4b6","schema_version":"1.0","event_id":"sha256:27c7ecda3d018a3ad04235ff6d85f8c986d2384dccf08b3cdf6071721bfca4b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L5BZ62R6LT6HHNAT3ESSRDD3UC/bundle.json","state_url":"https://pith.science/pith/L5BZ62R6LT6HHNAT3ESSRDD3UC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L5BZ62R6LT6HHNAT3ESSRDD3UC/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":"2026-05-24T23:08:08Z","links":{"resolver":"https://pith.science/pith/L5BZ62R6LT6HHNAT3ESSRDD3UC","bundle":"https://pith.science/pith/L5BZ62R6LT6HHNAT3ESSRDD3UC/bundle.json","state":"https://pith.science/pith/L5BZ62R6LT6HHNAT3ESSRDD3UC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L5BZ62R6LT6HHNAT3ESSRDD3UC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:L5BZ62R6LT6HHNAT3ESSRDD3UC","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":"b2517ba1e0cfddc0bd459cfdb314ac6fa237fb6688258439ebac8a9673f8fa44","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-16T07:20:21Z","title_canon_sha256":"1057a236a347f8d5eac77c52c76a3d9786e864e529a46bee9803ea68ea32c1dd"},"schema_version":"1.0","source":{"id":"1905.06566","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06566","created_at":"2026-05-17T23:46:01Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06566v1","created_at":"2026-05-17T23:46:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06566","created_at":"2026-05-17T23:46:01Z"},{"alias_kind":"pith_short_12","alias_value":"L5BZ62R6LT6H","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"L5BZ62R6LT6HHNAT","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"L5BZ62R6","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:27c7ecda3d018a3ad04235ff6d85f8c986d2384dccf08b3cdf6071721bfca4b6","target":"graph","created_at":"2026-05-17T23:46:01Z","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":"Neural extractive summarization models usually employ a hierarchical encoder for document encoding and they are trained using sentence-level labels, which are created heuristically using rule-based methods. Training the hierarchical encoder with these \\emph{inaccurate} labels is challenging. Inspired by the recent work on pre-training transformer sentence encoders \\cite{devlin:2018:arxiv}, we propose {\\sc Hibert} (as shorthand for {\\bf HI}erachical {\\bf B}idirectional {\\bf E}ncoder {\\bf R}epresentations from {\\bf T}ransformers) for document encoding and a method to pre-train it using unlabeled","authors_text":"Furu Wei, Ming Zhou, Xingxing Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-16T07:20:21Z","title":"HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06566","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:e55b5793678f705ac99f6921c449f4225486fee344165c3000d32110e077bb29","target":"record","created_at":"2026-05-17T23:46:01Z","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":"b2517ba1e0cfddc0bd459cfdb314ac6fa237fb6688258439ebac8a9673f8fa44","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-16T07:20:21Z","title_canon_sha256":"1057a236a347f8d5eac77c52c76a3d9786e864e529a46bee9803ea68ea32c1dd"},"schema_version":"1.0","source":{"id":"1905.06566","kind":"arxiv","version":1}},"canonical_sha256":"5f439f6a3e5cfc73b413d925288c7ba0abce1b94c0194024aa0f1b64d68ecae8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f439f6a3e5cfc73b413d925288c7ba0abce1b94c0194024aa0f1b64d68ecae8","first_computed_at":"2026-05-17T23:46:01.858140Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:01.858140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SAy9AbWK/PJqXRc4+ZyxO+AehJFr0d44h1l6/oo9CNCRvVby5h/ZPLwiB9CkYYcjcuDxuQjZtAy9V5AUitSsDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:01.858884Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.06566","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e55b5793678f705ac99f6921c449f4225486fee344165c3000d32110e077bb29","sha256:27c7ecda3d018a3ad04235ff6d85f8c986d2384dccf08b3cdf6071721bfca4b6"],"state_sha256":"c65657d107753895f79648d92cdbaf3fac37b44c435d120aa8ec3810bbfa08d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BudGggGnW3IuroNKPNDAUCGBY9uUZ+bw4CngPOa94ATp8z2iYZkGr2mzaLPMzIRKhe2A1fZyegYbAL2D0GZ/Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T23:08:08.470528Z","bundle_sha256":"51789cc83447ebfa6dbfaf49b6979a3b02f5467021765a95ff7240903d741091"}}