{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:N7XTDQQD2IOH2D666MHQHYQP6B","short_pith_number":"pith:N7XTDQQD","canonical_record":{"source":{"id":"2111.07158","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-13T17:27:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"542275eefcf3f77d235c0d6a0dec9537abdafa2baa61427f51a459f93d3ed943","abstract_canon_sha256":"b48ac429ee85043da41125505b4b7e92dc4d0bc7b11419d19e70709b4c4d243f"},"schema_version":"1.0"},"canonical_sha256":"6fef31c203d21c7d0fdef30f03e20ff066da71467fde6591aeccaac1704cf6e3","source":{"kind":"arxiv","id":"2111.07158","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.07158","created_at":"2026-07-05T04:14:26Z"},{"alias_kind":"arxiv_version","alias_value":"2111.07158v2","created_at":"2026-07-05T04:14:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.07158","created_at":"2026-07-05T04:14:26Z"},{"alias_kind":"pith_short_12","alias_value":"N7XTDQQD2IOH","created_at":"2026-07-05T04:14:26Z"},{"alias_kind":"pith_short_16","alias_value":"N7XTDQQD2IOH2D66","created_at":"2026-07-05T04:14:26Z"},{"alias_kind":"pith_short_8","alias_value":"N7XTDQQD","created_at":"2026-07-05T04:14:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:N7XTDQQD2IOH2D666MHQHYQP6B","target":"record","payload":{"canonical_record":{"source":{"id":"2111.07158","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-13T17:27:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"542275eefcf3f77d235c0d6a0dec9537abdafa2baa61427f51a459f93d3ed943","abstract_canon_sha256":"b48ac429ee85043da41125505b4b7e92dc4d0bc7b11419d19e70709b4c4d243f"},"schema_version":"1.0"},"canonical_sha256":"6fef31c203d21c7d0fdef30f03e20ff066da71467fde6591aeccaac1704cf6e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:26.364851Z","signature_b64":"3Pm+ZcUe1edhnU/bTIgnzvvaXeYs/EVriAIiSywGah19s1kRQStMHj7XpsDW3VIQlUuG/K1/cCFW/agm2aElBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fef31c203d21c7d0fdef30f03e20ff066da71467fde6591aeccaac1704cf6e3","last_reissued_at":"2026-07-05T04:14:26.364488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:26.364488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.07158","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:14:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"00qTiKJDp65MRDqp19W+vhTO0+MTRoIMMPio2Ec6Z6/tCGQ25WSSwoum7Z3HHrP1+bW3IOf9vzpZ+53cTNU0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T04:14:22.288176Z"},"content_sha256":"49c99280c5ae2ff3f4b8acc50bf4997beb39704559462e08db2ceb5f061fae41","schema_version":"1.0","event_id":"sha256:49c99280c5ae2ff3f4b8acc50bf4997beb39704559462e08db2ceb5f061fae41"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:N7XTDQQD2IOH2D666MHQHYQP6B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Deep Reinforcement Learning for Extractive Legal Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bao-Sinh Nguyen, Dung Tien Le, Duy-Hung Nguyen, Hung Le, Mim Amina Khatun, Minh-Tien Nguyen, Nguyen Viet Dung Nghiem","submitted_at":"2021-11-13T17:27:49Z","abstract_excerpt":"Automatic summarization of legal texts is an important and still a challenging task since legal documents are often long and complicated with unusual structures and styles. Recent advances of deep models trained end-to-end with differentiable losses can well-summarize natural text, yet when applied to legal domain, they show limited results. In this paper, we propose to use reinforcement learning to train current deep summarization models to improve their performance on the legal domain. To this end, we adopt proximal policy optimization methods and introduce novel reward functions that encour"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.07158","kind":"arxiv","version":2},"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/2111.07158/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":"2026-07-05T04:14:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JDdW9AhuNe9751srk8lWzRD6YAPE6w0T23w++SiyRJFHu93UOoBUo1FPw5CNYbyIo/a4MF24j3xQ6c+m2VAGCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T04:14:22.288735Z"},"content_sha256":"6bd699eb4f9d5cc63035278344c1a7adaec96619b97359d807b20890b516799e","schema_version":"1.0","event_id":"sha256:6bd699eb4f9d5cc63035278344c1a7adaec96619b97359d807b20890b516799e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N7XTDQQD2IOH2D666MHQHYQP6B/bundle.json","state_url":"https://pith.science/pith/N7XTDQQD2IOH2D666MHQHYQP6B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N7XTDQQD2IOH2D666MHQHYQP6B/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":"2026-08-23T04:14:22Z","links":{"resolver":"https://pith.science/pith/N7XTDQQD2IOH2D666MHQHYQP6B","bundle":"https://pith.science/pith/N7XTDQQD2IOH2D666MHQHYQP6B/bundle.json","state":"https://pith.science/pith/N7XTDQQD2IOH2D666MHQHYQP6B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N7XTDQQD2IOH2D666MHQHYQP6B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:N7XTDQQD2IOH2D666MHQHYQP6B","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":"b48ac429ee85043da41125505b4b7e92dc4d0bc7b11419d19e70709b4c4d243f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-13T17:27:49Z","title_canon_sha256":"542275eefcf3f77d235c0d6a0dec9537abdafa2baa61427f51a459f93d3ed943"},"schema_version":"1.0","source":{"id":"2111.07158","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.07158","created_at":"2026-07-05T04:14:26Z"},{"alias_kind":"arxiv_version","alias_value":"2111.07158v2","created_at":"2026-07-05T04:14:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.07158","created_at":"2026-07-05T04:14:26Z"},{"alias_kind":"pith_short_12","alias_value":"N7XTDQQD2IOH","created_at":"2026-07-05T04:14:26Z"},{"alias_kind":"pith_short_16","alias_value":"N7XTDQQD2IOH2D66","created_at":"2026-07-05T04:14:26Z"},{"alias_kind":"pith_short_8","alias_value":"N7XTDQQD","created_at":"2026-07-05T04:14:26Z"}],"graph_snapshots":[{"event_id":"sha256:6bd699eb4f9d5cc63035278344c1a7adaec96619b97359d807b20890b516799e","target":"graph","created_at":"2026-07-05T04:14:26Z","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/2111.07158/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic summarization of legal texts is an important and still a challenging task since legal documents are often long and complicated with unusual structures and styles. Recent advances of deep models trained end-to-end with differentiable losses can well-summarize natural text, yet when applied to legal domain, they show limited results. In this paper, we propose to use reinforcement learning to train current deep summarization models to improve their performance on the legal domain. To this end, we adopt proximal policy optimization methods and introduce novel reward functions that encour","authors_text":"Bao-Sinh Nguyen, Dung Tien Le, Duy-Hung Nguyen, Hung Le, Mim Amina Khatun, Minh-Tien Nguyen, Nguyen Viet Dung Nghiem","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-13T17:27:49Z","title":"Robust Deep Reinforcement Learning for Extractive Legal Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.07158","kind":"arxiv","version":2},"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":"sha256:49c99280c5ae2ff3f4b8acc50bf4997beb39704559462e08db2ceb5f061fae41","target":"record","created_at":"2026-07-05T04:14:26Z","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":"b48ac429ee85043da41125505b4b7e92dc4d0bc7b11419d19e70709b4c4d243f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-13T17:27:49Z","title_canon_sha256":"542275eefcf3f77d235c0d6a0dec9537abdafa2baa61427f51a459f93d3ed943"},"schema_version":"1.0","source":{"id":"2111.07158","kind":"arxiv","version":2}},"canonical_sha256":"6fef31c203d21c7d0fdef30f03e20ff066da71467fde6591aeccaac1704cf6e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fef31c203d21c7d0fdef30f03e20ff066da71467fde6591aeccaac1704cf6e3","first_computed_at":"2026-07-05T04:14:26.364488Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:14:26.364488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3Pm+ZcUe1edhnU/bTIgnzvvaXeYs/EVriAIiSywGah19s1kRQStMHj7XpsDW3VIQlUuG/K1/cCFW/agm2aElBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:14:26.364851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.07158","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49c99280c5ae2ff3f4b8acc50bf4997beb39704559462e08db2ceb5f061fae41","sha256:6bd699eb4f9d5cc63035278344c1a7adaec96619b97359d807b20890b516799e"],"state_sha256":"a9fbd74219f6ebf0e8643b4412b482504c39f34631709a3f9d33953812a22e99"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D20mx8CmnZeS2MgAjf8D9cQ6rr0Q6ltemjMhnO1UR8cp3Rv9saSMa3M5t0JQp+tLRCm2lU00jrDTNycQAvAiAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T04:14:22.293598Z","bundle_sha256":"a1597b05ea04351ef886927c56b75c07f0880b268f91c1677f6bca6f9bf8525f"}}