{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7S3VTOF4PUSRQM5OMLSCKVZXS3","short_pith_number":"pith:7S3VTOF4","canonical_record":{"source":{"id":"1804.07036","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-19T08:42:32Z","cross_cats_sorted":[],"title_canon_sha256":"1f86ab7389dd0c80cdbebbfcb96a7db5e1a5f9c23a420bb508942be5f9dbe76b","abstract_canon_sha256":"56581fb666a921d0d8980d4da50716ac11812024593acfbac1a48814a8939770"},"schema_version":"1.0"},"canonical_sha256":"fcb759b8bc7d251833ae62e425573796d8af755af99761083010e401a758a16a","source":{"kind":"arxiv","id":"1804.07036","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.07036","created_at":"2026-05-18T00:18:04Z"},{"alias_kind":"arxiv_version","alias_value":"1804.07036v1","created_at":"2026-05-18T00:18:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07036","created_at":"2026-05-18T00:18:04Z"},{"alias_kind":"pith_short_12","alias_value":"7S3VTOF4PUSR","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7S3VTOF4PUSRQM5O","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7S3VTOF4","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7S3VTOF4PUSRQM5OMLSCKVZXS3","target":"record","payload":{"canonical_record":{"source":{"id":"1804.07036","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-19T08:42:32Z","cross_cats_sorted":[],"title_canon_sha256":"1f86ab7389dd0c80cdbebbfcb96a7db5e1a5f9c23a420bb508942be5f9dbe76b","abstract_canon_sha256":"56581fb666a921d0d8980d4da50716ac11812024593acfbac1a48814a8939770"},"schema_version":"1.0"},"canonical_sha256":"fcb759b8bc7d251833ae62e425573796d8af755af99761083010e401a758a16a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:04.489503Z","signature_b64":"uv4KJ9M8NI5tU/Xr5q0ZBNljJF/Uu1AdBNGtyJBJW1EZqnLOJQrpUjhvkuVunqq0SgpAQGP7AHX/B7Qy7Jl0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcb759b8bc7d251833ae62e425573796d8af755af99761083010e401a758a16a","last_reissued_at":"2026-05-18T00:18:04.489059Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:04.489059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.07036","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":"2026-05-18T00:18:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S7m09bCAW6fd0q8Sh28v3T+l4HVV8j5pzEuVq8HJwHGEx/rvh3D0kSJ/fhX+TpnV/wld7ECaxpTd6CSDqnS7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T04:17:57.131426Z"},"content_sha256":"337ca3a844c66eed21631d67682a5fca8cf8720894621696875429e3d6352db0","schema_version":"1.0","event_id":"sha256:337ca3a844c66eed21631d67682a5fca8cf8720894621696875429e3d6352db0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7S3VTOF4PUSRQM5OMLSCKVZXS3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Extract Coherent Summary via Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baotian Hu, Yuxiang WU","submitted_at":"2018-04-19T08:42:32Z","abstract_excerpt":"Coherence plays a critical role in producing a high-quality summary from a document. In recent years, neural extractive summarization is becoming increasingly attractive. However, most of them ignore the coherence of summaries when extracting sentences. As an effort towards extracting coherent summaries, we propose a neural coherence model to capture the cross-sentence semantic and syntactic coherence patterns. The proposed neural coherence model obviates the need for feature engineering and can be trained in an end-to-end fashion using unlabeled data. Empirical results show that the proposed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07036","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":"2026-05-18T00:18:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MOQimZCChPDqzetSHBCWDE0SnviWES2mR3swN663RVWsvJ06wXmXP/qGPZIIUDcr1JHhnmHB7BuYeS+bVXOKDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T04:17:57.131788Z"},"content_sha256":"769ba5b528c52dae459cef6f890d2c70c756d99502067080ad7d462ad8117330","schema_version":"1.0","event_id":"sha256:769ba5b528c52dae459cef6f890d2c70c756d99502067080ad7d462ad8117330"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7S3VTOF4PUSRQM5OMLSCKVZXS3/bundle.json","state_url":"https://pith.science/pith/7S3VTOF4PUSRQM5OMLSCKVZXS3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7S3VTOF4PUSRQM5OMLSCKVZXS3/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":"2026-06-01T04:17:57Z","links":{"resolver":"https://pith.science/pith/7S3VTOF4PUSRQM5OMLSCKVZXS3","bundle":"https://pith.science/pith/7S3VTOF4PUSRQM5OMLSCKVZXS3/bundle.json","state":"https://pith.science/pith/7S3VTOF4PUSRQM5OMLSCKVZXS3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7S3VTOF4PUSRQM5OMLSCKVZXS3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7S3VTOF4PUSRQM5OMLSCKVZXS3","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":"56581fb666a921d0d8980d4da50716ac11812024593acfbac1a48814a8939770","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-19T08:42:32Z","title_canon_sha256":"1f86ab7389dd0c80cdbebbfcb96a7db5e1a5f9c23a420bb508942be5f9dbe76b"},"schema_version":"1.0","source":{"id":"1804.07036","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.07036","created_at":"2026-05-18T00:18:04Z"},{"alias_kind":"arxiv_version","alias_value":"1804.07036v1","created_at":"2026-05-18T00:18:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07036","created_at":"2026-05-18T00:18:04Z"},{"alias_kind":"pith_short_12","alias_value":"7S3VTOF4PUSR","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7S3VTOF4PUSRQM5O","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7S3VTOF4","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:769ba5b528c52dae459cef6f890d2c70c756d99502067080ad7d462ad8117330","target":"graph","created_at":"2026-05-18T00:18:04Z","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":"Coherence plays a critical role in producing a high-quality summary from a document. In recent years, neural extractive summarization is becoming increasingly attractive. However, most of them ignore the coherence of summaries when extracting sentences. As an effort towards extracting coherent summaries, we propose a neural coherence model to capture the cross-sentence semantic and syntactic coherence patterns. The proposed neural coherence model obviates the need for feature engineering and can be trained in an end-to-end fashion using unlabeled data. Empirical results show that the proposed ","authors_text":"Baotian Hu, Yuxiang WU","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-19T08:42:32Z","title":"Learning to Extract Coherent Summary via Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07036","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":"sha256:337ca3a844c66eed21631d67682a5fca8cf8720894621696875429e3d6352db0","target":"record","created_at":"2026-05-18T00:18:04Z","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":"56581fb666a921d0d8980d4da50716ac11812024593acfbac1a48814a8939770","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-19T08:42:32Z","title_canon_sha256":"1f86ab7389dd0c80cdbebbfcb96a7db5e1a5f9c23a420bb508942be5f9dbe76b"},"schema_version":"1.0","source":{"id":"1804.07036","kind":"arxiv","version":1}},"canonical_sha256":"fcb759b8bc7d251833ae62e425573796d8af755af99761083010e401a758a16a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fcb759b8bc7d251833ae62e425573796d8af755af99761083010e401a758a16a","first_computed_at":"2026-05-18T00:18:04.489059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:04.489059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uv4KJ9M8NI5tU/Xr5q0ZBNljJF/Uu1AdBNGtyJBJW1EZqnLOJQrpUjhvkuVunqq0SgpAQGP7AHX/B7Qy7Jl0AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:04.489503Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.07036","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:337ca3a844c66eed21631d67682a5fca8cf8720894621696875429e3d6352db0","sha256:769ba5b528c52dae459cef6f890d2c70c756d99502067080ad7d462ad8117330"],"state_sha256":"629f53ef093dcfb2f08e2f6ab2d9d3f7e22b54dbd7ac4e5cfa9675c2a322d7c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"piz/7+dMyZBfXz6OuCbD0losyh7x79qnNdlfGPcEVQkARYJ1lEWC5HD5fIgTYnieYoT0o5RVuu0BTHDs1NBiDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T04:17:57.133844Z","bundle_sha256":"709f38832c4d7868565e503c0f30b68e50cde236f189d69362dfd9b80321b337"}}