{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HETAOZWMDDUCDU4O2IPVMALGMI","short_pith_number":"pith:HETAOZWM","canonical_record":{"source":{"id":"1904.02020","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-04-03T14:24:04Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"66b42d6ba1b090115f88de781603e228fa25d5fea1e0af0b082f77296de5c5d3","abstract_canon_sha256":"9afd2b1fc2ac88222f71726320e8a295b42e10e911f9a909344724cdf7c8d2e7"},"schema_version":"1.0"},"canonical_sha256":"39260766cc18e821d38ed21f560166623d0518ab797643511c0d9b48e12e5e29","source":{"kind":"arxiv","id":"1904.02020","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.02020","created_at":"2026-05-17T23:49:20Z"},{"alias_kind":"arxiv_version","alias_value":"1904.02020v2","created_at":"2026-05-17T23:49:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02020","created_at":"2026-05-17T23:49:20Z"},{"alias_kind":"pith_short_12","alias_value":"HETAOZWMDDUC","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HETAOZWMDDUCDU4O","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HETAOZWM","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HETAOZWMDDUCDU4O2IPVMALGMI","target":"record","payload":{"canonical_record":{"source":{"id":"1904.02020","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-04-03T14:24:04Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"66b42d6ba1b090115f88de781603e228fa25d5fea1e0af0b082f77296de5c5d3","abstract_canon_sha256":"9afd2b1fc2ac88222f71726320e8a295b42e10e911f9a909344724cdf7c8d2e7"},"schema_version":"1.0"},"canonical_sha256":"39260766cc18e821d38ed21f560166623d0518ab797643511c0d9b48e12e5e29","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:20.022208Z","signature_b64":"HbgsUgrTsRNmoeif2ltXBx/kCbZeCjwXPyb/apLWYetH/FSAtKn7eTkw6Mi5VY36yonZoyJds29RvuydVcLnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39260766cc18e821d38ed21f560166623d0518ab797643511c0d9b48e12e5e29","last_reissued_at":"2026-05-17T23:49:20.021487Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:20.021487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.02020","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":"2026-05-17T23:49:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R13hET5NHOy4BLQlOvUvxmzHf7Go9f+1wWPJu0DsJ1E3s294aHtdXA1dPN9rqSEC5a8hkfS5EYDtemgXwUcLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T05:12:28.019411Z"},"content_sha256":"ad025d1b07c4e13e419319252b5f75c4b09282aa774883ecd39f3b992550774c","schema_version":"1.0","event_id":"sha256:ad025d1b07c4e13e419319252b5f75c4b09282aa774883ecd39f3b992550774c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HETAOZWMDDUCDU4O2IPVMALGMI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Jointly Extracting and Compressing Documents with Summary State Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Afonso Mendes, Andr\\'e F. T. Martins, Sebasti\\~ao Miranda, Shashi Narayan, Shay B. Cohen, Zita Marinho","submitted_at":"2019-04-03T14:24:04Z","abstract_excerpt":"We present a new neural model for text summarization that first extracts sentences from a document and then compresses them. The proposed model offers a balance that sidesteps the difficulties in abstractive methods while generating more concise summaries than extractive methods. In addition, our model dynamically determines the length of the output summary based on the gold summaries it observes during training and does not require length constraints typical to extractive summarization. The model achieves state-of-the-art results on the CNN/DailyMail and Newsroom datasets, improving over curr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02020","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":""},"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":"2026-05-17T23:49:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z5q4nGjoUDtJZ9KS35zwlVR419WBSHSZE0l8CvfauRDCVbEeFPTrmj60P/9gqGNpQof0uRupsbb6JR1h7qdeAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T05:12:28.020109Z"},"content_sha256":"58196d576e1f223ecaf43b9fa6c0310f9bde05b12d190de4b2b35e746f98a3c8","schema_version":"1.0","event_id":"sha256:58196d576e1f223ecaf43b9fa6c0310f9bde05b12d190de4b2b35e746f98a3c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HETAOZWMDDUCDU4O2IPVMALGMI/bundle.json","state_url":"https://pith.science/pith/HETAOZWMDDUCDU4O2IPVMALGMI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HETAOZWMDDUCDU4O2IPVMALGMI/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":"2026-06-08T05:12:28Z","links":{"resolver":"https://pith.science/pith/HETAOZWMDDUCDU4O2IPVMALGMI","bundle":"https://pith.science/pith/HETAOZWMDDUCDU4O2IPVMALGMI/bundle.json","state":"https://pith.science/pith/HETAOZWMDDUCDU4O2IPVMALGMI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HETAOZWMDDUCDU4O2IPVMALGMI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HETAOZWMDDUCDU4O2IPVMALGMI","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":"9afd2b1fc2ac88222f71726320e8a295b42e10e911f9a909344724cdf7c8d2e7","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-04-03T14:24:04Z","title_canon_sha256":"66b42d6ba1b090115f88de781603e228fa25d5fea1e0af0b082f77296de5c5d3"},"schema_version":"1.0","source":{"id":"1904.02020","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.02020","created_at":"2026-05-17T23:49:20Z"},{"alias_kind":"arxiv_version","alias_value":"1904.02020v2","created_at":"2026-05-17T23:49:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02020","created_at":"2026-05-17T23:49:20Z"},{"alias_kind":"pith_short_12","alias_value":"HETAOZWMDDUC","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HETAOZWMDDUCDU4O","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HETAOZWM","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:58196d576e1f223ecaf43b9fa6c0310f9bde05b12d190de4b2b35e746f98a3c8","target":"graph","created_at":"2026-05-17T23:49:20Z","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":"We present a new neural model for text summarization that first extracts sentences from a document and then compresses them. The proposed model offers a balance that sidesteps the difficulties in abstractive methods while generating more concise summaries than extractive methods. In addition, our model dynamically determines the length of the output summary based on the gold summaries it observes during training and does not require length constraints typical to extractive summarization. The model achieves state-of-the-art results on the CNN/DailyMail and Newsroom datasets, improving over curr","authors_text":"Afonso Mendes, Andr\\'e F. T. Martins, Sebasti\\~ao Miranda, Shashi Narayan, Shay B. Cohen, Zita Marinho","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-04-03T14:24:04Z","title":"Jointly Extracting and Compressing Documents with Summary State Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02020","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:ad025d1b07c4e13e419319252b5f75c4b09282aa774883ecd39f3b992550774c","target":"record","created_at":"2026-05-17T23:49:20Z","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":"9afd2b1fc2ac88222f71726320e8a295b42e10e911f9a909344724cdf7c8d2e7","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-04-03T14:24:04Z","title_canon_sha256":"66b42d6ba1b090115f88de781603e228fa25d5fea1e0af0b082f77296de5c5d3"},"schema_version":"1.0","source":{"id":"1904.02020","kind":"arxiv","version":2}},"canonical_sha256":"39260766cc18e821d38ed21f560166623d0518ab797643511c0d9b48e12e5e29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39260766cc18e821d38ed21f560166623d0518ab797643511c0d9b48e12e5e29","first_computed_at":"2026-05-17T23:49:20.021487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:20.021487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HbgsUgrTsRNmoeif2ltXBx/kCbZeCjwXPyb/apLWYetH/FSAtKn7eTkw6Mi5VY36yonZoyJds29RvuydVcLnAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:20.022208Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.02020","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad025d1b07c4e13e419319252b5f75c4b09282aa774883ecd39f3b992550774c","sha256:58196d576e1f223ecaf43b9fa6c0310f9bde05b12d190de4b2b35e746f98a3c8"],"state_sha256":"a7ca365daa304dada5e9b29399311e48b6f8221231430eab422693dc84f9281b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sBU6Ib0HKasylLi1v3ELOcmU2J6jzyWM3bTvf7ol4VNlyeu6TbnzsEkvwpC2pyRNJ5i5TTBvDBeXJ7LaPY60Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T05:12:28.023685Z","bundle_sha256":"649d772aa32a79afb3183d51342f97d19574118715030de7fa0f2b0bc645ae5d"}}