{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6IF3WQJH5Y4EYMMQBU2TEWPNWU","short_pith_number":"pith:6IF3WQJH","schema_version":"1.0","canonical_sha256":"f20bbb4127ee384c31900d353259edb5129ac13336c0d66150f5ab9a5b1ec90d","source":{"kind":"arxiv","id":"1804.06451","version":2},"attestation_state":"computed","paper":{"title":"Multi-Reward Reinforced Summarization with Saliency and Entailment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Mohit Bansal, Ramakanth Pasunuru","submitted_at":"2018-04-17T19:39:26Z","abstract_excerpt":"Abstractive text summarization is the task of compressing and rewriting a long document into a short summary while maintaining saliency, directed logical entailment, and non-redundancy. In this work, we address these three important aspects of a good summary via a reinforcement learning approach with two novel reward functions: ROUGESal and Entail, on top of a coverage-based baseline. The ROUGESal reward modifies the ROUGE metric by up-weighting the salient phrases/words detected via a keyphrase classifier. The Entail reward gives high (length-normalized) scores to logically-entailed summaries"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1804.06451","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-17T19:39:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b755ce4eddf187555f318ef35f871344f9e24fe8ba5f8a2bdbf99f1b74a10a6a","abstract_canon_sha256":"5a2f7bfd235987dbc043523146507ed737fa6edb3d9ca979cfd18a2b0d49c9b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:44.045127Z","signature_b64":"aJsEy5ol6FAHnJhfshGRfs2I86dS/H6MsW1bo+91MG6Gp1OxTBGVF44wURGV0j0fddcTiH+ACVKDT5uNOgyzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f20bbb4127ee384c31900d353259edb5129ac13336c0d66150f5ab9a5b1ec90d","last_reissued_at":"2026-05-18T00:14:44.044723Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:44.044723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Reward Reinforced Summarization with Saliency and Entailment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Mohit Bansal, Ramakanth Pasunuru","submitted_at":"2018-04-17T19:39:26Z","abstract_excerpt":"Abstractive text summarization is the task of compressing and rewriting a long document into a short summary while maintaining saliency, directed logical entailment, and non-redundancy. In this work, we address these three important aspects of a good summary via a reinforcement learning approach with two novel reward functions: ROUGESal and Entail, on top of a coverage-based baseline. The ROUGESal reward modifies the ROUGE metric by up-weighting the salient phrases/words detected via a keyphrase classifier. The Entail reward gives high (length-normalized) scores to logically-entailed summaries"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06451","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1804.06451","created_at":"2026-05-18T00:14:44.044790+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.06451v2","created_at":"2026-05-18T00:14:44.044790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06451","created_at":"2026-05-18T00:14:44.044790+00:00"},{"alias_kind":"pith_short_12","alias_value":"6IF3WQJH5Y4E","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"6IF3WQJH5Y4EYMMQ","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"6IF3WQJH","created_at":"2026-05-18T12:32:08.215937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6IF3WQJH5Y4EYMMQBU2TEWPNWU","json":"https://pith.science/pith/6IF3WQJH5Y4EYMMQBU2TEWPNWU.json","graph_json":"https://pith.science/api/pith-number/6IF3WQJH5Y4EYMMQBU2TEWPNWU/graph.json","events_json":"https://pith.science/api/pith-number/6IF3WQJH5Y4EYMMQBU2TEWPNWU/events.json","paper":"https://pith.science/paper/6IF3WQJH"},"agent_actions":{"view_html":"https://pith.science/pith/6IF3WQJH5Y4EYMMQBU2TEWPNWU","download_json":"https://pith.science/pith/6IF3WQJH5Y4EYMMQBU2TEWPNWU.json","view_paper":"https://pith.science/paper/6IF3WQJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.06451&json=true","fetch_graph":"https://pith.science/api/pith-number/6IF3WQJH5Y4EYMMQBU2TEWPNWU/graph.json","fetch_events":"https://pith.science/api/pith-number/6IF3WQJH5Y4EYMMQBU2TEWPNWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6IF3WQJH5Y4EYMMQBU2TEWPNWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6IF3WQJH5Y4EYMMQBU2TEWPNWU/action/storage_attestation","attest_author":"https://pith.science/pith/6IF3WQJH5Y4EYMMQBU2TEWPNWU/action/author_attestation","sign_citation":"https://pith.science/pith/6IF3WQJH5Y4EYMMQBU2TEWPNWU/action/citation_signature","submit_replication":"https://pith.science/pith/6IF3WQJH5Y4EYMMQBU2TEWPNWU/action/replication_record"}},"created_at":"2026-05-18T00:14:44.044790+00:00","updated_at":"2026-05-18T00:14:44.044790+00:00"}