{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:CKJ2WQ2DASZGYI3GV6425DANMX","short_pith_number":"pith:CKJ2WQ2D","schema_version":"1.0","canonical_sha256":"1293ab434304b26c2366afb9ae8c0d65e452428d2bbcaa4d6ed9e8545c1c9bec","source":{"kind":"arxiv","id":"1711.03859","version":2},"attestation_state":"computed","paper":{"title":"Towards the Use of Deep Reinforcement Learning with Global Policy For Query-based Extractive Summarisation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Diego Molla","submitted_at":"2017-11-10T15:14:49Z","abstract_excerpt":"Supervised approaches for text summarisation suffer from the problem of mismatch between the target labels/scores of individual sentences and the evaluation score of the final summary. Reinforcement learning can solve this problem by providing a learning mechanism that uses the score of the final summary as a guide to determine the decisions made at the time of selection of each sentence. In this paper we present a proof-of-concept approach that applies a policy-gradient algorithm to learn a stochastic policy using an undiscounted reward. The method has been applied to a policy consisting of a"},"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":"1711.03859","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-10T15:14:49Z","cross_cats_sorted":[],"title_canon_sha256":"89117b7f0a5ac1aa8530f3b20f092e94058d7b6862f4456d7b919e2f70a7775d","abstract_canon_sha256":"381aaef1b613481ff7f0bb8bacb13578ec80e38319b1eed809b07299ff3bc34c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:40.011528Z","signature_b64":"VwFt94D1uz5vKGlnHqX0aPMyNWFhP6j7QuoOp5HVfI+7NUqymemE3v0/FObpqvfZvNJyhyOZSyVSlwBGz9qbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1293ab434304b26c2366afb9ae8c0d65e452428d2bbcaa4d6ed9e8545c1c9bec","last_reissued_at":"2026-05-18T00:30:40.010800Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:40.010800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards the Use of Deep Reinforcement Learning with Global Policy For Query-based Extractive Summarisation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Diego Molla","submitted_at":"2017-11-10T15:14:49Z","abstract_excerpt":"Supervised approaches for text summarisation suffer from the problem of mismatch between the target labels/scores of individual sentences and the evaluation score of the final summary. Reinforcement learning can solve this problem by providing a learning mechanism that uses the score of the final summary as a guide to determine the decisions made at the time of selection of each sentence. In this paper we present a proof-of-concept approach that applies a policy-gradient algorithm to learn a stochastic policy using an undiscounted reward. The method has been applied to a policy consisting of a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.03859","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":"1711.03859","created_at":"2026-05-18T00:30:40.010919+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.03859v2","created_at":"2026-05-18T00:30:40.010919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.03859","created_at":"2026-05-18T00:30:40.010919+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKJ2WQ2DASZG","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKJ2WQ2DASZGYI3G","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKJ2WQ2D","created_at":"2026-05-18T12:31:10.602751+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/CKJ2WQ2DASZGYI3GV6425DANMX","json":"https://pith.science/pith/CKJ2WQ2DASZGYI3GV6425DANMX.json","graph_json":"https://pith.science/api/pith-number/CKJ2WQ2DASZGYI3GV6425DANMX/graph.json","events_json":"https://pith.science/api/pith-number/CKJ2WQ2DASZGYI3GV6425DANMX/events.json","paper":"https://pith.science/paper/CKJ2WQ2D"},"agent_actions":{"view_html":"https://pith.science/pith/CKJ2WQ2DASZGYI3GV6425DANMX","download_json":"https://pith.science/pith/CKJ2WQ2DASZGYI3GV6425DANMX.json","view_paper":"https://pith.science/paper/CKJ2WQ2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.03859&json=true","fetch_graph":"https://pith.science/api/pith-number/CKJ2WQ2DASZGYI3GV6425DANMX/graph.json","fetch_events":"https://pith.science/api/pith-number/CKJ2WQ2DASZGYI3GV6425DANMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKJ2WQ2DASZGYI3GV6425DANMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKJ2WQ2DASZGYI3GV6425DANMX/action/storage_attestation","attest_author":"https://pith.science/pith/CKJ2WQ2DASZGYI3GV6425DANMX/action/author_attestation","sign_citation":"https://pith.science/pith/CKJ2WQ2DASZGYI3GV6425DANMX/action/citation_signature","submit_replication":"https://pith.science/pith/CKJ2WQ2DASZGYI3GV6425DANMX/action/replication_record"}},"created_at":"2026-05-18T00:30:40.010919+00:00","updated_at":"2026-05-18T00:30:40.010919+00:00"}