{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:CKJ2WQ2DASZGYI3GV6425DANMX","short_pith_number":"pith:CKJ2WQ2D","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"},"canonical_sha256":"1293ab434304b26c2366afb9ae8c0d65e452428d2bbcaa4d6ed9e8545c1c9bec","source":{"kind":"arxiv","id":"1711.03859","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.03859","created_at":"2026-05-18T00:30:40Z"},{"alias_kind":"arxiv_version","alias_value":"1711.03859v2","created_at":"2026-05-18T00:30:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.03859","created_at":"2026-05-18T00:30:40Z"},{"alias_kind":"pith_short_12","alias_value":"CKJ2WQ2DASZG","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CKJ2WQ2DASZGYI3G","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CKJ2WQ2D","created_at":"2026-05-18T12:31:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:CKJ2WQ2DASZGYI3GV6425DANMX","target":"record","payload":{"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"},"canonical_sha256":"1293ab434304b26c2366afb9ae8c0d65e452428d2bbcaa4d6ed9e8545c1c9bec","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"},"source_kind":"arxiv","source_id":"1711.03859","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":"2026-05-18T00:30:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4WuUjqxxRaU0QL6ZlFVu3zk7wXJM2cVvyBsFZfM86hg0yJYWA2w2QOKRWPwL9hmS7DZMmd7Gp8qJl95Z9jB2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T07:37:03.137420Z"},"content_sha256":"c359ee3856c659a7c28180443701144b8646c7e1f39c6c3994501b46ee84c8b2","schema_version":"1.0","event_id":"sha256:c359ee3856c659a7c28180443701144b8646c7e1f39c6c3994501b46ee84c8b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:CKJ2WQ2DASZGYI3GV6425DANMX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:30:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XkaeFXLzBHssLS1hoXcQ9LrJlmay+fEvzkplsRkq2XK2vxBcco1f1PieesNxZ/6+4z3Ol02k8YYNfiaCVCowBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T07:37:03.137901Z"},"content_sha256":"a395c71fc24ee4b825bebdec577e3248e7dd10da00d7efdcff42e4b08327faa5","schema_version":"1.0","event_id":"sha256:a395c71fc24ee4b825bebdec577e3248e7dd10da00d7efdcff42e4b08327faa5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CKJ2WQ2DASZGYI3GV6425DANMX/bundle.json","state_url":"https://pith.science/pith/CKJ2WQ2DASZGYI3GV6425DANMX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CKJ2WQ2DASZGYI3GV6425DANMX/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":"2026-06-25T07:37:03Z","links":{"resolver":"https://pith.science/pith/CKJ2WQ2DASZGYI3GV6425DANMX","bundle":"https://pith.science/pith/CKJ2WQ2DASZGYI3GV6425DANMX/bundle.json","state":"https://pith.science/pith/CKJ2WQ2DASZGYI3GV6425DANMX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CKJ2WQ2DASZGYI3GV6425DANMX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:CKJ2WQ2DASZGYI3GV6425DANMX","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":"381aaef1b613481ff7f0bb8bacb13578ec80e38319b1eed809b07299ff3bc34c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-10T15:14:49Z","title_canon_sha256":"89117b7f0a5ac1aa8530f3b20f092e94058d7b6862f4456d7b919e2f70a7775d"},"schema_version":"1.0","source":{"id":"1711.03859","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.03859","created_at":"2026-05-18T00:30:40Z"},{"alias_kind":"arxiv_version","alias_value":"1711.03859v2","created_at":"2026-05-18T00:30:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.03859","created_at":"2026-05-18T00:30:40Z"},{"alias_kind":"pith_short_12","alias_value":"CKJ2WQ2DASZG","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CKJ2WQ2DASZGYI3G","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CKJ2WQ2D","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:a395c71fc24ee4b825bebdec577e3248e7dd10da00d7efdcff42e4b08327faa5","target":"graph","created_at":"2026-05-18T00:30:40Z","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":"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","authors_text":"Diego Molla","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-10T15:14:49Z","title":"Towards the Use of Deep Reinforcement Learning with Global Policy For Query-based Extractive Summarisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.03859","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:c359ee3856c659a7c28180443701144b8646c7e1f39c6c3994501b46ee84c8b2","target":"record","created_at":"2026-05-18T00:30:40Z","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":"381aaef1b613481ff7f0bb8bacb13578ec80e38319b1eed809b07299ff3bc34c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-10T15:14:49Z","title_canon_sha256":"89117b7f0a5ac1aa8530f3b20f092e94058d7b6862f4456d7b919e2f70a7775d"},"schema_version":"1.0","source":{"id":"1711.03859","kind":"arxiv","version":2}},"canonical_sha256":"1293ab434304b26c2366afb9ae8c0d65e452428d2bbcaa4d6ed9e8545c1c9bec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1293ab434304b26c2366afb9ae8c0d65e452428d2bbcaa4d6ed9e8545c1c9bec","first_computed_at":"2026-05-18T00:30:40.010800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:40.010800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VwFt94D1uz5vKGlnHqX0aPMyNWFhP6j7QuoOp5HVfI+7NUqymemE3v0/FObpqvfZvNJyhyOZSyVSlwBGz9qbCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:40.011528Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.03859","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c359ee3856c659a7c28180443701144b8646c7e1f39c6c3994501b46ee84c8b2","sha256:a395c71fc24ee4b825bebdec577e3248e7dd10da00d7efdcff42e4b08327faa5"],"state_sha256":"1db78bb32b7458f696183889c730c5442938bf5920cf08b4072336049b583a6a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/CCBMYCQZ9Q1xaTUNiSc5GdDx7MFxyk37rqbzRFy8aWhzxh1CwrrxOhtZhSE5yPLH7+RSw6JmcZK8vZ7qoo2CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T07:37:03.140290Z","bundle_sha256":"c03b897e5b366e9b8b1084bb423800427dab42a07bd0dd483287bbf9e5e1ddd4"}}