{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KEMOVTROKH4BVK7TBO4IHF6LPB","short_pith_number":"pith:KEMOVTRO","schema_version":"1.0","canonical_sha256":"5118eace2e51f81aabf30bb88397cb785e857fbc7b47abe799cc39f33847e1fb","source":{"kind":"arxiv","id":"1809.09672","version":3},"attestation_state":"computed","paper":{"title":"BanditSum: Extractive Summarization as a Contextual Bandit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eric Crawford, Herke van Hoof, Jackie Chi Kit Cheung, Yikang Shen, Yue Dong","submitted_at":"2018-09-25T19:18:52Z","abstract_excerpt":"In this work, we propose a novel method for training neural networks to perform single-document extractive summarization without heuristically-generated extractive labels. We call our approach BanditSum as it treats extractive summarization as a contextual bandit (CB) problem, where the model receives a document to summarize (the context), and chooses a sequence of sentences to include in the summary (the action). A policy gradient reinforcement learning algorithm is used to train the model to select sequences of sentences that maximize ROUGE score. We perform a series of experiments demonstra"},"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":"1809.09672","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-25T19:18:52Z","cross_cats_sorted":[],"title_canon_sha256":"ecae9656c00ad3232719c62013e3ec08760b2ff62ede9c337253360e45ef47ca","abstract_canon_sha256":"65e30ee3d416357d8a6d621bedfb4ea5be5d8d2d4ec33555c7a69a587c1a7c07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:46.118754Z","signature_b64":"2fJyKfGH62wS6My8tm+Oelu/XPto5Qbl+LUveXqPAado+s5C4ug+qIPfqNC8deplcOErDNaj8WDhTRLvAnQDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5118eace2e51f81aabf30bb88397cb785e857fbc7b47abe799cc39f33847e1fb","last_reissued_at":"2026-05-17T23:46:46.118135Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:46.118135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BanditSum: Extractive Summarization as a Contextual Bandit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eric Crawford, Herke van Hoof, Jackie Chi Kit Cheung, Yikang Shen, Yue Dong","submitted_at":"2018-09-25T19:18:52Z","abstract_excerpt":"In this work, we propose a novel method for training neural networks to perform single-document extractive summarization without heuristically-generated extractive labels. We call our approach BanditSum as it treats extractive summarization as a contextual bandit (CB) problem, where the model receives a document to summarize (the context), and chooses a sequence of sentences to include in the summary (the action). A policy gradient reinforcement learning algorithm is used to train the model to select sequences of sentences that maximize ROUGE score. We perform a series of experiments demonstra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.09672","kind":"arxiv","version":3},"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":"1809.09672","created_at":"2026-05-17T23:46:46.118224+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.09672v3","created_at":"2026-05-17T23:46:46.118224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.09672","created_at":"2026-05-17T23:46:46.118224+00:00"},{"alias_kind":"pith_short_12","alias_value":"KEMOVTROKH4B","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KEMOVTROKH4BVK7T","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KEMOVTRO","created_at":"2026-05-18T12:32:33.847187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2009.01325","citing_title":"Learning to summarize from human feedback","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KEMOVTROKH4BVK7TBO4IHF6LPB","json":"https://pith.science/pith/KEMOVTROKH4BVK7TBO4IHF6LPB.json","graph_json":"https://pith.science/api/pith-number/KEMOVTROKH4BVK7TBO4IHF6LPB/graph.json","events_json":"https://pith.science/api/pith-number/KEMOVTROKH4BVK7TBO4IHF6LPB/events.json","paper":"https://pith.science/paper/KEMOVTRO"},"agent_actions":{"view_html":"https://pith.science/pith/KEMOVTROKH4BVK7TBO4IHF6LPB","download_json":"https://pith.science/pith/KEMOVTROKH4BVK7TBO4IHF6LPB.json","view_paper":"https://pith.science/paper/KEMOVTRO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.09672&json=true","fetch_graph":"https://pith.science/api/pith-number/KEMOVTROKH4BVK7TBO4IHF6LPB/graph.json","fetch_events":"https://pith.science/api/pith-number/KEMOVTROKH4BVK7TBO4IHF6LPB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KEMOVTROKH4BVK7TBO4IHF6LPB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KEMOVTROKH4BVK7TBO4IHF6LPB/action/storage_attestation","attest_author":"https://pith.science/pith/KEMOVTROKH4BVK7TBO4IHF6LPB/action/author_attestation","sign_citation":"https://pith.science/pith/KEMOVTROKH4BVK7TBO4IHF6LPB/action/citation_signature","submit_replication":"https://pith.science/pith/KEMOVTROKH4BVK7TBO4IHF6LPB/action/replication_record"}},"created_at":"2026-05-17T23:46:46.118224+00:00","updated_at":"2026-05-17T23:46:46.118224+00:00"}