{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CTNHBAEMAUOBFBWAFK7LHLYURS","short_pith_number":"pith:CTNHBAEM","schema_version":"1.0","canonical_sha256":"14da70808c051c1286c02abeb3af148c9a15702e577ce7706d5a2d649d9f624d","source":{"kind":"arxiv","id":"1909.03582","version":1},"attestation_state":"computed","paper":{"title":"Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Andrea Madotto, Chien-Sheng Wu, Pascale Fung, Peng Xu","submitted_at":"2019-09-09T01:33:01Z","abstract_excerpt":"Sensational headlines are headlines that capture people's attention and generate reader interest. Conventional abstractive headline generation methods, unlike human writers, do not optimize for maximal reader attention. In this paper, we propose a model that generates sensational headlines without labeled data. We first train a sensationalism scorer by classifying online headlines with many comments (\"clickbait\") against a baseline of headlines generated from a summarization model. The score from the sensationalism scorer is used as the reward for a reinforcement learner. However, maximizing t"},"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":"1909.03582","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-09T01:33:01Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"1b0b52f33652495166656bb6adfad7b1cfabfe192d9fd2bc3b51f9c23fc157ec","abstract_canon_sha256":"6c251063d87f3a84b6f4d17ce52b6e4d6a13b99726f39610c0380548b9a4c9d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:06.996489Z","signature_b64":"trPNT4lBheus3Um6j8t4mXjK7RB7Mbg/+IvpB7Xy8dyg7V8o1jPw78hSDYAtbN0kuD+E42eB6cDEcLywFOS3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14da70808c051c1286c02abeb3af148c9a15702e577ce7706d5a2d649d9f624d","last_reissued_at":"2026-07-05T00:03:06.995954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:06.995954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Andrea Madotto, Chien-Sheng Wu, Pascale Fung, Peng Xu","submitted_at":"2019-09-09T01:33:01Z","abstract_excerpt":"Sensational headlines are headlines that capture people's attention and generate reader interest. Conventional abstractive headline generation methods, unlike human writers, do not optimize for maximal reader attention. In this paper, we propose a model that generates sensational headlines without labeled data. We first train a sensationalism scorer by classifying online headlines with many comments (\"clickbait\") against a baseline of headlines generated from a summarization model. The score from the sensationalism scorer is used as the reward for a reinforcement learner. However, maximizing t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.03582","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.03582/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1909.03582","created_at":"2026-07-05T00:03:06.996012+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.03582v1","created_at":"2026-07-05T00:03:06.996012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.03582","created_at":"2026-07-05T00:03:06.996012+00:00"},{"alias_kind":"pith_short_12","alias_value":"CTNHBAEMAUOB","created_at":"2026-07-05T00:03:06.996012+00:00"},{"alias_kind":"pith_short_16","alias_value":"CTNHBAEMAUOBFBWA","created_at":"2026-07-05T00:03:06.996012+00:00"},{"alias_kind":"pith_short_8","alias_value":"CTNHBAEM","created_at":"2026-07-05T00:03:06.996012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08071","citing_title":"COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CTNHBAEMAUOBFBWAFK7LHLYURS","json":"https://pith.science/pith/CTNHBAEMAUOBFBWAFK7LHLYURS.json","graph_json":"https://pith.science/api/pith-number/CTNHBAEMAUOBFBWAFK7LHLYURS/graph.json","events_json":"https://pith.science/api/pith-number/CTNHBAEMAUOBFBWAFK7LHLYURS/events.json","paper":"https://pith.science/paper/CTNHBAEM"},"agent_actions":{"view_html":"https://pith.science/pith/CTNHBAEMAUOBFBWAFK7LHLYURS","download_json":"https://pith.science/pith/CTNHBAEMAUOBFBWAFK7LHLYURS.json","view_paper":"https://pith.science/paper/CTNHBAEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.03582&json=true","fetch_graph":"https://pith.science/api/pith-number/CTNHBAEMAUOBFBWAFK7LHLYURS/graph.json","fetch_events":"https://pith.science/api/pith-number/CTNHBAEMAUOBFBWAFK7LHLYURS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CTNHBAEMAUOBFBWAFK7LHLYURS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CTNHBAEMAUOBFBWAFK7LHLYURS/action/storage_attestation","attest_author":"https://pith.science/pith/CTNHBAEMAUOBFBWAFK7LHLYURS/action/author_attestation","sign_citation":"https://pith.science/pith/CTNHBAEMAUOBFBWAFK7LHLYURS/action/citation_signature","submit_replication":"https://pith.science/pith/CTNHBAEMAUOBFBWAFK7LHLYURS/action/replication_record"}},"created_at":"2026-07-05T00:03:06.996012+00:00","updated_at":"2026-07-05T00:03:06.996012+00:00"}