{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KH2V6UDPODPI6R67WSFHVBQPKD","short_pith_number":"pith:KH2V6UDP","schema_version":"1.0","canonical_sha256":"51f55f506f70de8f47dfb48a7a860f50d2d3717a3e508ca1d7a7df6e11b1be62","source":{"kind":"arxiv","id":"2104.08799","version":2},"attestation_state":"computed","paper":{"title":"Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiacheng Ye, Qi Zhang, Xipeng Qiu, Yichao Luo, Yige Xu","submitted_at":"2021-04-18T10:13:46Z","abstract_excerpt":"Aiming to generate a set of keyphrases, Keyphrase Generation (KG) is a classical task for capturing the central idea from a given document. Based on Seq2Seq models, the previous reinforcement learning framework on KG tasks utilizes the evaluation metrics to further improve the well-trained neural models. However, these KG evaluation metrics such as $F_1@5$ and $F_1@M$ are only aware of the exact correctness of predictions on phrase-level and ignore the semantic similarities between similar predictions and targets, which inhibits the model from learning deep linguistic patterns. In response to "},"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":"2104.08799","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T10:13:46Z","cross_cats_sorted":[],"title_canon_sha256":"64fef46a5a1fc1a32b9331dc6e43ab6dc35d46f8b78e8bcc877632be0a90d674","abstract_canon_sha256":"9597da02d1b344bc05f551319f0673b6c70fc88d3e604381600d4452f9cd4bf7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:03.125474Z","signature_b64":"KVIGPH1YagvXHECCRY4V/6mgZ0RiwlqyW9Nt4cNHYpF044F672RGwowdvhIcxJVzFXyskxM/8E0d7CDWnGn+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51f55f506f70de8f47dfb48a7a860f50d2d3717a3e508ca1d7a7df6e11b1be62","last_reissued_at":"2026-07-05T03:13:03.125055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:03.125055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiacheng Ye, Qi Zhang, Xipeng Qiu, Yichao Luo, Yige Xu","submitted_at":"2021-04-18T10:13:46Z","abstract_excerpt":"Aiming to generate a set of keyphrases, Keyphrase Generation (KG) is a classical task for capturing the central idea from a given document. Based on Seq2Seq models, the previous reinforcement learning framework on KG tasks utilizes the evaluation metrics to further improve the well-trained neural models. However, these KG evaluation metrics such as $F_1@5$ and $F_1@M$ are only aware of the exact correctness of predictions on phrase-level and ignore the semantic similarities between similar predictions and targets, which inhibits the model from learning deep linguistic patterns. In response to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08799","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.08799/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":"2104.08799","created_at":"2026-07-05T03:13:03.125111+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.08799v2","created_at":"2026-07-05T03:13:03.125111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08799","created_at":"2026-07-05T03:13:03.125111+00:00"},{"alias_kind":"pith_short_12","alias_value":"KH2V6UDPODPI","created_at":"2026-07-05T03:13:03.125111+00:00"},{"alias_kind":"pith_short_16","alias_value":"KH2V6UDPODPI6R67","created_at":"2026-07-05T03:13:03.125111+00:00"},{"alias_kind":"pith_short_8","alias_value":"KH2V6UDP","created_at":"2026-07-05T03:13:03.125111+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/KH2V6UDPODPI6R67WSFHVBQPKD","json":"https://pith.science/pith/KH2V6UDPODPI6R67WSFHVBQPKD.json","graph_json":"https://pith.science/api/pith-number/KH2V6UDPODPI6R67WSFHVBQPKD/graph.json","events_json":"https://pith.science/api/pith-number/KH2V6UDPODPI6R67WSFHVBQPKD/events.json","paper":"https://pith.science/paper/KH2V6UDP"},"agent_actions":{"view_html":"https://pith.science/pith/KH2V6UDPODPI6R67WSFHVBQPKD","download_json":"https://pith.science/pith/KH2V6UDPODPI6R67WSFHVBQPKD.json","view_paper":"https://pith.science/paper/KH2V6UDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.08799&json=true","fetch_graph":"https://pith.science/api/pith-number/KH2V6UDPODPI6R67WSFHVBQPKD/graph.json","fetch_events":"https://pith.science/api/pith-number/KH2V6UDPODPI6R67WSFHVBQPKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KH2V6UDPODPI6R67WSFHVBQPKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KH2V6UDPODPI6R67WSFHVBQPKD/action/storage_attestation","attest_author":"https://pith.science/pith/KH2V6UDPODPI6R67WSFHVBQPKD/action/author_attestation","sign_citation":"https://pith.science/pith/KH2V6UDPODPI6R67WSFHVBQPKD/action/citation_signature","submit_replication":"https://pith.science/pith/KH2V6UDPODPI6R67WSFHVBQPKD/action/replication_record"}},"created_at":"2026-07-05T03:13:03.125111+00:00","updated_at":"2026-07-05T03:13:03.125111+00:00"}