{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:H4BWLWMRR7BFZDDONYO7RS7QVG","short_pith_number":"pith:H4BWLWMR","schema_version":"1.0","canonical_sha256":"3f0365d9918fc25c8c6e6e1df8cbf0a9978a9d1b517ada796d97d0b077da2f7f","source":{"kind":"arxiv","id":"2212.10233","version":2},"attestation_state":"computed","paper":{"title":"Pre-trained Language Models for Keyphrase Generation: A Thorough Empirical Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Di Wu, Kai-Wei Chang, Wasi Uddin Ahmad","submitted_at":"2022-12-20T13:20:21Z","abstract_excerpt":"Neural models that do not rely on pre-training have excelled in the keyphrase generation task with large annotated datasets. Meanwhile, new approaches have incorporated pre-trained language models (PLMs) for their data efficiency. However, there lacks a systematic study of how the two types of approaches compare and how different design choices can affect the performance of PLM-based models. To fill in this knowledge gap and facilitate a more informed use of PLMs for keyphrase extraction and keyphrase generation, we present an in-depth empirical study. Formulating keyphrase extraction as seque"},"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":"2212.10233","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T13:20:21Z","cross_cats_sorted":[],"title_canon_sha256":"51b752c532386b4503d7a9e580b8ccc154f362a193e5b31dca474ae01f4055ed","abstract_canon_sha256":"50f650399e1da4548357a547488779437f1e5936e31fec59925cd43be9379d0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:28.031014Z","signature_b64":"OZ4NcCwran4Vqa3N+LTzWH6Wtlzx74zcUieiaMcW3sG6JJ+tlwaUI8G0EFfenwzS+OcP6cyrlkgzCHIjQJXSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f0365d9918fc25c8c6e6e1df8cbf0a9978a9d1b517ada796d97d0b077da2f7f","last_reissued_at":"2026-07-05T07:48:28.030516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:28.030516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-trained Language Models for Keyphrase Generation: A Thorough Empirical Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Di Wu, Kai-Wei Chang, Wasi Uddin Ahmad","submitted_at":"2022-12-20T13:20:21Z","abstract_excerpt":"Neural models that do not rely on pre-training have excelled in the keyphrase generation task with large annotated datasets. Meanwhile, new approaches have incorporated pre-trained language models (PLMs) for their data efficiency. However, there lacks a systematic study of how the two types of approaches compare and how different design choices can affect the performance of PLM-based models. To fill in this knowledge gap and facilitate a more informed use of PLMs for keyphrase extraction and keyphrase generation, we present an in-depth empirical study. Formulating keyphrase extraction as seque"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10233","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/2212.10233/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":"2212.10233","created_at":"2026-07-05T07:48:28.030584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10233v2","created_at":"2026-07-05T07:48:28.030584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10233","created_at":"2026-07-05T07:48:28.030584+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4BWLWMRR7BF","created_at":"2026-07-05T07:48:28.030584+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4BWLWMRR7BFZDDO","created_at":"2026-07-05T07:48:28.030584+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4BWLWMR","created_at":"2026-07-05T07:48:28.030584+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24219","citing_title":"ERU-KG: Efficient Reference-aligned Unsupervised Keyphrase Generation","ref_index":65,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H4BWLWMRR7BFZDDONYO7RS7QVG","json":"https://pith.science/pith/H4BWLWMRR7BFZDDONYO7RS7QVG.json","graph_json":"https://pith.science/api/pith-number/H4BWLWMRR7BFZDDONYO7RS7QVG/graph.json","events_json":"https://pith.science/api/pith-number/H4BWLWMRR7BFZDDONYO7RS7QVG/events.json","paper":"https://pith.science/paper/H4BWLWMR"},"agent_actions":{"view_html":"https://pith.science/pith/H4BWLWMRR7BFZDDONYO7RS7QVG","download_json":"https://pith.science/pith/H4BWLWMRR7BFZDDONYO7RS7QVG.json","view_paper":"https://pith.science/paper/H4BWLWMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10233&json=true","fetch_graph":"https://pith.science/api/pith-number/H4BWLWMRR7BFZDDONYO7RS7QVG/graph.json","fetch_events":"https://pith.science/api/pith-number/H4BWLWMRR7BFZDDONYO7RS7QVG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4BWLWMRR7BFZDDONYO7RS7QVG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4BWLWMRR7BFZDDONYO7RS7QVG/action/storage_attestation","attest_author":"https://pith.science/pith/H4BWLWMRR7BFZDDONYO7RS7QVG/action/author_attestation","sign_citation":"https://pith.science/pith/H4BWLWMRR7BFZDDONYO7RS7QVG/action/citation_signature","submit_replication":"https://pith.science/pith/H4BWLWMRR7BFZDDONYO7RS7QVG/action/replication_record"}},"created_at":"2026-07-05T07:48:28.030584+00:00","updated_at":"2026-07-05T07:48:28.030584+00:00"}