{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PRTPBATTQLO6UXEFQAHUUHAVUU","short_pith_number":"pith:PRTPBATT","schema_version":"1.0","canonical_sha256":"7c66f0827382ddea5c85800f4a1c15a50b551eb284f2cb7da7a4e3389218e557","source":{"kind":"arxiv","id":"2410.13332","version":1},"attestation_state":"computed","paper":{"title":"Fine-Tuning Language Models on Multiple Datasets for Citation Intention Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel S. Karls, Ellad B. Tadmor, George Karypis, Mingjian Wen, Petros Karypis, Saurav Manchanda, Zeren Shui","submitted_at":"2024-10-17T08:45:02Z","abstract_excerpt":"Citation intention Classification (CIC) tools classify citations by their intention (e.g., background, motivation) and assist readers in evaluating the contribution of scientific literature. Prior research has shown that pretrained language models (PLMs) such as SciBERT can achieve state-of-the-art performance on CIC benchmarks. PLMs are trained via self-supervision tasks on a large corpus of general text and can quickly adapt to CIC tasks via moderate fine-tuning on the corresponding dataset. Despite their advantages, PLMs can easily overfit small datasets during fine-tuning. In this paper, w"},"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":"2410.13332","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T08:45:02Z","cross_cats_sorted":[],"title_canon_sha256":"d6aa55c814312ade2b319d00740227b498acbb938af9bd4cb78d57134ebe2817","abstract_canon_sha256":"c33609057522fa0e5802b289e8080b9c6f4ea228e459c453376e20f4090fefda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:58.806674Z","signature_b64":"BbRioaoiBhrXKZH/jLUkFtb+EtIDAHIQgmHOxQS6ONXAD4t3nejjTBIpkmA44IOj6wBs0sj+7O6VnYDQbDhqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c66f0827382ddea5c85800f4a1c15a50b551eb284f2cb7da7a4e3389218e557","last_reissued_at":"2026-07-05T09:21:58.806207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:58.806207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Tuning Language Models on Multiple Datasets for Citation Intention Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel S. Karls, Ellad B. Tadmor, George Karypis, Mingjian Wen, Petros Karypis, Saurav Manchanda, Zeren Shui","submitted_at":"2024-10-17T08:45:02Z","abstract_excerpt":"Citation intention Classification (CIC) tools classify citations by their intention (e.g., background, motivation) and assist readers in evaluating the contribution of scientific literature. Prior research has shown that pretrained language models (PLMs) such as SciBERT can achieve state-of-the-art performance on CIC benchmarks. PLMs are trained via self-supervision tasks on a large corpus of general text and can quickly adapt to CIC tasks via moderate fine-tuning on the corresponding dataset. Despite their advantages, PLMs can easily overfit small datasets during fine-tuning. In this paper, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13332","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/2410.13332/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":"2410.13332","created_at":"2026-07-05T09:21:58.806265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13332v1","created_at":"2026-07-05T09:21:58.806265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13332","created_at":"2026-07-05T09:21:58.806265+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRTPBATTQLO6","created_at":"2026-07-05T09:21:58.806265+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRTPBATTQLO6UXEF","created_at":"2026-07-05T09:21:58.806265+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRTPBATT","created_at":"2026-07-05T09:21:58.806265+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/PRTPBATTQLO6UXEFQAHUUHAVUU","json":"https://pith.science/pith/PRTPBATTQLO6UXEFQAHUUHAVUU.json","graph_json":"https://pith.science/api/pith-number/PRTPBATTQLO6UXEFQAHUUHAVUU/graph.json","events_json":"https://pith.science/api/pith-number/PRTPBATTQLO6UXEFQAHUUHAVUU/events.json","paper":"https://pith.science/paper/PRTPBATT"},"agent_actions":{"view_html":"https://pith.science/pith/PRTPBATTQLO6UXEFQAHUUHAVUU","download_json":"https://pith.science/pith/PRTPBATTQLO6UXEFQAHUUHAVUU.json","view_paper":"https://pith.science/paper/PRTPBATT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13332&json=true","fetch_graph":"https://pith.science/api/pith-number/PRTPBATTQLO6UXEFQAHUUHAVUU/graph.json","fetch_events":"https://pith.science/api/pith-number/PRTPBATTQLO6UXEFQAHUUHAVUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRTPBATTQLO6UXEFQAHUUHAVUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRTPBATTQLO6UXEFQAHUUHAVUU/action/storage_attestation","attest_author":"https://pith.science/pith/PRTPBATTQLO6UXEFQAHUUHAVUU/action/author_attestation","sign_citation":"https://pith.science/pith/PRTPBATTQLO6UXEFQAHUUHAVUU/action/citation_signature","submit_replication":"https://pith.science/pith/PRTPBATTQLO6UXEFQAHUUHAVUU/action/replication_record"}},"created_at":"2026-07-05T09:21:58.806265+00:00","updated_at":"2026-07-05T09:21:58.806265+00:00"}