{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LNPSKJJNMOWAC5JUFXRDF77WKN","short_pith_number":"pith:LNPSKJJN","schema_version":"1.0","canonical_sha256":"5b5f25252d63ac0175342de232fff6537746dd53830b0a8d48eac0a830fc0485","source":{"kind":"arxiv","id":"2505.08941","version":1},"attestation_state":"computed","paper":{"title":"ForeCite: Adapting Pre-Trained Language Models to Predict Future Citation Rates of Academic Papers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Alex Bihlo, Gavin Hull","submitted_at":"2025-05-13T20:10:00Z","abstract_excerpt":"Predicting the future citation rates of academic papers is an important step toward the automation of research evaluation and the acceleration of scientific progress. We present $\\textbf{ForeCite}$, a simple but powerful framework to append pre-trained causal language models with a linear head for average monthly citation rate prediction. Adapting transformers for regression tasks, ForeCite achieves a test correlation of $\\rho = 0.826$ on a curated dataset of 900K+ biomedical papers published between 2000 and 2024, a 27-point improvement over the previous state-of-the-art. Comprehensive scalin"},"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":"2505.08941","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-13T20:10:00Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1e8fff30146132cb48fffd6316d5d48ddf5d49fa7759090dacf3b824143b5e0d","abstract_canon_sha256":"2e7b736c983110f93c4b88d5045700086dff05c972c4d49f8fd9e17adceae58e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:47.606979Z","signature_b64":"vGTtKvgaNeFvNpd+XgaV1A5HzXtY0H/MTK/RCdjritrnUwKAsdp+hbi6aguFDueSQcoCtIM4KASfwlPv8c88Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b5f25252d63ac0175342de232fff6537746dd53830b0a8d48eac0a830fc0485","last_reissued_at":"2026-07-05T11:02:47.606527Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:47.606527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ForeCite: Adapting Pre-Trained Language Models to Predict Future Citation Rates of Academic Papers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Alex Bihlo, Gavin Hull","submitted_at":"2025-05-13T20:10:00Z","abstract_excerpt":"Predicting the future citation rates of academic papers is an important step toward the automation of research evaluation and the acceleration of scientific progress. We present $\\textbf{ForeCite}$, a simple but powerful framework to append pre-trained causal language models with a linear head for average monthly citation rate prediction. Adapting transformers for regression tasks, ForeCite achieves a test correlation of $\\rho = 0.826$ on a curated dataset of 900K+ biomedical papers published between 2000 and 2024, a 27-point improvement over the previous state-of-the-art. Comprehensive scalin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08941","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/2505.08941/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":"2505.08941","created_at":"2026-07-05T11:02:47.606583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.08941v1","created_at":"2026-07-05T11:02:47.606583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08941","created_at":"2026-07-05T11:02:47.606583+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNPSKJJNMOWA","created_at":"2026-07-05T11:02:47.606583+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNPSKJJNMOWAC5JU","created_at":"2026-07-05T11:02:47.606583+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNPSKJJN","created_at":"2026-07-05T11:02:47.606583+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22176","citing_title":"LLM-Metrics: Measuring Research Impact Through Large Language Model Memory","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LNPSKJJNMOWAC5JUFXRDF77WKN","json":"https://pith.science/pith/LNPSKJJNMOWAC5JUFXRDF77WKN.json","graph_json":"https://pith.science/api/pith-number/LNPSKJJNMOWAC5JUFXRDF77WKN/graph.json","events_json":"https://pith.science/api/pith-number/LNPSKJJNMOWAC5JUFXRDF77WKN/events.json","paper":"https://pith.science/paper/LNPSKJJN"},"agent_actions":{"view_html":"https://pith.science/pith/LNPSKJJNMOWAC5JUFXRDF77WKN","download_json":"https://pith.science/pith/LNPSKJJNMOWAC5JUFXRDF77WKN.json","view_paper":"https://pith.science/paper/LNPSKJJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.08941&json=true","fetch_graph":"https://pith.science/api/pith-number/LNPSKJJNMOWAC5JUFXRDF77WKN/graph.json","fetch_events":"https://pith.science/api/pith-number/LNPSKJJNMOWAC5JUFXRDF77WKN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNPSKJJNMOWAC5JUFXRDF77WKN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNPSKJJNMOWAC5JUFXRDF77WKN/action/storage_attestation","attest_author":"https://pith.science/pith/LNPSKJJNMOWAC5JUFXRDF77WKN/action/author_attestation","sign_citation":"https://pith.science/pith/LNPSKJJNMOWAC5JUFXRDF77WKN/action/citation_signature","submit_replication":"https://pith.science/pith/LNPSKJJNMOWAC5JUFXRDF77WKN/action/replication_record"}},"created_at":"2026-07-05T11:02:47.606583+00:00","updated_at":"2026-07-05T11:02:47.606583+00:00"}