{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KCTFDKCZWFME47TGTHIIHMOVGE","short_pith_number":"pith:KCTFDKCZ","schema_version":"1.0","canonical_sha256":"50a651a859b1584e7e6699d083b1d5312546c8fc296fc2785dea7565006aa91b","source":{"kind":"arxiv","id":"2407.12861","version":2},"attestation_state":"computed","paper":{"title":"CiteME: Can Language Models Accurately Cite Scientific Claims?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Ameya Prabhu, Andreas Hochlehnert, Matthias Bethge, Ofir Press, Ori Press, Vishaal Udandarao","submitted_at":"2024-07-10T11:31:20Z","abstract_excerpt":"Thousands of new scientific papers are published each month. Such information overload complicates researcher efforts to stay current with the state-of-the-art as well as to verify and correctly attribute claims. We pose the following research question: Given a text excerpt referencing a paper, could an LM act as a research assistant to correctly identify the referenced paper? We advance efforts to answer this question by building a benchmark that evaluates the abilities of LMs in citation attribution. Our benchmark, CiteME, consists of text excerpts from recent machine learning papers, each r"},"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":"2407.12861","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-10T11:31:20Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"8e039a6aa3d50445ee86a0c20a82f9539ac8f730509c8aa729c281ac4077a771","abstract_canon_sha256":"003bc2d2c58efdef79adb506c4f71c4d1e6e599c2fda0b22d53b7d16c8006482"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:19.011813Z","signature_b64":"uY0ojBYQt0d9z5FthHvhO9BMcXfkaxVq0fANJXq/onqcbwwYudNFT0SIA0eEXS88ZP0HMHD4qF1KiEjU5gqBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50a651a859b1584e7e6699d083b1d5312546c8fc296fc2785dea7565006aa91b","last_reissued_at":"2026-07-05T09:30:19.011359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:19.011359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CiteME: Can Language Models Accurately Cite Scientific Claims?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Ameya Prabhu, Andreas Hochlehnert, Matthias Bethge, Ofir Press, Ori Press, Vishaal Udandarao","submitted_at":"2024-07-10T11:31:20Z","abstract_excerpt":"Thousands of new scientific papers are published each month. Such information overload complicates researcher efforts to stay current with the state-of-the-art as well as to verify and correctly attribute claims. We pose the following research question: Given a text excerpt referencing a paper, could an LM act as a research assistant to correctly identify the referenced paper? We advance efforts to answer this question by building a benchmark that evaluates the abilities of LMs in citation attribution. Our benchmark, CiteME, consists of text excerpts from recent machine learning papers, each r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12861","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/2407.12861/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":"2407.12861","created_at":"2026-07-05T09:30:19.011416+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12861v2","created_at":"2026-07-05T09:30:19.011416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12861","created_at":"2026-07-05T09:30:19.011416+00:00"},{"alias_kind":"pith_short_12","alias_value":"KCTFDKCZWFME","created_at":"2026-07-05T09:30:19.011416+00:00"},{"alias_kind":"pith_short_16","alias_value":"KCTFDKCZWFME47TG","created_at":"2026-07-05T09:30:19.011416+00:00"},{"alias_kind":"pith_short_8","alias_value":"KCTFDKCZ","created_at":"2026-07-05T09:30:19.011416+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08700","citing_title":"Do You Need a Frontier Model as a Citation Verifier? Benchmarking Rubric LLMs for Deep-Research Source Attribution","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2505.11336","citing_title":"XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":151,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09554","citing_title":"LABBench2: An Improved Benchmark for AI Systems Performing Biology Research","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KCTFDKCZWFME47TGTHIIHMOVGE","json":"https://pith.science/pith/KCTFDKCZWFME47TGTHIIHMOVGE.json","graph_json":"https://pith.science/api/pith-number/KCTFDKCZWFME47TGTHIIHMOVGE/graph.json","events_json":"https://pith.science/api/pith-number/KCTFDKCZWFME47TGTHIIHMOVGE/events.json","paper":"https://pith.science/paper/KCTFDKCZ"},"agent_actions":{"view_html":"https://pith.science/pith/KCTFDKCZWFME47TGTHIIHMOVGE","download_json":"https://pith.science/pith/KCTFDKCZWFME47TGTHIIHMOVGE.json","view_paper":"https://pith.science/paper/KCTFDKCZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12861&json=true","fetch_graph":"https://pith.science/api/pith-number/KCTFDKCZWFME47TGTHIIHMOVGE/graph.json","fetch_events":"https://pith.science/api/pith-number/KCTFDKCZWFME47TGTHIIHMOVGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KCTFDKCZWFME47TGTHIIHMOVGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KCTFDKCZWFME47TGTHIIHMOVGE/action/storage_attestation","attest_author":"https://pith.science/pith/KCTFDKCZWFME47TGTHIIHMOVGE/action/author_attestation","sign_citation":"https://pith.science/pith/KCTFDKCZWFME47TGTHIIHMOVGE/action/citation_signature","submit_replication":"https://pith.science/pith/KCTFDKCZWFME47TGTHIIHMOVGE/action/replication_record"}},"created_at":"2026-07-05T09:30:19.011416+00:00","updated_at":"2026-07-05T09:30:19.011416+00:00"}