{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WKBTFJ2NQPMUYM2F5CLGPITD6Q","short_pith_number":"pith:WKBTFJ2N","schema_version":"1.0","canonical_sha256":"b28332a74d83d94c3345e89667a263f43a47bd03f0a22fe4c93b89a873b90885","source":{"kind":"arxiv","id":"2409.16605","version":1},"attestation_state":"computed","paper":{"title":"Evaluating and Enhancing Large Language Models for Novelty Assessment in Scholarly Publications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ethan Lin, Yi Fang, Zhiyuan Peng","submitted_at":"2024-09-25T04:12:38Z","abstract_excerpt":"Recent studies have evaluated the creativity/novelty of large language models (LLMs) primarily from a semantic perspective, using benchmarks from cognitive science. However, accessing the novelty in scholarly publications is a largely unexplored area in evaluating LLMs. In this paper, we introduce a scholarly novelty benchmark (SchNovel) to evaluate LLMs' ability to assess novelty in scholarly papers. SchNovel consists of 15000 pairs of papers across six fields sampled from the arXiv dataset with publication dates spanning 2 to 10 years apart. In each pair, the more recently published paper is"},"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":"2409.16605","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-25T04:12:38Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"57dc88a367f4e89589e1e6614c813c06913e7867bdfb9e3661d96b453a914e14","abstract_canon_sha256":"87f91c59ac17e566df163f7f23d23cbd073d64b700961a99d0063d840ce96d06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:36.647295Z","signature_b64":"n5BztQp3Tc8MZv0Ge4OFEF5/c7FMoxx8HIraI/WxAYnimxylqJ6S57VGSS6JdWZ3i5OnimeccFj1P+jy7eV2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b28332a74d83d94c3345e89667a263f43a47bd03f0a22fe4c93b89a873b90885","last_reissued_at":"2026-07-05T09:11:36.646730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:36.646730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating and Enhancing Large Language Models for Novelty Assessment in Scholarly Publications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ethan Lin, Yi Fang, Zhiyuan Peng","submitted_at":"2024-09-25T04:12:38Z","abstract_excerpt":"Recent studies have evaluated the creativity/novelty of large language models (LLMs) primarily from a semantic perspective, using benchmarks from cognitive science. However, accessing the novelty in scholarly publications is a largely unexplored area in evaluating LLMs. In this paper, we introduce a scholarly novelty benchmark (SchNovel) to evaluate LLMs' ability to assess novelty in scholarly papers. SchNovel consists of 15000 pairs of papers across six fields sampled from the arXiv dataset with publication dates spanning 2 to 10 years apart. In each pair, the more recently published paper is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16605","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/2409.16605/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":"2409.16605","created_at":"2026-07-05T09:11:36.646792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.16605v1","created_at":"2026-07-05T09:11:36.646792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16605","created_at":"2026-07-05T09:11:36.646792+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKBTFJ2NQPMU","created_at":"2026-07-05T09:11:36.646792+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKBTFJ2NQPMUYM2F","created_at":"2026-07-05T09:11:36.646792+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKBTFJ2N","created_at":"2026-07-05T09:11:36.646792+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.11810","citing_title":"Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15736","citing_title":"IDRBench: Understanding the Capability of Large Language Models on Interdisciplinary Research","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WKBTFJ2NQPMUYM2F5CLGPITD6Q","json":"https://pith.science/pith/WKBTFJ2NQPMUYM2F5CLGPITD6Q.json","graph_json":"https://pith.science/api/pith-number/WKBTFJ2NQPMUYM2F5CLGPITD6Q/graph.json","events_json":"https://pith.science/api/pith-number/WKBTFJ2NQPMUYM2F5CLGPITD6Q/events.json","paper":"https://pith.science/paper/WKBTFJ2N"},"agent_actions":{"view_html":"https://pith.science/pith/WKBTFJ2NQPMUYM2F5CLGPITD6Q","download_json":"https://pith.science/pith/WKBTFJ2NQPMUYM2F5CLGPITD6Q.json","view_paper":"https://pith.science/paper/WKBTFJ2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.16605&json=true","fetch_graph":"https://pith.science/api/pith-number/WKBTFJ2NQPMUYM2F5CLGPITD6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/WKBTFJ2NQPMUYM2F5CLGPITD6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKBTFJ2NQPMUYM2F5CLGPITD6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKBTFJ2NQPMUYM2F5CLGPITD6Q/action/storage_attestation","attest_author":"https://pith.science/pith/WKBTFJ2NQPMUYM2F5CLGPITD6Q/action/author_attestation","sign_citation":"https://pith.science/pith/WKBTFJ2NQPMUYM2F5CLGPITD6Q/action/citation_signature","submit_replication":"https://pith.science/pith/WKBTFJ2NQPMUYM2F5CLGPITD6Q/action/replication_record"}},"created_at":"2026-07-05T09:11:36.646792+00:00","updated_at":"2026-07-05T09:11:36.646792+00:00"}