{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IMKV22NXZT3245UIMZDIJKAJRB","short_pith_number":"pith:IMKV22NX","schema_version":"1.0","canonical_sha256":"43155d69b7ccf7ae7688664684a8098846ae0ea460c3d8e102be80c08791d924","source":{"kind":"arxiv","id":"2502.16487","version":3},"attestation_state":"computed","paper":{"title":"All That Glitters is Not Novel: Plagiarism in AI Generated Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Danish Pruthi, Tarun Gupta","submitted_at":"2025-02-23T08:00:33Z","abstract_excerpt":"Automating scientific research is considered the final frontier of science. Recently, several papers claim autonomous research agents can generate novel research ideas. Amidst the prevailing optimism, we document a critical concern: a considerable fraction of such research documents are smartly plagiarized. Unlike past efforts where experts evaluate the novelty and feasibility of research ideas, we request $13$ experts to operate under a different situational logic: to identify similarities between LLM-generated research documents and existing work. Concerningly, the experts identify $24\\%$ of"},"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":"2502.16487","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-23T08:00:33Z","cross_cats_sorted":[],"title_canon_sha256":"98b1449cec98e86b47a61394797adb57fc4c60be9aa9047c031ebfecc8855841","abstract_canon_sha256":"2305bf187b7094150fa6a07a4b1b7f75bb8d22e62eec0c242bc680dd9e37f176"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:13.918447Z","signature_b64":"jwx0/mn6SMq+t0Soy8RNJzt37DzLN063disPRifYL8leT1yTsDeQNtYmI6p9n+442UB4OVZIgFpQJ1YvCI1eCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43155d69b7ccf7ae7688664684a8098846ae0ea460c3d8e102be80c08791d924","last_reissued_at":"2026-07-05T12:05:13.917943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:13.917943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"All That Glitters is Not Novel: Plagiarism in AI Generated Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Danish Pruthi, Tarun Gupta","submitted_at":"2025-02-23T08:00:33Z","abstract_excerpt":"Automating scientific research is considered the final frontier of science. Recently, several papers claim autonomous research agents can generate novel research ideas. Amidst the prevailing optimism, we document a critical concern: a considerable fraction of such research documents are smartly plagiarized. Unlike past efforts where experts evaluate the novelty and feasibility of research ideas, we request $13$ experts to operate under a different situational logic: to identify similarities between LLM-generated research documents and existing work. Concerningly, the experts identify $24\\%$ of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16487","kind":"arxiv","version":3},"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/2502.16487/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":"2502.16487","created_at":"2026-07-05T12:05:13.918006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.16487v3","created_at":"2026-07-05T12:05:13.918006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16487","created_at":"2026-07-05T12:05:13.918006+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMKV22NXZT32","created_at":"2026-07-05T12:05:13.918006+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMKV22NXZT3245UI","created_at":"2026-07-05T12:05:13.918006+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMKV22NX","created_at":"2026-07-05T12:05:13.918006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25198","citing_title":"Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25198","citing_title":"Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2409.14634","citing_title":"Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty Evaluation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2602.10995","citing_title":"A Human-Centric Framework for Data Attribution in Large Language Models","ref_index":82,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IMKV22NXZT3245UIMZDIJKAJRB","json":"https://pith.science/pith/IMKV22NXZT3245UIMZDIJKAJRB.json","graph_json":"https://pith.science/api/pith-number/IMKV22NXZT3245UIMZDIJKAJRB/graph.json","events_json":"https://pith.science/api/pith-number/IMKV22NXZT3245UIMZDIJKAJRB/events.json","paper":"https://pith.science/paper/IMKV22NX"},"agent_actions":{"view_html":"https://pith.science/pith/IMKV22NXZT3245UIMZDIJKAJRB","download_json":"https://pith.science/pith/IMKV22NXZT3245UIMZDIJKAJRB.json","view_paper":"https://pith.science/paper/IMKV22NX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.16487&json=true","fetch_graph":"https://pith.science/api/pith-number/IMKV22NXZT3245UIMZDIJKAJRB/graph.json","fetch_events":"https://pith.science/api/pith-number/IMKV22NXZT3245UIMZDIJKAJRB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMKV22NXZT3245UIMZDIJKAJRB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMKV22NXZT3245UIMZDIJKAJRB/action/storage_attestation","attest_author":"https://pith.science/pith/IMKV22NXZT3245UIMZDIJKAJRB/action/author_attestation","sign_citation":"https://pith.science/pith/IMKV22NXZT3245UIMZDIJKAJRB/action/citation_signature","submit_replication":"https://pith.science/pith/IMKV22NXZT3245UIMZDIJKAJRB/action/replication_record"}},"created_at":"2026-07-05T12:05:13.918006+00:00","updated_at":"2026-07-05T12:05:13.918006+00:00"}