{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3MNIMN2RM5N47HUVFQ5PCZ7RY6","short_pith_number":"pith:3MNIMN2R","schema_version":"1.0","canonical_sha256":"db1a863751675bcf9e952c3af167f1c7885f7faeadbfe987dcecd8f3fe00a620","source":{"kind":"arxiv","id":"2608.03859","version":1},"attestation_state":"computed","paper":{"title":"Beyond Representational Similarity: Source-Conditioned Description-Length Gain for Generative Plagiarism Detection and Candidate Source Reranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ming Li, Peijia Guo, Wenxuan Xie, Ziguang Li","submitted_at":"2026-08-04T16:03:45Z","abstract_excerpt":"Large language models (LLMs) pose challenges to academic integrity and peer review. Yet generative plagiarism detection remains an underexplored and largely unresolved challenge. Prior work on LLM-generated-text detection targets AI involvement, which may be permissible, rather than source reuse, while similarity-based methods struggle after extensive rewriting and multi-source synthesis. Motivated by the description-length view of probabilistic prediction, in which relevant side information can reduce a target sequence's code length, we introduce Source-Conditioned Description-Length Gain (SC"},"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":"2608.03859","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T16:03:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1e4fc156ebca25e85c9dac9a21a3b4ddb78c810c8050e7fcf7ab6a073bb31b55","abstract_canon_sha256":"22c822597b24f128be588c147ee7728ba12a1feb33a7d8727f9dd45b224b95e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:37:16.114044Z","signature_b64":"uJ9CD20C0IxUzssEothiPJiv4n+cgaxFIcCz0JkVZ6riBXIOA4FxZcZ8Q14NEEgg3ub1fL7pgIweupzh3ayLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db1a863751675bcf9e952c3af167f1c7885f7faeadbfe987dcecd8f3fe00a620","last_reissued_at":"2026-08-05T01:37:16.112510Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:37:16.112510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Representational Similarity: Source-Conditioned Description-Length Gain for Generative Plagiarism Detection and Candidate Source Reranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ming Li, Peijia Guo, Wenxuan Xie, Ziguang Li","submitted_at":"2026-08-04T16:03:45Z","abstract_excerpt":"Large language models (LLMs) pose challenges to academic integrity and peer review. Yet generative plagiarism detection remains an underexplored and largely unresolved challenge. Prior work on LLM-generated-text detection targets AI involvement, which may be permissible, rather than source reuse, while similarity-based methods struggle after extensive rewriting and multi-source synthesis. Motivated by the description-length view of probabilistic prediction, in which relevant side information can reduce a target sequence's code length, we introduce Source-Conditioned Description-Length Gain (SC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03859","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/2608.03859/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":"2608.03859","created_at":"2026-08-05T01:37:16.113049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03859v1","created_at":"2026-08-05T01:37:16.113049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03859","created_at":"2026-08-05T01:37:16.113049+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MNIMN2RM5N4","created_at":"2026-08-05T01:37:16.113049+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MNIMN2RM5N47HUV","created_at":"2026-08-05T01:37:16.113049+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MNIMN2R","created_at":"2026-08-05T01:37:16.113049+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/3MNIMN2RM5N47HUVFQ5PCZ7RY6","json":"https://pith.science/pith/3MNIMN2RM5N47HUVFQ5PCZ7RY6.json","graph_json":"https://pith.science/api/pith-number/3MNIMN2RM5N47HUVFQ5PCZ7RY6/graph.json","events_json":"https://pith.science/api/pith-number/3MNIMN2RM5N47HUVFQ5PCZ7RY6/events.json","paper":"https://pith.science/paper/3MNIMN2R"},"agent_actions":{"view_html":"https://pith.science/pith/3MNIMN2RM5N47HUVFQ5PCZ7RY6","download_json":"https://pith.science/pith/3MNIMN2RM5N47HUVFQ5PCZ7RY6.json","view_paper":"https://pith.science/paper/3MNIMN2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03859&json=true","fetch_graph":"https://pith.science/api/pith-number/3MNIMN2RM5N47HUVFQ5PCZ7RY6/graph.json","fetch_events":"https://pith.science/api/pith-number/3MNIMN2RM5N47HUVFQ5PCZ7RY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MNIMN2RM5N47HUVFQ5PCZ7RY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MNIMN2RM5N47HUVFQ5PCZ7RY6/action/storage_attestation","attest_author":"https://pith.science/pith/3MNIMN2RM5N47HUVFQ5PCZ7RY6/action/author_attestation","sign_citation":"https://pith.science/pith/3MNIMN2RM5N47HUVFQ5PCZ7RY6/action/citation_signature","submit_replication":"https://pith.science/pith/3MNIMN2RM5N47HUVFQ5PCZ7RY6/action/replication_record"}},"created_at":"2026-08-05T01:37:16.113049+00:00","updated_at":"2026-08-05T01:37:16.113049+00:00"}