{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7TXERVHUJLLI6G3QWSDXTWLENC","short_pith_number":"pith:7TXERVHU","schema_version":"1.0","canonical_sha256":"fcee48d4f44ad68f1b70b48779d96468a87d1a54e5d2b70ab812ce0ab5becef0","source":{"kind":"arxiv","id":"2405.16546","version":2},"attestation_state":"computed","paper":{"title":"Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Gang Wang, Ji-Rong Wen, Jun Xu, Liang Pang, Rongju Ruan, Sunhao Dai, Weihao Liu, Yuqi Zhou, Zhenhua Dong","submitted_at":"2024-05-26T12:30:20Z","abstract_excerpt":"The proliferation of Large Language Models (LLMs) has led to an influx of AI-generated content (AIGC) on the internet, transforming the corpus of Information Retrieval (IR) systems from solely human-written to a coexistence with LLM-generated content. The impact of this surge in AIGC on IR systems remains an open question, with the primary challenge being the lack of a dedicated benchmark for researchers. In this paper, we introduce Cocktail, a comprehensive benchmark tailored for evaluating IR models in this mixed-sourced data landscape of the LLM era. Cocktail consists of 16 diverse datasets"},"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":"2405.16546","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2024-05-26T12:30:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d5c7e7c86b25912a107f648f845d52b964153e03c600b9b3f8d6cde36d243a2c","abstract_canon_sha256":"1c1951ba0ba6ceb073a82af8a266412a4bcd15c3fedff75e8193f14a4234e120"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:00.208535Z","signature_b64":"07dEaVMrh9u8abzgj/hnQpgKfTgiih372QZPwzAh24U0B47gKoMJU2yp95fPfug4nHM2eUhEicvdA/lSChpPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcee48d4f44ad68f1b70b48779d96468a87d1a54e5d2b70ab812ce0ab5becef0","last_reissued_at":"2026-07-05T08:39:00.208044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:00.208044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Gang Wang, Ji-Rong Wen, Jun Xu, Liang Pang, Rongju Ruan, Sunhao Dai, Weihao Liu, Yuqi Zhou, Zhenhua Dong","submitted_at":"2024-05-26T12:30:20Z","abstract_excerpt":"The proliferation of Large Language Models (LLMs) has led to an influx of AI-generated content (AIGC) on the internet, transforming the corpus of Information Retrieval (IR) systems from solely human-written to a coexistence with LLM-generated content. The impact of this surge in AIGC on IR systems remains an open question, with the primary challenge being the lack of a dedicated benchmark for researchers. In this paper, we introduce Cocktail, a comprehensive benchmark tailored for evaluating IR models in this mixed-sourced data landscape of the LLM era. Cocktail consists of 16 diverse datasets"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16546","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/2405.16546/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":"2405.16546","created_at":"2026-07-05T08:39:00.208100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16546v2","created_at":"2026-07-05T08:39:00.208100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16546","created_at":"2026-07-05T08:39:00.208100+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TXERVHUJLLI","created_at":"2026-07-05T08:39:00.208100+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TXERVHUJLLI6G3Q","created_at":"2026-07-05T08:39:00.208100+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TXERVHU","created_at":"2026-07-05T08:39:00.208100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14833","citing_title":"Federated User Behavior Modeling for Privacy-Preserving LLM Recommendation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7TXERVHUJLLI6G3QWSDXTWLENC","json":"https://pith.science/pith/7TXERVHUJLLI6G3QWSDXTWLENC.json","graph_json":"https://pith.science/api/pith-number/7TXERVHUJLLI6G3QWSDXTWLENC/graph.json","events_json":"https://pith.science/api/pith-number/7TXERVHUJLLI6G3QWSDXTWLENC/events.json","paper":"https://pith.science/paper/7TXERVHU"},"agent_actions":{"view_html":"https://pith.science/pith/7TXERVHUJLLI6G3QWSDXTWLENC","download_json":"https://pith.science/pith/7TXERVHUJLLI6G3QWSDXTWLENC.json","view_paper":"https://pith.science/paper/7TXERVHU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16546&json=true","fetch_graph":"https://pith.science/api/pith-number/7TXERVHUJLLI6G3QWSDXTWLENC/graph.json","fetch_events":"https://pith.science/api/pith-number/7TXERVHUJLLI6G3QWSDXTWLENC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TXERVHUJLLI6G3QWSDXTWLENC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TXERVHUJLLI6G3QWSDXTWLENC/action/storage_attestation","attest_author":"https://pith.science/pith/7TXERVHUJLLI6G3QWSDXTWLENC/action/author_attestation","sign_citation":"https://pith.science/pith/7TXERVHUJLLI6G3QWSDXTWLENC/action/citation_signature","submit_replication":"https://pith.science/pith/7TXERVHUJLLI6G3QWSDXTWLENC/action/replication_record"}},"created_at":"2026-07-05T08:39:00.208100+00:00","updated_at":"2026-07-05T08:39:00.208100+00:00"}