{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M3BN7OW74NCUCF22UHCNT5RVA7","short_pith_number":"pith:M3BN7OW7","schema_version":"1.0","canonical_sha256":"66c2dfbadfe34541175aa1c4d9f63507c4ab7ffc5b4d37b29ec01b6a8ffc5e41","source":{"kind":"arxiv","id":"2412.13102","version":4},"attestation_state":"computed","paper":{"title":"AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Bo Wang, Chaofan Li, Defu Lian, Han Xiao, Hao Liao, Jianlyu Chen, Nan Wang, Shitao Xiao, Zheng Liu","submitted_at":"2024-12-17T17:15:21Z","abstract_excerpt":"Evaluation plays a crucial role in the advancement of information retrieval (IR) models. However, current benchmarks, which are based on predefined domains and human-labeled data, face limitations in addressing evaluation needs for emerging domains both cost-effectively and efficiently. To address this challenge, we propose the Automated Heterogeneous Information Retrieval Benchmark (AIR-Bench). AIR-Bench is distinguished by three key features: 1) Automated. The testing data in AIR-Bench is automatically generated by large language models (LLMs) without human intervention. 2) Heterogeneous. Th"},"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":"2412.13102","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-17T17:15:21Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"404b25bf050de04f0b6fbd00a3b1e41b499375116258f46d6787e9888afc4f50","abstract_canon_sha256":"621b8cdc2ecf8a0e1d9ea65b76e4165de5170952f25ef3cd5b2bdce32fc3ba26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:24.671208Z","signature_b64":"ZNXmnDTVz5/w53ALbyC6lY0w3Nv+eEtsVJf2KxXwPHCJ2JuZqS64VtiYGhd1LhZjWomeMN3dLfA3PyB2siyICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66c2dfbadfe34541175aa1c4d9f63507c4ab7ffc5b4d37b29ec01b6a8ffc5e41","last_reissued_at":"2026-07-05T11:42:24.670758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:24.670758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Bo Wang, Chaofan Li, Defu Lian, Han Xiao, Hao Liao, Jianlyu Chen, Nan Wang, Shitao Xiao, Zheng Liu","submitted_at":"2024-12-17T17:15:21Z","abstract_excerpt":"Evaluation plays a crucial role in the advancement of information retrieval (IR) models. However, current benchmarks, which are based on predefined domains and human-labeled data, face limitations in addressing evaluation needs for emerging domains both cost-effectively and efficiently. To address this challenge, we propose the Automated Heterogeneous Information Retrieval Benchmark (AIR-Bench). AIR-Bench is distinguished by three key features: 1) Automated. The testing data in AIR-Bench is automatically generated by large language models (LLMs) without human intervention. 2) Heterogeneous. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13102","kind":"arxiv","version":4},"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/2412.13102/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":"2412.13102","created_at":"2026-07-05T11:42:24.670815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13102v4","created_at":"2026-07-05T11:42:24.670815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13102","created_at":"2026-07-05T11:42:24.670815+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3BN7OW74NCU","created_at":"2026-07-05T11:42:24.670815+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3BN7OW74NCUCF22","created_at":"2026-07-05T11:42:24.670815+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3BN7OW7","created_at":"2026-07-05T11:42:24.670815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01408","citing_title":"Artificial Intelligence and Misinformation in Art: Can Vision Language Models Judge the Hand or the Machine Behind the Canvas?","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M3BN7OW74NCUCF22UHCNT5RVA7","json":"https://pith.science/pith/M3BN7OW74NCUCF22UHCNT5RVA7.json","graph_json":"https://pith.science/api/pith-number/M3BN7OW74NCUCF22UHCNT5RVA7/graph.json","events_json":"https://pith.science/api/pith-number/M3BN7OW74NCUCF22UHCNT5RVA7/events.json","paper":"https://pith.science/paper/M3BN7OW7"},"agent_actions":{"view_html":"https://pith.science/pith/M3BN7OW74NCUCF22UHCNT5RVA7","download_json":"https://pith.science/pith/M3BN7OW74NCUCF22UHCNT5RVA7.json","view_paper":"https://pith.science/paper/M3BN7OW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13102&json=true","fetch_graph":"https://pith.science/api/pith-number/M3BN7OW74NCUCF22UHCNT5RVA7/graph.json","fetch_events":"https://pith.science/api/pith-number/M3BN7OW74NCUCF22UHCNT5RVA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3BN7OW74NCUCF22UHCNT5RVA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3BN7OW74NCUCF22UHCNT5RVA7/action/storage_attestation","attest_author":"https://pith.science/pith/M3BN7OW74NCUCF22UHCNT5RVA7/action/author_attestation","sign_citation":"https://pith.science/pith/M3BN7OW74NCUCF22UHCNT5RVA7/action/citation_signature","submit_replication":"https://pith.science/pith/M3BN7OW74NCUCF22UHCNT5RVA7/action/replication_record"}},"created_at":"2026-07-05T11:42:24.670815+00:00","updated_at":"2026-07-05T11:42:24.670815+00:00"}