{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M3BN7OW74NCUCF22UHCNT5RVA7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"621b8cdc2ecf8a0e1d9ea65b76e4165de5170952f25ef3cd5b2bdce32fc3ba26","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-17T17:15:21Z","title_canon_sha256":"404b25bf050de04f0b6fbd00a3b1e41b499375116258f46d6787e9888afc4f50"},"schema_version":"1.0","source":{"id":"2412.13102","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13102","created_at":"2026-07-05T11:42:24Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13102v4","created_at":"2026-07-05T11:42:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13102","created_at":"2026-07-05T11:42:24Z"},{"alias_kind":"pith_short_12","alias_value":"M3BN7OW74NCU","created_at":"2026-07-05T11:42:24Z"},{"alias_kind":"pith_short_16","alias_value":"M3BN7OW74NCUCF22","created_at":"2026-07-05T11:42:24Z"},{"alias_kind":"pith_short_8","alias_value":"M3BN7OW7","created_at":"2026-07-05T11:42:24Z"}],"graph_snapshots":[{"event_id":"sha256:30e061b6c6eda19e2445250fbdec744130276fefb5aa2d546bbc53f82a7241ef","target":"graph","created_at":"2026-07-05T11:42:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.13102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bo Wang, Chaofan Li, Defu Lian, Han Xiao, Hao Liao, Jianlyu Chen, Nan Wang, Shitao Xiao, Zheng Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-17T17:15:21Z","title":"AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13102","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5d1c17ee2f47be3f9c3cac3970ab19db4842b9e3c30ae77090f3e6730c7b258a","target":"record","created_at":"2026-07-05T11:42:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"621b8cdc2ecf8a0e1d9ea65b76e4165de5170952f25ef3cd5b2bdce32fc3ba26","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-12-17T17:15:21Z","title_canon_sha256":"404b25bf050de04f0b6fbd00a3b1e41b499375116258f46d6787e9888afc4f50"},"schema_version":"1.0","source":{"id":"2412.13102","kind":"arxiv","version":4}},"canonical_sha256":"66c2dfbadfe34541175aa1c4d9f63507c4ab7ffc5b4d37b29ec01b6a8ffc5e41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66c2dfbadfe34541175aa1c4d9f63507c4ab7ffc5b4d37b29ec01b6a8ffc5e41","first_computed_at":"2026-07-05T11:42:24.670758Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:24.670758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZNXmnDTVz5/w53ALbyC6lY0w3Nv+eEtsVJf2KxXwPHCJ2JuZqS64VtiYGhd1LhZjWomeMN3dLfA3PyB2siyICw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:24.671208Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13102","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d1c17ee2f47be3f9c3cac3970ab19db4842b9e3c30ae77090f3e6730c7b258a","sha256:30e061b6c6eda19e2445250fbdec744130276fefb5aa2d546bbc53f82a7241ef"],"state_sha256":"28b94603a6d99318af9a4b11221613589f4614a712f0cef5f053d7cc345fbbd8"}