{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FGEJI43IUNNDFB4LT6M7XG35BQ","short_pith_number":"pith:FGEJI43I","canonical_record":{"source":{"id":"2507.09488","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-13T04:21:21Z","cross_cats_sorted":[],"title_canon_sha256":"b9e4584153657f5788ab629ca50b8719464196fef1426e4ad981208e1a5f9f39","abstract_canon_sha256":"967e185799a81d5422538335b8094989ffadf7d9bd2a670f28d21b49aa8a03b0"},"schema_version":"1.0"},"canonical_sha256":"2988947368a35a32878b9f99fb9b7d0c091f8f805206402a58ad1d8f51982b44","source":{"kind":"arxiv","id":"2507.09488","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09488","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09488v1","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09488","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"pith_short_12","alias_value":"FGEJI43IUNND","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"pith_short_16","alias_value":"FGEJI43IUNNDFB4L","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"pith_short_8","alias_value":"FGEJI43I","created_at":"2026-07-05T11:36:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FGEJI43IUNNDFB4LT6M7XG35BQ","target":"record","payload":{"canonical_record":{"source":{"id":"2507.09488","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-13T04:21:21Z","cross_cats_sorted":[],"title_canon_sha256":"b9e4584153657f5788ab629ca50b8719464196fef1426e4ad981208e1a5f9f39","abstract_canon_sha256":"967e185799a81d5422538335b8094989ffadf7d9bd2a670f28d21b49aa8a03b0"},"schema_version":"1.0"},"canonical_sha256":"2988947368a35a32878b9f99fb9b7d0c091f8f805206402a58ad1d8f51982b44","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:09.859685Z","signature_b64":"eEZ6dA16Y7t9+CPeftARjztmSIY24/mPQHc0MUo2Juy23zOv5zd8c/F2/VF84kRJewxxHZAalioWLKAWTfnNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2988947368a35a32878b9f99fb9b7d0c091f8f805206402a58ad1d8f51982b44","last_reissued_at":"2026-07-05T11:36:09.859254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:09.859254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.09488","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:36:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2OMZaGrzZmNxj4iGoekFXeVvD6PzVvDuADpBdXUEWj3bR3jqE5grIymNNCrsyZcR6ZNbCI2DAKIb/tF5zhZiBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:41:31.394859Z"},"content_sha256":"33633e69f52e76f20ec70fa208b3d0ccb5594299b4093c425cb4b2594ba54b4a","schema_version":"1.0","event_id":"sha256:33633e69f52e76f20ec70fa208b3d0ccb5594299b4093c425cb4b2594ba54b4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FGEJI43IUNNDFB4LT6M7XG35BQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Criteria-Based LLM Relevance Judgments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Laura Dietz, Naghmeh Farzi","submitted_at":"2025-07-13T04:21:21Z","abstract_excerpt":"Relevance judgments are crucial for evaluating information retrieval systems, but traditional human-annotated labels are time-consuming and expensive. As a result, many researchers turn to automatic alternatives to accelerate method development. Among these, Large Language Models (LLMs) provide a scalable solution by generating relevance labels directly through prompting. However, prompting an LLM for a relevance label without constraints often results in not only incorrect predictions but also outputs that are difficult for humans to interpret. We propose the Multi-Criteria framework for LLM-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09488","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/2507.09488/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:36:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8+U5k2+L/aqSPR4GCSFP9MBDJ5Hwl1gSgRs69LbT4h0919IqlsNXkSZdiH5OvCFrie36oTL9p1VRVJHQiiMBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:41:31.396079Z"},"content_sha256":"21c13f03169d1e3d6420d06dc3e559f9a59354cca7a3ece3c39f9655f350f7a4","schema_version":"1.0","event_id":"sha256:21c13f03169d1e3d6420d06dc3e559f9a59354cca7a3ece3c39f9655f350f7a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FGEJI43IUNNDFB4LT6M7XG35BQ/bundle.json","state_url":"https://pith.science/pith/FGEJI43IUNNDFB4LT6M7XG35BQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FGEJI43IUNNDFB4LT6M7XG35BQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T22:41:31Z","links":{"resolver":"https://pith.science/pith/FGEJI43IUNNDFB4LT6M7XG35BQ","bundle":"https://pith.science/pith/FGEJI43IUNNDFB4LT6M7XG35BQ/bundle.json","state":"https://pith.science/pith/FGEJI43IUNNDFB4LT6M7XG35BQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FGEJI43IUNNDFB4LT6M7XG35BQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FGEJI43IUNNDFB4LT6M7XG35BQ","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":"967e185799a81d5422538335b8094989ffadf7d9bd2a670f28d21b49aa8a03b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-13T04:21:21Z","title_canon_sha256":"b9e4584153657f5788ab629ca50b8719464196fef1426e4ad981208e1a5f9f39"},"schema_version":"1.0","source":{"id":"2507.09488","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09488","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09488v1","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09488","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"pith_short_12","alias_value":"FGEJI43IUNND","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"pith_short_16","alias_value":"FGEJI43IUNNDFB4L","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"pith_short_8","alias_value":"FGEJI43I","created_at":"2026-07-05T11:36:09Z"}],"graph_snapshots":[{"event_id":"sha256:21c13f03169d1e3d6420d06dc3e559f9a59354cca7a3ece3c39f9655f350f7a4","target":"graph","created_at":"2026-07-05T11:36:09Z","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/2507.09488/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Relevance judgments are crucial for evaluating information retrieval systems, but traditional human-annotated labels are time-consuming and expensive. As a result, many researchers turn to automatic alternatives to accelerate method development. Among these, Large Language Models (LLMs) provide a scalable solution by generating relevance labels directly through prompting. However, prompting an LLM for a relevance label without constraints often results in not only incorrect predictions but also outputs that are difficult for humans to interpret. We propose the Multi-Criteria framework for LLM-","authors_text":"Laura Dietz, Naghmeh Farzi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-13T04:21:21Z","title":"Criteria-Based LLM Relevance Judgments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09488","kind":"arxiv","version":1},"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":"sha256:33633e69f52e76f20ec70fa208b3d0ccb5594299b4093c425cb4b2594ba54b4a","target":"record","created_at":"2026-07-05T11:36:09Z","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":"967e185799a81d5422538335b8094989ffadf7d9bd2a670f28d21b49aa8a03b0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-13T04:21:21Z","title_canon_sha256":"b9e4584153657f5788ab629ca50b8719464196fef1426e4ad981208e1a5f9f39"},"schema_version":"1.0","source":{"id":"2507.09488","kind":"arxiv","version":1}},"canonical_sha256":"2988947368a35a32878b9f99fb9b7d0c091f8f805206402a58ad1d8f51982b44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2988947368a35a32878b9f99fb9b7d0c091f8f805206402a58ad1d8f51982b44","first_computed_at":"2026-07-05T11:36:09.859254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:09.859254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eEZ6dA16Y7t9+CPeftARjztmSIY24/mPQHc0MUo2Juy23zOv5zd8c/F2/VF84kRJewxxHZAalioWLKAWTfnNBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:09.859685Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.09488","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33633e69f52e76f20ec70fa208b3d0ccb5594299b4093c425cb4b2594ba54b4a","sha256:21c13f03169d1e3d6420d06dc3e559f9a59354cca7a3ece3c39f9655f350f7a4"],"state_sha256":"8a851fc5402ac0aeceee01bb3d23ff054b276a2febe30225017e9d72e6b8f214"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/dxgx/RKuu97LTnipZXFSegzUdqpvGyqnC68WnNUVIR5/WB7ucNizvNW6UFcE5dU1pcVinbMfuss/vuOWkpxCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:41:31.401640Z","bundle_sha256":"cadea1a642bbec9162e261929d54f92e1043b1a6048be0a9a079ffa3347ec7af"}}