{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:W65SF6X2Z55UAJ2TXLW5QPZYVM","short_pith_number":"pith:W65SF6X2","canonical_record":{"source":{"id":"2410.14044","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-10-17T21:37:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"68d1c577fb96e7df0dcfb27e84bf15d929ec6240731a249ff67f0c6f86557492","abstract_canon_sha256":"f2fd849f44041c4c90dc9a3b7875a83f32c415d9289dfca1dad56b05e4fc7621"},"schema_version":"1.0"},"canonical_sha256":"b7bb22fafacf7b402753baedd83f38ab18426fd5e90ffdb165250358b44a5181","source":{"kind":"arxiv","id":"2410.14044","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14044","created_at":"2026-07-05T09:22:26Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14044v1","created_at":"2026-07-05T09:22:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14044","created_at":"2026-07-05T09:22:26Z"},{"alias_kind":"pith_short_12","alias_value":"W65SF6X2Z55U","created_at":"2026-07-05T09:22:26Z"},{"alias_kind":"pith_short_16","alias_value":"W65SF6X2Z55UAJ2T","created_at":"2026-07-05T09:22:26Z"},{"alias_kind":"pith_short_8","alias_value":"W65SF6X2","created_at":"2026-07-05T09:22:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:W65SF6X2Z55UAJ2TXLW5QPZYVM","target":"record","payload":{"canonical_record":{"source":{"id":"2410.14044","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-10-17T21:37:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"68d1c577fb96e7df0dcfb27e84bf15d929ec6240731a249ff67f0c6f86557492","abstract_canon_sha256":"f2fd849f44041c4c90dc9a3b7875a83f32c415d9289dfca1dad56b05e4fc7621"},"schema_version":"1.0"},"canonical_sha256":"b7bb22fafacf7b402753baedd83f38ab18426fd5e90ffdb165250358b44a5181","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:26.331801Z","signature_b64":"QQ/6/1yJxgEVLTUbHIwaIdJMagQpVIcdatuFJr5qUJKhrqgVqs5Vw6EYsuSMrLTLOnsQFlyB7ZSg2uScOEqVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7bb22fafacf7b402753baedd83f38ab18426fd5e90ffdb165250358b44a5181","last_reissued_at":"2026-07-05T09:22:26.331391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:26.331391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.14044","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":"2026-07-05T09:22:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MKtSsOAUAW05x5uQWYfz06uVEDC40nOvmdGu9FXA1onmPapaOWTREmBg29mR0d1UAxL20eJaY7NyyneVjyjVCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T16:46:16.522102Z"},"content_sha256":"ba5212cb24503979f517594a2babcb92962397e223060db6046fbe62aef46d52","schema_version":"1.0","event_id":"sha256:ba5212cb24503979f517594a2babcb92962397e223060db6046fbe62aef46d52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:W65SF6X2Z55UAJ2TXLW5QPZYVM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Best in Tau@LLMJudge: Criteria-Based Relevance Evaluation with Llama3","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Laura Dietz, Naghmeh Farzi","submitted_at":"2024-10-17T21:37:08Z","abstract_excerpt":"Traditional evaluation of information retrieval (IR) systems relies on human-annotated relevance labels, which can be both biased and costly at scale. In this context, large language models (LLMs) offer an alternative by allowing us to directly prompt them to assign relevance labels for passages associated with each query. In this study, we explore alternative methods to directly prompt LLMs for assigned relevance labels, by exploring two hypotheses:\n  Hypothesis 1 assumes that it is helpful to break down \"relevance\" into specific criteria - exactness, coverage, topicality, and contextual fit."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14044","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/2410.14044/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":"2026-07-05T09:22:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YzJFhT6x6gD7dFvVBin/GerSvIwqv1OawJ5E1DvP4yWGrNdAvfAkb1x3CmuCrLNfDGrYiEEKRj7v/As4BwefAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T16:46:16.522614Z"},"content_sha256":"9d2d279caed1873f1d48f2d55ee3fe7f47faceef3766a642f9ef29730715e3c2","schema_version":"1.0","event_id":"sha256:9d2d279caed1873f1d48f2d55ee3fe7f47faceef3766a642f9ef29730715e3c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W65SF6X2Z55UAJ2TXLW5QPZYVM/bundle.json","state_url":"https://pith.science/pith/W65SF6X2Z55UAJ2TXLW5QPZYVM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W65SF6X2Z55UAJ2TXLW5QPZYVM/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":"2026-08-13T16:46:16Z","links":{"resolver":"https://pith.science/pith/W65SF6X2Z55UAJ2TXLW5QPZYVM","bundle":"https://pith.science/pith/W65SF6X2Z55UAJ2TXLW5QPZYVM/bundle.json","state":"https://pith.science/pith/W65SF6X2Z55UAJ2TXLW5QPZYVM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W65SF6X2Z55UAJ2TXLW5QPZYVM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W65SF6X2Z55UAJ2TXLW5QPZYVM","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":"f2fd849f44041c4c90dc9a3b7875a83f32c415d9289dfca1dad56b05e4fc7621","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-10-17T21:37:08Z","title_canon_sha256":"68d1c577fb96e7df0dcfb27e84bf15d929ec6240731a249ff67f0c6f86557492"},"schema_version":"1.0","source":{"id":"2410.14044","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14044","created_at":"2026-07-05T09:22:26Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14044v1","created_at":"2026-07-05T09:22:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14044","created_at":"2026-07-05T09:22:26Z"},{"alias_kind":"pith_short_12","alias_value":"W65SF6X2Z55U","created_at":"2026-07-05T09:22:26Z"},{"alias_kind":"pith_short_16","alias_value":"W65SF6X2Z55UAJ2T","created_at":"2026-07-05T09:22:26Z"},{"alias_kind":"pith_short_8","alias_value":"W65SF6X2","created_at":"2026-07-05T09:22:26Z"}],"graph_snapshots":[{"event_id":"sha256:9d2d279caed1873f1d48f2d55ee3fe7f47faceef3766a642f9ef29730715e3c2","target":"graph","created_at":"2026-07-05T09:22:26Z","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/2410.14044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional evaluation of information retrieval (IR) systems relies on human-annotated relevance labels, which can be both biased and costly at scale. In this context, large language models (LLMs) offer an alternative by allowing us to directly prompt them to assign relevance labels for passages associated with each query. In this study, we explore alternative methods to directly prompt LLMs for assigned relevance labels, by exploring two hypotheses:\n  Hypothesis 1 assumes that it is helpful to break down \"relevance\" into specific criteria - exactness, coverage, topicality, and contextual fit.","authors_text":"Laura Dietz, Naghmeh Farzi","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-10-17T21:37:08Z","title":"Best in Tau@LLMJudge: Criteria-Based Relevance Evaluation with Llama3"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14044","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:ba5212cb24503979f517594a2babcb92962397e223060db6046fbe62aef46d52","target":"record","created_at":"2026-07-05T09:22:26Z","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":"f2fd849f44041c4c90dc9a3b7875a83f32c415d9289dfca1dad56b05e4fc7621","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-10-17T21:37:08Z","title_canon_sha256":"68d1c577fb96e7df0dcfb27e84bf15d929ec6240731a249ff67f0c6f86557492"},"schema_version":"1.0","source":{"id":"2410.14044","kind":"arxiv","version":1}},"canonical_sha256":"b7bb22fafacf7b402753baedd83f38ab18426fd5e90ffdb165250358b44a5181","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7bb22fafacf7b402753baedd83f38ab18426fd5e90ffdb165250358b44a5181","first_computed_at":"2026-07-05T09:22:26.331391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:26.331391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QQ/6/1yJxgEVLTUbHIwaIdJMagQpVIcdatuFJr5qUJKhrqgVqs5Vw6EYsuSMrLTLOnsQFlyB7ZSg2uScOEqVAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:26.331801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.14044","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba5212cb24503979f517594a2babcb92962397e223060db6046fbe62aef46d52","sha256:9d2d279caed1873f1d48f2d55ee3fe7f47faceef3766a642f9ef29730715e3c2"],"state_sha256":"f47055268c53eb90fdbc1292c0b7fa6c348e38ea7d341cbdbfb5499625b05a70"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+nRKvDR6+wEC4wRVhqLGpYqB7kgxh/uQUNrOLfbu5/zti01dGCB+QvbLEAJs+rxDTxtabIumIry24OHrHKK/Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T16:46:16.528882Z","bundle_sha256":"b8d1a7e48cd7e40ae77469496e58cee29462fb73a63eb9b07d3cf1481ccaa6d6"}}