{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KNFWZ5AHD6ZVXK2J5BYULFBU4W","short_pith_number":"pith:KNFWZ5AH","schema_version":"1.0","canonical_sha256":"534b6cf4071fb35bab49e871459434e5ab65b1ddd45a665f736083de4b1f2a13","source":{"kind":"arxiv","id":"2606.23915","version":1},"attestation_state":"computed","paper":{"title":"Do LLM Attribution Metrics Transfer? Auditing Retrieval-Augmented Generation Evaluation Across Datasets and Constructs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditya Nannapaneni, Juan Pablo De la Cruz Weinstein, Tianyu Ding","submitted_at":"2026-06-22T20:25:36Z","abstract_excerpt":"Practice often treats automatic metrics for attribution in LLM retrieval-augmented generation as interchangeable. We audit eight automatic scorers -- lexical, embedding, and BERTScore baselines alongside entailment/grounding-trained models (clean and FEVER NLI, the checker MiniCheck) -- across three evaluation constructs (provenance/topicality, generated-answer attribution, and fact-check entailment), asking whether any scorer transfers: stays within the 95% confidence interval of the best audited scorer on every dataset of a multi-dataset construct. In the construct with the most multi-datase"},"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":"2606.23915","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-22T20:25:36Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"68f7be124e45f9279899a2320fed1942226a1592285d75792da3114feaee118f","abstract_canon_sha256":"f33c7df9a8a017123cd86d1aed7c9775ae3b07b73f14c48633b3cc12d81cb9fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T00:14:30.073638Z","signature_b64":"RpCgI03rqhqpJ//NV1fXKxlF6GijaDnwc65R/sjIpIYGNXv9uIwc04rhPy2bzInb1As1iHV6CA+vLGgy6GruCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"534b6cf4071fb35bab49e871459434e5ab65b1ddd45a665f736083de4b1f2a13","last_reissued_at":"2026-06-24T00:14:30.073219Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T00:14:30.073219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do LLM Attribution Metrics Transfer? Auditing Retrieval-Augmented Generation Evaluation Across Datasets and Constructs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditya Nannapaneni, Juan Pablo De la Cruz Weinstein, Tianyu Ding","submitted_at":"2026-06-22T20:25:36Z","abstract_excerpt":"Practice often treats automatic metrics for attribution in LLM retrieval-augmented generation as interchangeable. We audit eight automatic scorers -- lexical, embedding, and BERTScore baselines alongside entailment/grounding-trained models (clean and FEVER NLI, the checker MiniCheck) -- across three evaluation constructs (provenance/topicality, generated-answer attribution, and fact-check entailment), asking whether any scorer transfers: stays within the 95% confidence interval of the best audited scorer on every dataset of a multi-dataset construct. In the construct with the most multi-datase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23915","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/2606.23915/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":"2606.23915","created_at":"2026-06-24T00:14:30.073283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23915v1","created_at":"2026-06-24T00:14:30.073283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23915","created_at":"2026-06-24T00:14:30.073283+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNFWZ5AHD6ZV","created_at":"2026-06-24T00:14:30.073283+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNFWZ5AHD6ZVXK2J","created_at":"2026-06-24T00:14:30.073283+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNFWZ5AH","created_at":"2026-06-24T00:14:30.073283+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KNFWZ5AHD6ZVXK2J5BYULFBU4W","json":"https://pith.science/pith/KNFWZ5AHD6ZVXK2J5BYULFBU4W.json","graph_json":"https://pith.science/api/pith-number/KNFWZ5AHD6ZVXK2J5BYULFBU4W/graph.json","events_json":"https://pith.science/api/pith-number/KNFWZ5AHD6ZVXK2J5BYULFBU4W/events.json","paper":"https://pith.science/paper/KNFWZ5AH"},"agent_actions":{"view_html":"https://pith.science/pith/KNFWZ5AHD6ZVXK2J5BYULFBU4W","download_json":"https://pith.science/pith/KNFWZ5AHD6ZVXK2J5BYULFBU4W.json","view_paper":"https://pith.science/paper/KNFWZ5AH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23915&json=true","fetch_graph":"https://pith.science/api/pith-number/KNFWZ5AHD6ZVXK2J5BYULFBU4W/graph.json","fetch_events":"https://pith.science/api/pith-number/KNFWZ5AHD6ZVXK2J5BYULFBU4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNFWZ5AHD6ZVXK2J5BYULFBU4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNFWZ5AHD6ZVXK2J5BYULFBU4W/action/storage_attestation","attest_author":"https://pith.science/pith/KNFWZ5AHD6ZVXK2J5BYULFBU4W/action/author_attestation","sign_citation":"https://pith.science/pith/KNFWZ5AHD6ZVXK2J5BYULFBU4W/action/citation_signature","submit_replication":"https://pith.science/pith/KNFWZ5AHD6ZVXK2J5BYULFBU4W/action/replication_record"}},"created_at":"2026-06-24T00:14:30.073283+00:00","updated_at":"2026-06-24T00:14:30.073283+00:00"}