{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QVCTTPUVZG5AE3KRA4FQWE6PHB","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":"a6a1071f055cb542af4df283acd76f98da44c33a91612754e74b1ef23274453c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T03:31:44Z","title_canon_sha256":"17df459e1cd9de46eb36bc9b65462d2e48b9aba141297d90ec1b3fbc56f81da0"},"schema_version":"1.0","source":{"id":"2607.22766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22766","created_at":"2026-07-28T00:21:53Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22766v1","created_at":"2026-07-28T00:21:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22766","created_at":"2026-07-28T00:21:53Z"},{"alias_kind":"pith_short_12","alias_value":"QVCTTPUVZG5A","created_at":"2026-07-28T00:21:53Z"},{"alias_kind":"pith_short_16","alias_value":"QVCTTPUVZG5AE3KR","created_at":"2026-07-28T00:21:53Z"},{"alias_kind":"pith_short_8","alias_value":"QVCTTPUV","created_at":"2026-07-28T00:21:53Z"}],"graph_snapshots":[{"event_id":"sha256:c8941a09b1dd3b40295205bb41af1447d381033c2efb95d8e939cc6d3e9585a1","target":"graph","created_at":"2026-07-28T00:21:53Z","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/2607.22766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The alignment of Large Language Models (LLMs) is increasingly bottlenecked by data quality. As datasets scale, massive preference and instruction-tuning corpora inevitably accumulate hidden structural contradictions, safety risks, and systemic human annotation errors. Standard dataset auditing methods, such as semantic deduplication or LLM-as-a-judge, struggle to capture the actual predictive impact of individual records and often miss deep functional rule clashes. To address this, we introduce a scalable, inference-only data valuation pipeline that approximates the Shapley value without itera","authors_text":"Jun Qin, Matthew Watson, Peter Grabowski, Yunting Song","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T03:31:44Z","title":"Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22766","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:b6995f7f7da1484954fa8394af9c18adf0b37af4bca0a8397a5fbd82e66a63ff","target":"record","created_at":"2026-07-28T00:21:53Z","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":"a6a1071f055cb542af4df283acd76f98da44c33a91612754e74b1ef23274453c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T03:31:44Z","title_canon_sha256":"17df459e1cd9de46eb36bc9b65462d2e48b9aba141297d90ec1b3fbc56f81da0"},"schema_version":"1.0","source":{"id":"2607.22766","kind":"arxiv","version":1}},"canonical_sha256":"854539be95c9ba026d51070b0b13cf3845db4b6d8936f37ca0003c21a4b3eb99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"854539be95c9ba026d51070b0b13cf3845db4b6d8936f37ca0003c21a4b3eb99","first_computed_at":"2026-07-28T00:21:53.346118Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T00:21:53.346118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KxL0p4/aYPwkUYhcyjC4wpvRqVy5J4ck+M+QcY+7HQqsqdGXwJpoY+6khYbQTmC2In/FDi0KSD9oI0XFMGqbCA==","signature_status":"signed_v1","signed_at":"2026-07-28T00:21:53.346969Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6995f7f7da1484954fa8394af9c18adf0b37af4bca0a8397a5fbd82e66a63ff","sha256:c8941a09b1dd3b40295205bb41af1447d381033c2efb95d8e939cc6d3e9585a1"],"state_sha256":"20110cb6a85bb8bb3e6b605d2e6558dd00a6a21bd3727f2ac903894df52ac64e"}