{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NZAABDPB6Y4E7IUMXJIFU5UYLJ","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":"9a554c7b894dc4dcf82e31c96b5f36d658620c811829f3f8890fba286366a7a5","cross_cats_sorted":["cs.AI","cs.LG","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T23:59:23Z","title_canon_sha256":"f0ae926ea0e84c745482a9cd7a7839b790c58c8d3ff7ec81316b8882a9ff0e81"},"schema_version":"1.0","source":{"id":"2501.08496","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08496","created_at":"2026-07-05T11:31:04Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08496v3","created_at":"2026-07-05T11:31:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08496","created_at":"2026-07-05T11:31:04Z"},{"alias_kind":"pith_short_12","alias_value":"NZAABDPB6Y4E","created_at":"2026-07-05T11:31:04Z"},{"alias_kind":"pith_short_16","alias_value":"NZAABDPB6Y4E7IUM","created_at":"2026-07-05T11:31:04Z"},{"alias_kind":"pith_short_8","alias_value":"NZAABDPB","created_at":"2026-07-05T11:31:04Z"}],"graph_snapshots":[{"event_id":"sha256:d27248737eeb663fd63cb053816c817c348e62c5847225a9d543961e3b39105d","target":"graph","created_at":"2026-07-05T11:31:04Z","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/2501.08496/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrary to the conventional emphasis on dataset size, we explore the role of data alignment -- an often overlooked aspect of data quality -- in training capable Large Language Models (LLMs). To do so, we use the Task2Vec-based alignment coefficient, a quantitative measure of the similarity between two datasets, to quantify the impact of alignment between training data and evaluation data on downstream performance. In particular, we conduct controlled \\textit{interventional} experiments for two settings: 1. the impact of increased alignment coefficients between various pre-training (pt) agains","authors_text":"Aryan Sahai, Brando Miranda, Elyas Obbad, Krrish Chawla, Mario DePavia, Sanmi Koyejo, Sudharsan Sundar","cross_cats":["cs.AI","cs.LG","cs.PL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T23:59:23Z","title":"Quantifying the Importance of Data Alignment in Downstream Model Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08496","kind":"arxiv","version":3},"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":"sha256:72af0d83313a7506b50c63346606a2180a6eee9f3ffda44c6da6ab84bd810d7c","target":"record","created_at":"2026-07-05T11:31:04Z","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":"9a554c7b894dc4dcf82e31c96b5f36d658620c811829f3f8890fba286366a7a5","cross_cats_sorted":["cs.AI","cs.LG","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T23:59:23Z","title_canon_sha256":"f0ae926ea0e84c745482a9cd7a7839b790c58c8d3ff7ec81316b8882a9ff0e81"},"schema_version":"1.0","source":{"id":"2501.08496","kind":"arxiv","version":3}},"canonical_sha256":"6e40008de1f6384fa28cba505a76985a55102b51aae81fe956664a82d1e45dc2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e40008de1f6384fa28cba505a76985a55102b51aae81fe956664a82d1e45dc2","first_computed_at":"2026-07-05T11:31:04.328695Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:04.328695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SBDTYYQ+llCHTAf4YSps2RL2ZFQcSZaO885LwMAgp0vhcI6lLj0SdXIOci/h6Udbr8fSIHyb6FQnSXAYIF+LDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:04.329222Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.08496","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72af0d83313a7506b50c63346606a2180a6eee9f3ffda44c6da6ab84bd810d7c","sha256:d27248737eeb663fd63cb053816c817c348e62c5847225a9d543961e3b39105d"],"state_sha256":"9d7b7db4d13916cd527ea506e63cba8537bfff9726a8fce81279570d59ed69ac"}