{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CRSWDVUOMGDWWBWE6PKU5V2CSW","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":"bb07a10933d5583a7d0b105db060289387572326f41cfdb7a47490b0a4d5aa94","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T23:35:07Z","title_canon_sha256":"4cbebfa04e299b24dce42dccaef6def82411b8ee09e7364998ebaaf768e81625"},"schema_version":"1.0","source":{"id":"2605.16704","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16704","created_at":"2026-05-20T00:02:37Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16704v1","created_at":"2026-05-20T00:02:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16704","created_at":"2026-05-20T00:02:37Z"},{"alias_kind":"pith_short_12","alias_value":"CRSWDVUOMGDW","created_at":"2026-05-20T00:02:37Z"},{"alias_kind":"pith_short_16","alias_value":"CRSWDVUOMGDWWBWE","created_at":"2026-05-20T00:02:37Z"},{"alias_kind":"pith_short_8","alias_value":"CRSWDVUO","created_at":"2026-05-20T00:02:37Z"}],"graph_snapshots":[{"event_id":"sha256:caaaf9220feda839dcbafca20ae3b97241b9778081aa32965e1fc1a4650d38df","target":"graph","created_at":"2026-05-20T00:02:37Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.364449Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.486460Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16704/integrity.json","findings":[],"snapshot_sha256":"3cc73d7486932bebf6c331c0bf1b311d5e04c417a6f779deec663f2cd6f48fb1","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Improving LLM performance on downstream tasks sometimes requires leveraging auxiliary datasets during post-training. In practice, however, developers face constraints on compute, labeling, and licensing costs that preclude using all available data, necessitating principled dataset-level selection. These constraints are increasingly shaped by dataset marketplaces, where data acquisition is governed by budgets and negotiation. We study dataset valuation as a subset selection problem during LLM post-training. Our goal is to identify and weight auxiliary datasets so as to maximize target task perf","authors_text":"Christopher Jung, Fuchun Peng, Han Zhao, Ming Li, Nima Noorshams, Rui Li, Siqi Zeng, Xue Feng, Zhe Kang, Zhigang Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T23:35:07Z","title":"Convex Dataset Valuation for Post-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16704","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":"sha256:35a175b19b5cd9093b05f3b309724da72418452b2ae2152813c4a14f3d886a4f","target":"record","created_at":"2026-05-20T00:02:37Z","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":"bb07a10933d5583a7d0b105db060289387572326f41cfdb7a47490b0a4d5aa94","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T23:35:07Z","title_canon_sha256":"4cbebfa04e299b24dce42dccaef6def82411b8ee09e7364998ebaaf768e81625"},"schema_version":"1.0","source":{"id":"2605.16704","kind":"arxiv","version":1}},"canonical_sha256":"146561d68e61876b06c4f3d54ed74295868ce1013c9eb9a935746ed0789dc65d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"146561d68e61876b06c4f3d54ed74295868ce1013c9eb9a935746ed0789dc65d","first_computed_at":"2026-05-20T00:02:37.428310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:37.428310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xeOeJEHLjA5ElkTeKidQIQiz9VwpCIzxPkWdecGQvRH/OTYXh0GBWNmrGiyWZtx1tCvGDm1sigHp52RzsMQeBA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:37.429077Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16704","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35a175b19b5cd9093b05f3b309724da72418452b2ae2152813c4a14f3d886a4f","sha256:caaaf9220feda839dcbafca20ae3b97241b9778081aa32965e1fc1a4650d38df"],"state_sha256":"a18fad8f08e05d2470dd849885b743f355c9728bbabc1c4745e0abfe5ffe18d2"}