{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CRSWDVUOMGDWWBWE6PKU5V2CSW","short_pith_number":"pith:CRSWDVUO","canonical_record":{"source":{"id":"2605.16704","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T23:35:07Z","cross_cats_sorted":[],"title_canon_sha256":"4cbebfa04e299b24dce42dccaef6def82411b8ee09e7364998ebaaf768e81625","abstract_canon_sha256":"bb07a10933d5583a7d0b105db060289387572326f41cfdb7a47490b0a4d5aa94"},"schema_version":"1.0"},"canonical_sha256":"146561d68e61876b06c4f3d54ed74295868ce1013c9eb9a935746ed0789dc65d","source":{"kind":"arxiv","id":"2605.16704","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CRSWDVUOMGDWWBWE6PKU5V2CSW","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16704","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T23:35:07Z","cross_cats_sorted":[],"title_canon_sha256":"4cbebfa04e299b24dce42dccaef6def82411b8ee09e7364998ebaaf768e81625","abstract_canon_sha256":"bb07a10933d5583a7d0b105db060289387572326f41cfdb7a47490b0a4d5aa94"},"schema_version":"1.0"},"canonical_sha256":"146561d68e61876b06c4f3d54ed74295868ce1013c9eb9a935746ed0789dc65d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:37.429077Z","signature_b64":"xeOeJEHLjA5ElkTeKidQIQiz9VwpCIzxPkWdecGQvRH/OTYXh0GBWNmrGiyWZtx1tCvGDm1sigHp52RzsMQeBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"146561d68e61876b06c4f3d54ed74295868ce1013c9eb9a935746ed0789dc65d","last_reissued_at":"2026-05-20T00:02:37.428310Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:37.428310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16704","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":"2026-05-20T00:02:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R1HRexk5wL76ojk3nVH4cdsGjU56q0VBCQL9gPX77eCVnzxbOseW/KpedtCfyFjDdPX1tnVeFJRvouZQqzypAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T06:50:30.145776Z"},"content_sha256":"35a175b19b5cd9093b05f3b309724da72418452b2ae2152813c4a14f3d886a4f","schema_version":"1.0","event_id":"sha256:35a175b19b5cd9093b05f3b309724da72418452b2ae2152813c4a14f3d886a4f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CRSWDVUOMGDWWBWE6PKU5V2CSW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convex Dataset Valuation for Post-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christopher Jung, Fuchun Peng, Han Zhao, Ming Li, Nima Noorshams, Rui Li, Siqi Zeng, Xue Feng, Zhe Kang, Zhigang Wang","submitted_at":"2026-05-15T23:35:07Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16704","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/2605.16704/integrity.json","findings":[],"available":true,"detectors_run":[{"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","findings_count":0}],"snapshot_sha256":"3cc73d7486932bebf6c331c0bf1b311d5e04c417a6f779deec663f2cd6f48fb1"},"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":"2026-05-20T00:02:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IQdPinx5FpoUUZ9XF3CrrUYetYmdwbGRD5e1rq9JtMvFGbO4wm62xx0KLYW4Wj07OSIxGe7N1Qlut8uAYgtYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T06:50:30.146599Z"},"content_sha256":"caaaf9220feda839dcbafca20ae3b97241b9778081aa32965e1fc1a4650d38df","schema_version":"1.0","event_id":"sha256:caaaf9220feda839dcbafca20ae3b97241b9778081aa32965e1fc1a4650d38df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CRSWDVUOMGDWWBWE6PKU5V2CSW/bundle.json","state_url":"https://pith.science/pith/CRSWDVUOMGDWWBWE6PKU5V2CSW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CRSWDVUOMGDWWBWE6PKU5V2CSW/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":"2026-05-23T06:50:30Z","links":{"resolver":"https://pith.science/pith/CRSWDVUOMGDWWBWE6PKU5V2CSW","bundle":"https://pith.science/pith/CRSWDVUOMGDWWBWE6PKU5V2CSW/bundle.json","state":"https://pith.science/pith/CRSWDVUOMGDWWBWE6PKU5V2CSW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CRSWDVUOMGDWWBWE6PKU5V2CSW/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9PRM1c3j9hRK5LiEgRUSs01y9hS9oPQ7vixXm5y+Ll8/ogc3Q5zxv2T56L0ShPvxi4pWTfS+bEdJ5RnkKrH0Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T06:50:30.150275Z","bundle_sha256":"8aed6dfbd163cfe8555acfa160d76b072ed76a9a8fc8adf4dd154ba33485ff96"}}