{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:74YGJ2KHKQUTENWUZF72RD5ZSI","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":"261fe2bc39a23413ac62081b9d25cf264c1c214074af14c8b195fd0559913a97","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T03:16:19Z","title_canon_sha256":"3dd24c5b1870c4e5a8b3eef206105eaf242db75e8e6ddc4b853c443422dcf2d3"},"schema_version":"1.0","source":{"id":"2606.07954","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07954","created_at":"2026-06-09T01:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07954v1","created_at":"2026-06-09T01:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07954","created_at":"2026-06-09T01:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"74YGJ2KHKQUT","created_at":"2026-06-09T01:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"74YGJ2KHKQUTENWU","created_at":"2026-06-09T01:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"74YGJ2KH","created_at":"2026-06-09T01:04:56Z"}],"graph_snapshots":[{"event_id":"sha256:71e0ae7e7e9e1b351d5ac1b14c14012a6c78db289b79c735a14a5a8fb914ddf8","target":"graph","created_at":"2026-06-09T01:04:56Z","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/2606.07954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training large language models (LLMs) on heterogeneous data requires selecting minibatches that balance convergence speed with coverage across domains. Existing methods either select samples independently within each domain or rely on computationally expensive proxy models to learn continuous domain weights. We propose PartitionSel, a cross-domain minibatch selection approach that maximizes a validation-guided gradient-matching utility under per-domain budgets encoded as a partition-matroid constraint. By coupling the per-domain budgets through a single utility, PartitionSel is designed to red","authors_text":"Bamdev Mishra, Ganesh Ramakrishnan, Ishita Khatri, Prateek Chanda, Pratik Jawanpuria, Prayas Agrawal","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T03:16:19Z","title":"Minibatch Selection via Partition Matroid Constrained Gradient Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07954","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":"sha256:8072b955ab7c55c21f7ef6502a35470b25c4ef495fd1f3356480b26ceb018984","target":"record","created_at":"2026-06-09T01:04:56Z","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":"261fe2bc39a23413ac62081b9d25cf264c1c214074af14c8b195fd0559913a97","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T03:16:19Z","title_canon_sha256":"3dd24c5b1870c4e5a8b3eef206105eaf242db75e8e6ddc4b853c443422dcf2d3"},"schema_version":"1.0","source":{"id":"2606.07954","kind":"arxiv","version":1}},"canonical_sha256":"ff3064e94754293236d4c97fa88fb992097fea4ec4678f9a9e5035988f7b888d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff3064e94754293236d4c97fa88fb992097fea4ec4678f9a9e5035988f7b888d","first_computed_at":"2026-06-09T01:04:56.347453Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:04:56.347453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1rU5lxAfnSuEftaNeUgPT3sDOH5yD9hM8X+s6BKK0VHU6/1zQhz3GMSMsmMe1t3dFBT4nyHNdAwN5oH9rHn4Dg==","signature_status":"signed_v1","signed_at":"2026-06-09T01:04:56.347857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07954","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8072b955ab7c55c21f7ef6502a35470b25c4ef495fd1f3356480b26ceb018984","sha256:71e0ae7e7e9e1b351d5ac1b14c14012a6c78db289b79c735a14a5a8fb914ddf8"],"state_sha256":"7b3af020a991b42f8a61b3e3d9f8568c303bdc5cf29a4297bd01e648e0e53202"}