{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OKHOUVWKD5QBKDLJB7UGJ5XOGN","short_pith_number":"pith:OKHOUVWK","canonical_record":{"source":{"id":"2607.24516","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T14:55:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"488c0f71adfdcdbf33e660f4d5d8c18495eaa90f09d3d145a53b0b49ac3e1d02","abstract_canon_sha256":"b6d82a22f7ace8381cd974673cb1d4e5c1461c2907d8f3700a91e0ec92c9beb5"},"schema_version":"1.0"},"canonical_sha256":"728eea56ca1f60150d690fe864f6ee335dad817b43af0ce2f7e8128571aca63a","source":{"kind":"arxiv","id":"2607.24516","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24516","created_at":"2026-07-28T02:24:07Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24516v1","created_at":"2026-07-28T02:24:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24516","created_at":"2026-07-28T02:24:07Z"},{"alias_kind":"pith_short_12","alias_value":"OKHOUVWKD5QB","created_at":"2026-07-28T02:24:07Z"},{"alias_kind":"pith_short_16","alias_value":"OKHOUVWKD5QBKDLJ","created_at":"2026-07-28T02:24:07Z"},{"alias_kind":"pith_short_8","alias_value":"OKHOUVWK","created_at":"2026-07-28T02:24:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OKHOUVWKD5QBKDLJB7UGJ5XOGN","target":"record","payload":{"canonical_record":{"source":{"id":"2607.24516","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T14:55:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"488c0f71adfdcdbf33e660f4d5d8c18495eaa90f09d3d145a53b0b49ac3e1d02","abstract_canon_sha256":"b6d82a22f7ace8381cd974673cb1d4e5c1461c2907d8f3700a91e0ec92c9beb5"},"schema_version":"1.0"},"canonical_sha256":"728eea56ca1f60150d690fe864f6ee335dad817b43af0ce2f7e8128571aca63a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:24:07.719663Z","signature_b64":"twyl+BxGE8DbexA+NrCRh0qP9fiX1iinisw8Cn9F1Np34RNHwE69gxDLUZKhuJIg1J5xbhaaqeQ3g5Pv9lC7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"728eea56ca1f60150d690fe864f6ee335dad817b43af0ce2f7e8128571aca63a","last_reissued_at":"2026-07-28T02:24:07.718811Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:24:07.718811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.24516","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":"2026-07-28T02:24:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ODjG8sY2Yh4M/TjyBGZE1lwdFDlS8MXm5OqmsC+DsP6OGzmiY7WkXR6ACJ07gPIIlXWI0DhZFMjQUFIcTd0XCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:45:10.754124Z"},"content_sha256":"412b2c1fe4f4508f69c137ab5ec23b1726f7366f4a34aac096d801c22779ae3c","schema_version":"1.0","event_id":"sha256:412b2c1fe4f4508f69c137ab5ec23b1726f7366f4a34aac096d801c22779ae3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OKHOUVWKD5QBKDLJB7UGJ5XOGN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DecoupleMix: Decoupled Ratio Search and Convex Allocation for Scalable VLM Data Recipes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cheng Yang, Dongling Xiao, Jiahao Xie, Qianle Wang, Ruiqi Lu, Wanxuan Sun, Zhongbin Guo","submitted_at":"2026-07-27T14:55:04Z","abstract_excerpt":"While data curation for Vision Language Models (VLMs) is increasingly active, public practice for constructing pretraining mixtures remains largely heuristic: practitioners stack datasets that pass quality filters, set cross-domain ratios by intuition, and lack a principled, attributable criterion for admitting new data, while frontier recipes remain undisclosed. We formulate data construction as a systematic mixture-optimization problem and turn it into a reproducible engineering discipline by decoupling the mixture into two orthogonal sub-problems: inter-class ratios across capabilities and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24516","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/2607.24516/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-28T02:24:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AsijFTM/LtHHF/ID2EXgfeWheyGgkaQkE88z/Zb6wWlWGVyueTjXYJzDpKIrmlg7gSahoWb+EDllSNtEY6P+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:45:10.754926Z"},"content_sha256":"5b2de95199cf89f09680cef29b9a4a2b60641a5700a5cfb7d8e9a15168773ec8","schema_version":"1.0","event_id":"sha256:5b2de95199cf89f09680cef29b9a4a2b60641a5700a5cfb7d8e9a15168773ec8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OKHOUVWKD5QBKDLJB7UGJ5XOGN/bundle.json","state_url":"https://pith.science/pith/OKHOUVWKD5QBKDLJB7UGJ5XOGN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OKHOUVWKD5QBKDLJB7UGJ5XOGN/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":"2026-08-04T07:45:10Z","links":{"resolver":"https://pith.science/pith/OKHOUVWKD5QBKDLJB7UGJ5XOGN","bundle":"https://pith.science/pith/OKHOUVWKD5QBKDLJB7UGJ5XOGN/bundle.json","state":"https://pith.science/pith/OKHOUVWKD5QBKDLJB7UGJ5XOGN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OKHOUVWKD5QBKDLJB7UGJ5XOGN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OKHOUVWKD5QBKDLJB7UGJ5XOGN","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":"b6d82a22f7ace8381cd974673cb1d4e5c1461c2907d8f3700a91e0ec92c9beb5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T14:55:04Z","title_canon_sha256":"488c0f71adfdcdbf33e660f4d5d8c18495eaa90f09d3d145a53b0b49ac3e1d02"},"schema_version":"1.0","source":{"id":"2607.24516","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24516","created_at":"2026-07-28T02:24:07Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24516v1","created_at":"2026-07-28T02:24:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24516","created_at":"2026-07-28T02:24:07Z"},{"alias_kind":"pith_short_12","alias_value":"OKHOUVWKD5QB","created_at":"2026-07-28T02:24:07Z"},{"alias_kind":"pith_short_16","alias_value":"OKHOUVWKD5QBKDLJ","created_at":"2026-07-28T02:24:07Z"},{"alias_kind":"pith_short_8","alias_value":"OKHOUVWK","created_at":"2026-07-28T02:24:07Z"}],"graph_snapshots":[{"event_id":"sha256:5b2de95199cf89f09680cef29b9a4a2b60641a5700a5cfb7d8e9a15168773ec8","target":"graph","created_at":"2026-07-28T02:24:07Z","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/2607.24516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While data curation for Vision Language Models (VLMs) is increasingly active, public practice for constructing pretraining mixtures remains largely heuristic: practitioners stack datasets that pass quality filters, set cross-domain ratios by intuition, and lack a principled, attributable criterion for admitting new data, while frontier recipes remain undisclosed. We formulate data construction as a systematic mixture-optimization problem and turn it into a reproducible engineering discipline by decoupling the mixture into two orthogonal sub-problems: inter-class ratios across capabilities and ","authors_text":"Cheng Yang, Dongling Xiao, Jiahao Xie, Qianle Wang, Ruiqi Lu, Wanxuan Sun, Zhongbin Guo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T14:55:04Z","title":"DecoupleMix: Decoupled Ratio Search and Convex Allocation for Scalable VLM Data Recipes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24516","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":"sha256:412b2c1fe4f4508f69c137ab5ec23b1726f7366f4a34aac096d801c22779ae3c","target":"record","created_at":"2026-07-28T02:24:07Z","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":"b6d82a22f7ace8381cd974673cb1d4e5c1461c2907d8f3700a91e0ec92c9beb5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T14:55:04Z","title_canon_sha256":"488c0f71adfdcdbf33e660f4d5d8c18495eaa90f09d3d145a53b0b49ac3e1d02"},"schema_version":"1.0","source":{"id":"2607.24516","kind":"arxiv","version":1}},"canonical_sha256":"728eea56ca1f60150d690fe864f6ee335dad817b43af0ce2f7e8128571aca63a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"728eea56ca1f60150d690fe864f6ee335dad817b43af0ce2f7e8128571aca63a","first_computed_at":"2026-07-28T02:24:07.718811Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T02:24:07.718811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"twyl+BxGE8DbexA+NrCRh0qP9fiX1iinisw8Cn9F1Np34RNHwE69gxDLUZKhuJIg1J5xbhaaqeQ3g5Pv9lC7Bw==","signature_status":"signed_v1","signed_at":"2026-07-28T02:24:07.719663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24516","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:412b2c1fe4f4508f69c137ab5ec23b1726f7366f4a34aac096d801c22779ae3c","sha256:5b2de95199cf89f09680cef29b9a4a2b60641a5700a5cfb7d8e9a15168773ec8"],"state_sha256":"9ab9a681a2e4cef33ca2c7d72879b041735785c2424aacbfccbcfd0936400269"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fc0hy4ffwRuuuUj5jkVFbOBvUxqJatbBtvOH+BChYu68VqEpLv7cby/FHLT3TzQ7pj74JLpuJzjtF7e62Z/gAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:45:10.852833Z","bundle_sha256":"0dab06ae89bae651e5656df1e2da5307d6a40941e925d15e0219f18564c180fa"}}