{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Y3I5GASDDOHPVB42J2GWXEYLZ6","short_pith_number":"pith:Y3I5GASD","canonical_record":{"source":{"id":"2601.10922","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-16T00:50:01Z","cross_cats_sorted":[],"title_canon_sha256":"84c558b80cf01ebd1349f448f3719096c00629f19f608515ec36a7177d673dc2","abstract_canon_sha256":"5555968e12d9c0155c393ace12244296c00bc64c557e327da0839c9dcba349f0"},"schema_version":"1.0"},"canonical_sha256":"c6d1d302431b8efa879a4e8d6b930bcf9ade248cec7e3b9c251dd1e0a31581f9","source":{"kind":"arxiv","id":"2601.10922","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.10922","created_at":"2026-07-21T00:19:54Z"},{"alias_kind":"arxiv_version","alias_value":"2601.10922v2","created_at":"2026-07-21T00:19:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.10922","created_at":"2026-07-21T00:19:54Z"},{"alias_kind":"pith_short_12","alias_value":"Y3I5GASDDOHP","created_at":"2026-07-21T00:19:54Z"},{"alias_kind":"pith_short_16","alias_value":"Y3I5GASDDOHPVB42","created_at":"2026-07-21T00:19:54Z"},{"alias_kind":"pith_short_8","alias_value":"Y3I5GASD","created_at":"2026-07-21T00:19:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Y3I5GASDDOHPVB42J2GWXEYLZ6","target":"record","payload":{"canonical_record":{"source":{"id":"2601.10922","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-16T00:50:01Z","cross_cats_sorted":[],"title_canon_sha256":"84c558b80cf01ebd1349f448f3719096c00629f19f608515ec36a7177d673dc2","abstract_canon_sha256":"5555968e12d9c0155c393ace12244296c00bc64c557e327da0839c9dcba349f0"},"schema_version":"1.0"},"canonical_sha256":"c6d1d302431b8efa879a4e8d6b930bcf9ade248cec7e3b9c251dd1e0a31581f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:19:54.774125Z","signature_b64":"+cEIgMN6dNouZmDu9cSJ3/nx0arpF/TaX+J+wc/jytST4duUlN/sAdV8jqIgFq6B5g4/oRj3pfiE1x1iLtnwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6d1d302431b8efa879a4e8d6b930bcf9ade248cec7e3b9c251dd1e0a31581f9","last_reissued_at":"2026-07-21T00:19:54.773082Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:19:54.773082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.10922","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-21T00:19:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g7/b5S0XXL59y4m9bO1tnUjlJ6yR4VzO18BZ6KfBUXCv2rz55YWcUiQPGkL7F7W/36oL8MA3gVogwd70Fr9UBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:36:22.949458Z"},"content_sha256":"b351d2eb9e324dac18ae4101cd017e576f9178d84dc962a85d28e752045ac5f8","schema_version":"1.0","event_id":"sha256:b351d2eb9e324dac18ae4101cd017e576f9178d84dc962a85d28e752045ac5f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Y3I5GASDDOHPVB42J2GWXEYLZ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data-Efficient Curation for Multimodal Reasoning under Fixed Training Protocols","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Boris Sobolev, Haoyang Xu, Igor Molybog, Michael Buriek, Pavel Bushuyeu, Samuel Watson, Vikas Kumar, Yosub Shin","submitted_at":"2026-01-16T00:50:01Z","abstract_excerpt":"We study data curation for multimodal reasoning in a fixed-protocol fine-tuning regime, where the base model, optimizer, training schedule, and evaluation pipeline are held constant and the main degree of freedom is the training data. Using the NeurIPS 2025 Data Curation for Vision--Language Reasoning (DCVLR) challenge as a controlled testbed, we analyze how source-dataset alignment, model-relative difficulty, dataset size, diversity heuristics, and rewritten synthetic mixtures affect downstream reasoning accuracy. Among the tested interventions, difficulty filtering on an aligned source corpu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.10922","kind":"arxiv","version":2},"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/2601.10922/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":"2026-07-21T00:19:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T9BLLC+iTHclGjigQTOsNWV6BKmIY55ZxO15l6JCKZ7GCBtdnhB0KBf9e2W7f+9ChXYSzvM7wZI6ICghK26OCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:36:22.949831Z"},"content_sha256":"637c866a4a6a123ef02dfd0c2f941c640fe95933ce98e8b8af80fe7856c6b489","schema_version":"1.0","event_id":"sha256:637c866a4a6a123ef02dfd0c2f941c640fe95933ce98e8b8af80fe7856c6b489"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y3I5GASDDOHPVB42J2GWXEYLZ6/bundle.json","state_url":"https://pith.science/pith/Y3I5GASDDOHPVB42J2GWXEYLZ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y3I5GASDDOHPVB42J2GWXEYLZ6/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":"2026-08-05T22:36:22Z","links":{"resolver":"https://pith.science/pith/Y3I5GASDDOHPVB42J2GWXEYLZ6","bundle":"https://pith.science/pith/Y3I5GASDDOHPVB42J2GWXEYLZ6/bundle.json","state":"https://pith.science/pith/Y3I5GASDDOHPVB42J2GWXEYLZ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y3I5GASDDOHPVB42J2GWXEYLZ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y3I5GASDDOHPVB42J2GWXEYLZ6","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":"5555968e12d9c0155c393ace12244296c00bc64c557e327da0839c9dcba349f0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-16T00:50:01Z","title_canon_sha256":"84c558b80cf01ebd1349f448f3719096c00629f19f608515ec36a7177d673dc2"},"schema_version":"1.0","source":{"id":"2601.10922","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.10922","created_at":"2026-07-21T00:19:54Z"},{"alias_kind":"arxiv_version","alias_value":"2601.10922v2","created_at":"2026-07-21T00:19:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.10922","created_at":"2026-07-21T00:19:54Z"},{"alias_kind":"pith_short_12","alias_value":"Y3I5GASDDOHP","created_at":"2026-07-21T00:19:54Z"},{"alias_kind":"pith_short_16","alias_value":"Y3I5GASDDOHPVB42","created_at":"2026-07-21T00:19:54Z"},{"alias_kind":"pith_short_8","alias_value":"Y3I5GASD","created_at":"2026-07-21T00:19:54Z"}],"graph_snapshots":[{"event_id":"sha256:637c866a4a6a123ef02dfd0c2f941c640fe95933ce98e8b8af80fe7856c6b489","target":"graph","created_at":"2026-07-21T00:19:54Z","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/2601.10922/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study data curation for multimodal reasoning in a fixed-protocol fine-tuning regime, where the base model, optimizer, training schedule, and evaluation pipeline are held constant and the main degree of freedom is the training data. Using the NeurIPS 2025 Data Curation for Vision--Language Reasoning (DCVLR) challenge as a controlled testbed, we analyze how source-dataset alignment, model-relative difficulty, dataset size, diversity heuristics, and rewritten synthetic mixtures affect downstream reasoning accuracy. Among the tested interventions, difficulty filtering on an aligned source corpu","authors_text":"Boris Sobolev, Haoyang Xu, Igor Molybog, Michael Buriek, Pavel Bushuyeu, Samuel Watson, Vikas Kumar, Yosub Shin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-16T00:50:01Z","title":"Data-Efficient Curation for Multimodal Reasoning under Fixed Training Protocols"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.10922","kind":"arxiv","version":2},"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:b351d2eb9e324dac18ae4101cd017e576f9178d84dc962a85d28e752045ac5f8","target":"record","created_at":"2026-07-21T00:19:54Z","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":"5555968e12d9c0155c393ace12244296c00bc64c557e327da0839c9dcba349f0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-16T00:50:01Z","title_canon_sha256":"84c558b80cf01ebd1349f448f3719096c00629f19f608515ec36a7177d673dc2"},"schema_version":"1.0","source":{"id":"2601.10922","kind":"arxiv","version":2}},"canonical_sha256":"c6d1d302431b8efa879a4e8d6b930bcf9ade248cec7e3b9c251dd1e0a31581f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6d1d302431b8efa879a4e8d6b930bcf9ade248cec7e3b9c251dd1e0a31581f9","first_computed_at":"2026-07-21T00:19:54.773082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T00:19:54.773082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+cEIgMN6dNouZmDu9cSJ3/nx0arpF/TaX+J+wc/jytST4duUlN/sAdV8jqIgFq6B5g4/oRj3pfiE1x1iLtnwDw==","signature_status":"signed_v1","signed_at":"2026-07-21T00:19:54.774125Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.10922","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b351d2eb9e324dac18ae4101cd017e576f9178d84dc962a85d28e752045ac5f8","sha256:637c866a4a6a123ef02dfd0c2f941c640fe95933ce98e8b8af80fe7856c6b489"],"state_sha256":"50ba8bb8143252cd507fc1b721eae8a5c6613ee8e9089a2d885121c09699437b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P7f9TsllDqug+wthrsTwaiGzd6cHdlESeBAbk8jxwG9H/td64LRUFea6WLsAJ6jvD1YNTts1XyMLNcxVsQR5DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:36:22.952859Z","bundle_sha256":"cab16ff5eed157127c4db32ca1339c9e5b68024513016e3a9cc5bf1e65053e0c"}}