{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GPDP7VEYGGHKLNWOU6CRVUP22S","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":"7f453f96e03703b277274f9447e5d7f42b21c4048ba305525030ff9adc0cc61c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T17:58:19Z","title_canon_sha256":"cf97b1de6a8c57600894242db7fef59fae3d07eb8722b11ca38d1d62ab9fd9df"},"schema_version":"1.0","source":{"id":"2503.07603","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07603","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07603v1","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07603","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"pith_short_12","alias_value":"GPDP7VEYGGHK","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"pith_short_16","alias_value":"GPDP7VEYGGHKLNWO","created_at":"2026-07-05T10:28:07Z"},{"alias_kind":"pith_short_8","alias_value":"GPDP7VEY","created_at":"2026-07-05T10:28:07Z"}],"graph_snapshots":[{"event_id":"sha256:2ccee69609e68af4b2d4eb77dd65dfc36a33b4e484121875467d9ba21a1f55aa","target":"graph","created_at":"2026-07-05T10:28:07Z","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/2503.07603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained LLMs that are further trained with image data perform well on vision-language tasks. While adding images during a second training phase effectively unlocks this capability, it is unclear how much of a gain or loss this two-step pipeline gives over VLMs which integrate images earlier into the training process. To investigate this, we train models spanning various datasets, scales, image-text ratios, and amount of pre-training done before introducing vision tokens. We then fine-tune these models and evaluate their downstream performance on a suite of vision-language and text-only tas","authors_text":"Achal Dave, Benjamin Burchfiel, Igor Vasiljevic, Jean Mercat, Kushal Arora, Ludwig Schmidt, Russ Tedrake, Samir Yitzhak Gadre, Sedrick Keh, Shuran Song, Thomas Kollar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T17:58:19Z","title":"Should VLMs be Pre-trained with Image Data?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07603","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":"sha256:0a28f8d7fa406d40845bec6e9b608e6e88aec325a4e6facebe27f500c5768f5b","target":"record","created_at":"2026-07-05T10:28:07Z","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":"7f453f96e03703b277274f9447e5d7f42b21c4048ba305525030ff9adc0cc61c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T17:58:19Z","title_canon_sha256":"cf97b1de6a8c57600894242db7fef59fae3d07eb8722b11ca38d1d62ab9fd9df"},"schema_version":"1.0","source":{"id":"2503.07603","kind":"arxiv","version":1}},"canonical_sha256":"33c6ffd498318ea5b6cea7851ad1fad4831e8bbe06e343e179bba4be984107cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33c6ffd498318ea5b6cea7851ad1fad4831e8bbe06e343e179bba4be984107cf","first_computed_at":"2026-07-05T10:28:07.931860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:07.931860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BE6xxmhME84micYHGrb02/p3UzgpBA15Y/ogZpEpw6alVjGNPG4WkKxC0wK8rv/K9LOvpbHNT8D+eUYlPoVcBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:07.932860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.07603","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a28f8d7fa406d40845bec6e9b608e6e88aec325a4e6facebe27f500c5768f5b","sha256:2ccee69609e68af4b2d4eb77dd65dfc36a33b4e484121875467d9ba21a1f55aa"],"state_sha256":"559aa9e4ba3e013a76d74f03a14441a8a2def16aaea4b9fd086e782db83070fa"}