{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EQOTML5SWCR3JLEFP6Y2I7MUYD","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":"15406706f337bd03f4256954ec12c224d60a8f584cc2b5b1faf2d411220bf2ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T17:57:28Z","title_canon_sha256":"aac4f553b05e0b271be3a431467290c205b447e2eab508a71ff3b73f5c5a2912"},"schema_version":"1.0","source":{"id":"2504.07951","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07951","created_at":"2026-07-05T11:51:25Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07951v4","created_at":"2026-07-05T11:51:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07951","created_at":"2026-07-05T11:51:25Z"},{"alias_kind":"pith_short_12","alias_value":"EQOTML5SWCR3","created_at":"2026-07-05T11:51:25Z"},{"alias_kind":"pith_short_16","alias_value":"EQOTML5SWCR3JLEF","created_at":"2026-07-05T11:51:25Z"},{"alias_kind":"pith_short_8","alias_value":"EQOTML5S","created_at":"2026-07-05T11:51:25Z"}],"graph_snapshots":[{"event_id":"sha256:5068333c54db6113c5ec24503a031d6088a36821d7c46228e99a645e3cb6d3c0","target":"graph","created_at":"2026-07-05T11:51:25Z","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/2504.07951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building general-purpose models that can effectively perceive the world through multimodal signals has been a long-standing goal. Current approaches involve integrating separately pre-trained components, such as connecting vision encoders to LLMs and continuing multimodal training. While such approaches exhibit remarkable sample efficiency, it remains an open question whether such late-fusion architectures are inherently superior. In this work, we revisit the architectural design of native multimodal models (NMMs)-those trained from the ground up on all modalities-and conduct an extensive scal","authors_text":"Alaaeldin El-Nouby, Enrico Fini, Joshua Susskind, Matthieu Cord, Mustafa Shukor, Victor Guilherme Turrisi da Costa","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T17:57:28Z","title":"Scaling Laws for Native Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07951","kind":"arxiv","version":4},"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:c66522f6897a924f5dfa1f0f1d36127fef563989d37aec739c8eeed13145f9c6","target":"record","created_at":"2026-07-05T11:51:25Z","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":"15406706f337bd03f4256954ec12c224d60a8f584cc2b5b1faf2d411220bf2ec","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-10T17:57:28Z","title_canon_sha256":"aac4f553b05e0b271be3a431467290c205b447e2eab508a71ff3b73f5c5a2912"},"schema_version":"1.0","source":{"id":"2504.07951","kind":"arxiv","version":4}},"canonical_sha256":"241d362fb2b0a3b4ac857fb1a47d94c0e2e0e9a0b80465c3960d090889f0c388","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"241d362fb2b0a3b4ac857fb1a47d94c0e2e0e9a0b80465c3960d090889f0c388","first_computed_at":"2026-07-05T11:51:25.283335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:25.283335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OXRMSDFBYdLak3hJLGHkEAl/TIvxZfpCcRiS8nxPNJC/olCXr0LXO6j/AuyYS9ACwJm9m7fGALuHhq28pNtbAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:25.283829Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07951","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c66522f6897a924f5dfa1f0f1d36127fef563989d37aec739c8eeed13145f9c6","sha256:5068333c54db6113c5ec24503a031d6088a36821d7c46228e99a645e3cb6d3c0"],"state_sha256":"819a89ef0cc7872ff158174721d721010c3320794f7c7e3ffc2b86f9b570540e"}