{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:W57O62RG3ETKLQZN3RFMEXTMJX","short_pith_number":"pith:W57O62RG","canonical_record":{"source":{"id":"2608.05000","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T16:09:25Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"1a8291b49ebfe6b01a3010ae9d170b957421ee6d0b017c7ed8fdbd2db502dcf7","abstract_canon_sha256":"177fee1269536ccc240d5cc64a2374aa54731cef1645ac7bcc5d74c4a5c31232"},"schema_version":"1.0"},"canonical_sha256":"b77eef6a26d926a5c32ddc4ac25e6c4de4c1b7d551c8cd5e9197ee179e4dc460","source":{"kind":"arxiv","id":"2608.05000","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05000","created_at":"2026-08-06T01:48:01Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05000v1","created_at":"2026-08-06T01:48:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05000","created_at":"2026-08-06T01:48:01Z"},{"alias_kind":"pith_short_12","alias_value":"W57O62RG3ETK","created_at":"2026-08-06T01:48:01Z"},{"alias_kind":"pith_short_16","alias_value":"W57O62RG3ETKLQZN","created_at":"2026-08-06T01:48:01Z"},{"alias_kind":"pith_short_8","alias_value":"W57O62RG","created_at":"2026-08-06T01:48:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:W57O62RG3ETKLQZN3RFMEXTMJX","target":"record","payload":{"canonical_record":{"source":{"id":"2608.05000","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T16:09:25Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"1a8291b49ebfe6b01a3010ae9d170b957421ee6d0b017c7ed8fdbd2db502dcf7","abstract_canon_sha256":"177fee1269536ccc240d5cc64a2374aa54731cef1645ac7bcc5d74c4a5c31232"},"schema_version":"1.0"},"canonical_sha256":"b77eef6a26d926a5c32ddc4ac25e6c4de4c1b7d551c8cd5e9197ee179e4dc460","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:48:01.704197Z","signature_b64":"4iteRx5hl3X9qVaomchpOsoJc8R+r+qD90EzZi9J7QIRjVk7chT6sLyRubYcxFPc+pz9zG3+rjZ/giB+blqcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b77eef6a26d926a5c32ddc4ac25e6c4de4c1b7d551c8cd5e9197ee179e4dc460","last_reissued_at":"2026-08-06T01:48:01.702767Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:48:01.702767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.05000","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":"2026-08-06T01:48:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/QNFaAeMIlRIIiUT2ks7+4ub5+w/s7dc4ctCvFv7rYVeBzRY3f8q6ZAjk+9B4ESfaP9PRzlhSm3W0Dr7MhhsDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:30:30.164196Z"},"content_sha256":"66c7170f0de422336d8cd7bce2b43d6746b657d83becb48d80c548e48c4045ed","schema_version":"1.0","event_id":"sha256:66c7170f0de422336d8cd7bce2b43d6746b657d83becb48d80c548e48c4045ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:W57O62RG3ETKLQZN3RFMEXTMJX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"David Fan, Filippos Kokkinos, Junlin Han, Mike Lewis, Minghao Chen, Philip Torr, Shengbang Tong","submitted_at":"2026-08-05T16:09:25Z","abstract_excerpt":"Vision offers a critical axis for advancing foundation models, driving a shift towards natively unified multimodal pretraining. Despite this momentum, the design space and the fundamental mechanisms of how modalities interact during unified training remain underexplored. We provide empirical clarity through a systematic exploration of multimodal pretraining. Our controlled experiments on both synthetic and large-scale real-world datasets yield four key insights into the physics of multimodal pretraining: (i) Knowledge Flow: We disentangle how language, visual understanding, and visual generati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05000","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/2608.05000/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":"2026-08-06T01:48:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LyorZbz5IFhOXG73En2D0+d+J1XhH2ocpBxeeBWspB5DorB3As/CXwPhiQqGNOPU1XIaSJoz0DYq/GEs8l2TCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:30:30.164694Z"},"content_sha256":"3624404a39b14fba36e5ca2d75af04c7a1562d0ab5c5b6aa7cc0f7f354cbd19d","schema_version":"1.0","event_id":"sha256:3624404a39b14fba36e5ca2d75af04c7a1562d0ab5c5b6aa7cc0f7f354cbd19d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W57O62RG3ETKLQZN3RFMEXTMJX/bundle.json","state_url":"https://pith.science/pith/W57O62RG3ETKLQZN3RFMEXTMJX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W57O62RG3ETKLQZN3RFMEXTMJX/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":"2026-08-06T20:30:30Z","links":{"resolver":"https://pith.science/pith/W57O62RG3ETKLQZN3RFMEXTMJX","bundle":"https://pith.science/pith/W57O62RG3ETKLQZN3RFMEXTMJX/bundle.json","state":"https://pith.science/pith/W57O62RG3ETKLQZN3RFMEXTMJX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W57O62RG3ETKLQZN3RFMEXTMJX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:W57O62RG3ETKLQZN3RFMEXTMJX","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":"177fee1269536ccc240d5cc64a2374aa54731cef1645ac7bcc5d74c4a5c31232","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T16:09:25Z","title_canon_sha256":"1a8291b49ebfe6b01a3010ae9d170b957421ee6d0b017c7ed8fdbd2db502dcf7"},"schema_version":"1.0","source":{"id":"2608.05000","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05000","created_at":"2026-08-06T01:48:01Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05000v1","created_at":"2026-08-06T01:48:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05000","created_at":"2026-08-06T01:48:01Z"},{"alias_kind":"pith_short_12","alias_value":"W57O62RG3ETK","created_at":"2026-08-06T01:48:01Z"},{"alias_kind":"pith_short_16","alias_value":"W57O62RG3ETKLQZN","created_at":"2026-08-06T01:48:01Z"},{"alias_kind":"pith_short_8","alias_value":"W57O62RG","created_at":"2026-08-06T01:48:01Z"}],"graph_snapshots":[{"event_id":"sha256:3624404a39b14fba36e5ca2d75af04c7a1562d0ab5c5b6aa7cc0f7f354cbd19d","target":"graph","created_at":"2026-08-06T01:48:01Z","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/2608.05000/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision offers a critical axis for advancing foundation models, driving a shift towards natively unified multimodal pretraining. Despite this momentum, the design space and the fundamental mechanisms of how modalities interact during unified training remain underexplored. We provide empirical clarity through a systematic exploration of multimodal pretraining. Our controlled experiments on both synthetic and large-scale real-world datasets yield four key insights into the physics of multimodal pretraining: (i) Knowledge Flow: We disentangle how language, visual understanding, and visual generati","authors_text":"David Fan, Filippos Kokkinos, Junlin Han, Mike Lewis, Minghao Chen, Philip Torr, Shengbang Tong","cross_cats":["cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T16:09:25Z","title":"Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05000","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":"sha256:66c7170f0de422336d8cd7bce2b43d6746b657d83becb48d80c548e48c4045ed","target":"record","created_at":"2026-08-06T01:48:01Z","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":"177fee1269536ccc240d5cc64a2374aa54731cef1645ac7bcc5d74c4a5c31232","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T16:09:25Z","title_canon_sha256":"1a8291b49ebfe6b01a3010ae9d170b957421ee6d0b017c7ed8fdbd2db502dcf7"},"schema_version":"1.0","source":{"id":"2608.05000","kind":"arxiv","version":1}},"canonical_sha256":"b77eef6a26d926a5c32ddc4ac25e6c4de4c1b7d551c8cd5e9197ee179e4dc460","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b77eef6a26d926a5c32ddc4ac25e6c4de4c1b7d551c8cd5e9197ee179e4dc460","first_computed_at":"2026-08-06T01:48:01.702767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:48:01.702767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4iteRx5hl3X9qVaomchpOsoJc8R+r+qD90EzZi9J7QIRjVk7chT6sLyRubYcxFPc+pz9zG3+rjZ/giB+blqcBA==","signature_status":"signed_v1","signed_at":"2026-08-06T01:48:01.704197Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.05000","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66c7170f0de422336d8cd7bce2b43d6746b657d83becb48d80c548e48c4045ed","sha256:3624404a39b14fba36e5ca2d75af04c7a1562d0ab5c5b6aa7cc0f7f354cbd19d"],"state_sha256":"01eb6f6bf0f47e5446fb057085a3a9669c6b8551fbaed951c2c1132f12a9cc40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w4Dm/JAHmmKsQE59yicGOhn0CK/1lTaswo9E9lSAjcPV6YCMSwj/41/86OZvIM1Fu2RcJ0CctANKR9eNiukeBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T20:30:30.169312Z","bundle_sha256":"cfb34d61fbcb30eb9cd876354414c350e9740040f26621fd9cc525c1e94e5d90"}}