{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JMFMACRYRWHZTMAAVBMP4GT44K","short_pith_number":"pith:JMFMACRY","canonical_record":{"source":{"id":"2405.02246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-03T17:00:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8536d4f5b642eecfa0533c9714f162a76f7d15640cfabf9504c059142b479d2a","abstract_canon_sha256":"875c63e21164f8796287b682c6a14d70baa67c2e0208a37378b83bcd75efdd18"},"schema_version":"1.0"},"canonical_sha256":"4b0ac00a388d8f99b000a858fe1a7ce28414943933cd7d2dba8323c97733eb1a","source":{"kind":"arxiv","id":"2405.02246","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02246","created_at":"2026-07-05T08:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02246v1","created_at":"2026-07-05T08:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02246","created_at":"2026-07-05T08:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"JMFMACRYRWHZ","created_at":"2026-07-05T08:15:08Z"},{"alias_kind":"pith_short_16","alias_value":"JMFMACRYRWHZTMAA","created_at":"2026-07-05T08:15:08Z"},{"alias_kind":"pith_short_8","alias_value":"JMFMACRY","created_at":"2026-07-05T08:15:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JMFMACRYRWHZTMAAVBMP4GT44K","target":"record","payload":{"canonical_record":{"source":{"id":"2405.02246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-03T17:00:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8536d4f5b642eecfa0533c9714f162a76f7d15640cfabf9504c059142b479d2a","abstract_canon_sha256":"875c63e21164f8796287b682c6a14d70baa67c2e0208a37378b83bcd75efdd18"},"schema_version":"1.0"},"canonical_sha256":"4b0ac00a388d8f99b000a858fe1a7ce28414943933cd7d2dba8323c97733eb1a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:08.818391Z","signature_b64":"oiSakkfhHpV1Ue2KC7Jf67LWrYqhDulI3BaljaahXYmtUB8YWTghch7xTcOOLmHEdNwY/o/xs7oyRPoMApZ2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b0ac00a388d8f99b000a858fe1a7ce28414943933cd7d2dba8323c97733eb1a","last_reissued_at":"2026-07-05T08:15:08.817931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:08.817931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.02246","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":"2026-07-05T08:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xwNkUDLocMFxDoNXOUMZFV1IjnYg8oVXVsZN54fJ+uvIbxfPsNC9Uz6NJK44Ia2G/C+24/cOlQVJl2Bgg4pJDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:04:08.680577Z"},"content_sha256":"ddc35305d3ae020b022d35423b852a0fc2b162405b495e873d2f7aae2a7e41a1","schema_version":"1.0","event_id":"sha256:ddc35305d3ae020b022d35423b852a0fc2b162405b495e873d2f7aae2a7e41a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JMFMACRYRWHZTMAAVBMP4GT44K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What matters when building vision-language models?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hugo Lauren\\c{c}on, L\\'eo Tronchon, Matthieu Cord, Victor Sanh","submitted_at":"2024-05-03T17:00:00Z","abstract_excerpt":"The growing interest in vision-language models (VLMs) has been driven by improvements in large language models and vision transformers. Despite the abundance of literature on this subject, we observe that critical decisions regarding the design of VLMs are often not justified. We argue that these unsupported decisions impede progress in the field by making it difficult to identify which choices improve model performance. To address this issue, we conduct extensive experiments around pre-trained models, architecture choice, data, and training methods. Our consolidation of findings includes the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02246","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/2405.02246/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":"2026-07-05T08:15:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aDEwq/5QLl9o0LXuZTl9YcZQrBR1L0n7axtLlYXxtdukMXHpVvmw5um3tVDZfAf768DuCYwuXWpCITuJle6+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:04:08.680962Z"},"content_sha256":"5941417e4f80db47a89b88b3131305d9740eb66b4340e3dd59be5647e145296b","schema_version":"1.0","event_id":"sha256:5941417e4f80db47a89b88b3131305d9740eb66b4340e3dd59be5647e145296b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JMFMACRYRWHZTMAAVBMP4GT44K/bundle.json","state_url":"https://pith.science/pith/JMFMACRYRWHZTMAAVBMP4GT44K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JMFMACRYRWHZTMAAVBMP4GT44K/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":"2026-07-09T02:04:08Z","links":{"resolver":"https://pith.science/pith/JMFMACRYRWHZTMAAVBMP4GT44K","bundle":"https://pith.science/pith/JMFMACRYRWHZTMAAVBMP4GT44K/bundle.json","state":"https://pith.science/pith/JMFMACRYRWHZTMAAVBMP4GT44K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JMFMACRYRWHZTMAAVBMP4GT44K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JMFMACRYRWHZTMAAVBMP4GT44K","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":"875c63e21164f8796287b682c6a14d70baa67c2e0208a37378b83bcd75efdd18","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-03T17:00:00Z","title_canon_sha256":"8536d4f5b642eecfa0533c9714f162a76f7d15640cfabf9504c059142b479d2a"},"schema_version":"1.0","source":{"id":"2405.02246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02246","created_at":"2026-07-05T08:15:08Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02246v1","created_at":"2026-07-05T08:15:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02246","created_at":"2026-07-05T08:15:08Z"},{"alias_kind":"pith_short_12","alias_value":"JMFMACRYRWHZ","created_at":"2026-07-05T08:15:08Z"},{"alias_kind":"pith_short_16","alias_value":"JMFMACRYRWHZTMAA","created_at":"2026-07-05T08:15:08Z"},{"alias_kind":"pith_short_8","alias_value":"JMFMACRY","created_at":"2026-07-05T08:15:08Z"}],"graph_snapshots":[{"event_id":"sha256:5941417e4f80db47a89b88b3131305d9740eb66b4340e3dd59be5647e145296b","target":"graph","created_at":"2026-07-05T08:15:08Z","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/2405.02246/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The growing interest in vision-language models (VLMs) has been driven by improvements in large language models and vision transformers. Despite the abundance of literature on this subject, we observe that critical decisions regarding the design of VLMs are often not justified. We argue that these unsupported decisions impede progress in the field by making it difficult to identify which choices improve model performance. To address this issue, we conduct extensive experiments around pre-trained models, architecture choice, data, and training methods. Our consolidation of findings includes the ","authors_text":"Hugo Lauren\\c{c}on, L\\'eo Tronchon, Matthieu Cord, Victor Sanh","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-03T17:00:00Z","title":"What matters when building vision-language models?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02246","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:ddc35305d3ae020b022d35423b852a0fc2b162405b495e873d2f7aae2a7e41a1","target":"record","created_at":"2026-07-05T08:15:08Z","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":"875c63e21164f8796287b682c6a14d70baa67c2e0208a37378b83bcd75efdd18","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-03T17:00:00Z","title_canon_sha256":"8536d4f5b642eecfa0533c9714f162a76f7d15640cfabf9504c059142b479d2a"},"schema_version":"1.0","source":{"id":"2405.02246","kind":"arxiv","version":1}},"canonical_sha256":"4b0ac00a388d8f99b000a858fe1a7ce28414943933cd7d2dba8323c97733eb1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b0ac00a388d8f99b000a858fe1a7ce28414943933cd7d2dba8323c97733eb1a","first_computed_at":"2026-07-05T08:15:08.817931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:15:08.817931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oiSakkfhHpV1Ue2KC7Jf67LWrYqhDulI3BaljaahXYmtUB8YWTghch7xTcOOLmHEdNwY/o/xs7oyRPoMApZ2Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:15:08.818391Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.02246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddc35305d3ae020b022d35423b852a0fc2b162405b495e873d2f7aae2a7e41a1","sha256:5941417e4f80db47a89b88b3131305d9740eb66b4340e3dd59be5647e145296b"],"state_sha256":"9075a73d8d62b4145ea8e5ddae3a3433dcf4883fd62867927034e8c090614d82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DYZ0K15sBjW3icDDgMLkySW9adY7MA/fNiyRYk6RFk+bLQxeZNbqwA0EFVjraJJV2OuDc1wSkTq3r0lR1L8KDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:04:08.683032Z","bundle_sha256":"bd1cd68f6a3ca8f2f15558f3def783f6ea9242caac86f77219a28c96cd38a85c"}}