{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EJZD36WTQ5WLHPN5Y4USJ5MYAY","short_pith_number":"pith:EJZD36WT","canonical_record":{"source":{"id":"2312.07533","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T18:58:18Z","cross_cats_sorted":[],"title_canon_sha256":"033e0857004416d965a0594f66e41e0e26b364d6b26afdb5410f100374e0e995","abstract_canon_sha256":"238c6b16de68d76b8e3654c311aca2dbd42b3449ff6933e4cfa34eee4cd511fb"},"schema_version":"1.0"},"canonical_sha256":"22723dfad3876cb3bdbdc72924f598063fe53b214f35564778b32c5067d7360d","source":{"kind":"arxiv","id":"2312.07533","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.07533","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"arxiv_version","alias_value":"2312.07533v4","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07533","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"pith_short_12","alias_value":"EJZD36WTQ5WL","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"pith_short_16","alias_value":"EJZD36WTQ5WLHPN5","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"pith_short_8","alias_value":"EJZD36WT","created_at":"2026-07-05T08:19:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EJZD36WTQ5WLHPN5Y4USJ5MYAY","target":"record","payload":{"canonical_record":{"source":{"id":"2312.07533","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T18:58:18Z","cross_cats_sorted":[],"title_canon_sha256":"033e0857004416d965a0594f66e41e0e26b364d6b26afdb5410f100374e0e995","abstract_canon_sha256":"238c6b16de68d76b8e3654c311aca2dbd42b3449ff6933e4cfa34eee4cd511fb"},"schema_version":"1.0"},"canonical_sha256":"22723dfad3876cb3bdbdc72924f598063fe53b214f35564778b32c5067d7360d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:57.883936Z","signature_b64":"Upjs9u33ZqkJieGTSZcGv5lUmgK71q57O2xaHr3t4YctfUMmMYdwhKTybA+i6+49O2p8d9ZK4sZSIJQ283aDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22723dfad3876cb3bdbdc72924f598063fe53b214f35564778b32c5067d7360d","last_reissued_at":"2026-07-05T08:19:57.883458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:57.883458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.07533","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:19:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RnUOg72BtoCYr7fIgVO9g1XLZeYpRG1w+1FYuZXfXWrU7y4M+5EDbckimTvhw3f8RcSYchDWd8PNYU9topIIDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:32:54.277044Z"},"content_sha256":"e7b84abe29b9f22a5f6889e46241744cd0162bcf72591e1b8c2ffd8f534577ff","schema_version":"1.0","event_id":"sha256:e7b84abe29b9f22a5f6889e46241744cd0162bcf72591e1b8c2ffd8f534577ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EJZD36WTQ5WLHPN5Y4USJ5MYAY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VILA: On Pre-training for Visual Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Tao, Hongxu Yin, Huizi Mao, Jan Kautz, Ji Lin, Mohammad Shoeybi, Pavlo Molchanov, Song Han, Wei Ping, Yao Lu","submitted_at":"2023-12-12T18:58:18Z","abstract_excerpt":"Visual language models (VLMs) rapidly progressed with the recent success of large language models. There have been growing efforts on visual instruction tuning to extend the LLM with visual inputs, but lacks an in-depth study of the visual language pre-training process, where the model learns to perform joint modeling on both modalities. In this work, we examine the design options for VLM pre-training by augmenting LLM towards VLM through step-by-step controllable comparisons. We introduce three main findings: (1) freezing LLMs during pre-training can achieve decent zero-shot performance, but "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07533","kind":"arxiv","version":4},"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/2312.07533/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":"2026-07-05T08:19:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dwSSi+sI60kNooC2jJ5UswucfBEVTBviBpw2XcwK9kUa3u9EQmwiHNk1gqCcHkKyZ8pdVwlR8ddg7cc9bfQVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:32:54.277549Z"},"content_sha256":"bcaf9ac063ed1d57ddfc70fc2aa5446f81f5e87646d0a162c3900c3705b2d6c6","schema_version":"1.0","event_id":"sha256:bcaf9ac063ed1d57ddfc70fc2aa5446f81f5e87646d0a162c3900c3705b2d6c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EJZD36WTQ5WLHPN5Y4USJ5MYAY/bundle.json","state_url":"https://pith.science/pith/EJZD36WTQ5WLHPN5Y4USJ5MYAY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EJZD36WTQ5WLHPN5Y4USJ5MYAY/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":"2026-08-06T03:32:54Z","links":{"resolver":"https://pith.science/pith/EJZD36WTQ5WLHPN5Y4USJ5MYAY","bundle":"https://pith.science/pith/EJZD36WTQ5WLHPN5Y4USJ5MYAY/bundle.json","state":"https://pith.science/pith/EJZD36WTQ5WLHPN5Y4USJ5MYAY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EJZD36WTQ5WLHPN5Y4USJ5MYAY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EJZD36WTQ5WLHPN5Y4USJ5MYAY","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":"238c6b16de68d76b8e3654c311aca2dbd42b3449ff6933e4cfa34eee4cd511fb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T18:58:18Z","title_canon_sha256":"033e0857004416d965a0594f66e41e0e26b364d6b26afdb5410f100374e0e995"},"schema_version":"1.0","source":{"id":"2312.07533","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.07533","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"arxiv_version","alias_value":"2312.07533v4","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07533","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"pith_short_12","alias_value":"EJZD36WTQ5WL","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"pith_short_16","alias_value":"EJZD36WTQ5WLHPN5","created_at":"2026-07-05T08:19:57Z"},{"alias_kind":"pith_short_8","alias_value":"EJZD36WT","created_at":"2026-07-05T08:19:57Z"}],"graph_snapshots":[{"event_id":"sha256:bcaf9ac063ed1d57ddfc70fc2aa5446f81f5e87646d0a162c3900c3705b2d6c6","target":"graph","created_at":"2026-07-05T08:19:57Z","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/2312.07533/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual language models (VLMs) rapidly progressed with the recent success of large language models. There have been growing efforts on visual instruction tuning to extend the LLM with visual inputs, but lacks an in-depth study of the visual language pre-training process, where the model learns to perform joint modeling on both modalities. In this work, we examine the design options for VLM pre-training by augmenting LLM towards VLM through step-by-step controllable comparisons. We introduce three main findings: (1) freezing LLMs during pre-training can achieve decent zero-shot performance, but ","authors_text":"Andrew Tao, Hongxu Yin, Huizi Mao, Jan Kautz, Ji Lin, Mohammad Shoeybi, Pavlo Molchanov, Song Han, Wei Ping, Yao Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T18:58:18Z","title":"VILA: On Pre-training for Visual Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07533","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:e7b84abe29b9f22a5f6889e46241744cd0162bcf72591e1b8c2ffd8f534577ff","target":"record","created_at":"2026-07-05T08:19:57Z","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":"238c6b16de68d76b8e3654c311aca2dbd42b3449ff6933e4cfa34eee4cd511fb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T18:58:18Z","title_canon_sha256":"033e0857004416d965a0594f66e41e0e26b364d6b26afdb5410f100374e0e995"},"schema_version":"1.0","source":{"id":"2312.07533","kind":"arxiv","version":4}},"canonical_sha256":"22723dfad3876cb3bdbdc72924f598063fe53b214f35564778b32c5067d7360d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22723dfad3876cb3bdbdc72924f598063fe53b214f35564778b32c5067d7360d","first_computed_at":"2026-07-05T08:19:57.883458Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:19:57.883458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Upjs9u33ZqkJieGTSZcGv5lUmgK71q57O2xaHr3t4YctfUMmMYdwhKTybA+i6+49O2p8d9ZK4sZSIJQ283aDDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:19:57.883936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.07533","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7b84abe29b9f22a5f6889e46241744cd0162bcf72591e1b8c2ffd8f534577ff","sha256:bcaf9ac063ed1d57ddfc70fc2aa5446f81f5e87646d0a162c3900c3705b2d6c6"],"state_sha256":"57f78a48ef7390571f35d67942a86044c3b2ddf201d4ebc675b0f8645713c50f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A1MQhPnk9RZjvQBQqM/AMmhRG3eqHtim82iG4PHlByE9YscLfhefrta4bCaHRIoXcUebA5clEVzW18uu/O++Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:32:54.282882Z","bundle_sha256":"f1228520f9b11b4efe98fd85725c0cd0a793f47a415c9f46d6d76fb9599aef06"}}