{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C3OCQSYFVWIWVAKXQVZGBGUEOE","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":"1c837b46fb0698c34922d4db571fd56675d4d54e266c4357c6f00e9ba2e477d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T17:59:04Z","title_canon_sha256":"26bd7b9ca5bf1883b1c9e5ecb70e46188d5e049dbe491c6c98394f7b9fb2f681"},"schema_version":"1.0","source":{"id":"2507.07104","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07104","created_at":"2026-07-05T11:35:15Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07104v2","created_at":"2026-07-05T11:35:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07104","created_at":"2026-07-05T11:35:15Z"},{"alias_kind":"pith_short_12","alias_value":"C3OCQSYFVWIW","created_at":"2026-07-05T11:35:15Z"},{"alias_kind":"pith_short_16","alias_value":"C3OCQSYFVWIWVAKX","created_at":"2026-07-05T11:35:15Z"},{"alias_kind":"pith_short_8","alias_value":"C3OCQSYF","created_at":"2026-07-05T11:35:15Z"}],"graph_snapshots":[{"event_id":"sha256:5fa3b98f93f816a7abf9a8bd7b6fdfd4025eed3c62b8704ce3e19fd5cb7c2dbc","target":"graph","created_at":"2026-07-05T11:35:15Z","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/2507.07104/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building state-of-the-art Vision-Language Models (VLMs) with strong captioning capabilities typically necessitates training on billions of high-quality image-text pairs, requiring millions of GPU hours. This paper introduces the Vision-Language-Vision (VLV) auto-encoder framework, which strategically leverages key pretrained components: a vision encoder, the decoder of a Text-to-Image (T2I) diffusion model, and subsequently, a Large Language Model (LLM). Specifically, we establish an information bottleneck by regularizing the language representation space, achieved through freezing the pretrai","authors_text":"Alan Yuille, Chen Wei, Jieneng Chen, Junfei Xiao, Tiezheng Zhang, Yitong Li, Yu-Cheng Chou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T17:59:04Z","title":"Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07104","kind":"arxiv","version":2},"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:bbd86283cede2047bc8e020749842098bcd39a2d7c69338ec36c67cebcf570fb","target":"record","created_at":"2026-07-05T11:35:15Z","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":"1c837b46fb0698c34922d4db571fd56675d4d54e266c4357c6f00e9ba2e477d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T17:59:04Z","title_canon_sha256":"26bd7b9ca5bf1883b1c9e5ecb70e46188d5e049dbe491c6c98394f7b9fb2f681"},"schema_version":"1.0","source":{"id":"2507.07104","kind":"arxiv","version":2}},"canonical_sha256":"16dc284b05ad916a81578572609a84712d9a3828e87bad8094dddf297738bb98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16dc284b05ad916a81578572609a84712d9a3828e87bad8094dddf297738bb98","first_computed_at":"2026-07-05T11:35:15.144079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:15.144079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JNEa5zcvGO+eAAKV/ZBjnF0ZdAnaaqlhbP4LpVyYd3qQd0Pzm1ZhXIh1aBPAdOaE6FUv+QEZU55i4jfzrWuhBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:15.144547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07104","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbd86283cede2047bc8e020749842098bcd39a2d7c69338ec36c67cebcf570fb","sha256:5fa3b98f93f816a7abf9a8bd7b6fdfd4025eed3c62b8704ce3e19fd5cb7c2dbc"],"state_sha256":"7c9552947ad0caefbcef2a900a833619df4c5f3ae2ad2e71bbba062e31524837"}