{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YWUGTIEFJ62VWLI727PKAIP37L","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":"5787449ce068ea270cfcc5b431f6d2e098643a3129cd26000ac0b09f99a822de","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T16:11:13Z","title_canon_sha256":"34eac346ada7192dd69bf21e40a6ebd3b9af523a49c9e09a6e4f507adc431947"},"schema_version":"1.0","source":{"id":"2607.06445","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06445","created_at":"2026-07-08T01:19:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06445v1","created_at":"2026-07-08T01:19:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06445","created_at":"2026-07-08T01:19:25Z"},{"alias_kind":"pith_short_12","alias_value":"YWUGTIEFJ62V","created_at":"2026-07-08T01:19:25Z"},{"alias_kind":"pith_short_16","alias_value":"YWUGTIEFJ62VWLI7","created_at":"2026-07-08T01:19:25Z"},{"alias_kind":"pith_short_8","alias_value":"YWUGTIEF","created_at":"2026-07-08T01:19:25Z"}],"graph_snapshots":[{"event_id":"sha256:c5660e1c608633a9ec121b71f19f4d11f0d7a97fa2c02a5d1556805c7061edf9","target":"graph","created_at":"2026-07-08T01:19:25Z","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/2607.06445/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) are increasingly utilized as the conditioning backbone for diffusion-based image editing due to their remarkable multimodal reasoning capabilities. While standalone VLMs demonstrate strong localization capabilities, editing pipelines frequently struggle to maintain this accuracy, particularly in complex, multi-entity scenes. In this work, we investigate this performance gap, hypothesizing that it stems from treating the VLM as a condition encoder. In this role, the model is restricted to a single forward pass, preventing the autoregressive generation process for w","authors_text":"Daniel Cohen-Or, Or Patashnik, Roni Paiss, Sara Dorfman, Yoav Baron","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T16:11:13Z","title":"Analysis-by-Proxy: Localization Signals in VLMs Operating as Condition Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06445","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":"sha256:55d762247a6d9676c54356ae0ffce8ceb6c6ff8242387ce893367c4cf312a3ce","target":"record","created_at":"2026-07-08T01:19:25Z","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":"5787449ce068ea270cfcc5b431f6d2e098643a3129cd26000ac0b09f99a822de","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T16:11:13Z","title_canon_sha256":"34eac346ada7192dd69bf21e40a6ebd3b9af523a49c9e09a6e4f507adc431947"},"schema_version":"1.0","source":{"id":"2607.06445","kind":"arxiv","version":1}},"canonical_sha256":"c5a869a0854fb55b2d1fd7dea021fbfadd08eec6d1359f5131b13caf40adb6e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5a869a0854fb55b2d1fd7dea021fbfadd08eec6d1359f5131b13caf40adb6e9","first_computed_at":"2026-07-08T01:19:25.470497Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:19:25.470497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZekTlpf0ijf0h5TTyPAlfFj86DE/xNI4TjvdPlAIi4+t0lOwwl2qIfSbyz2Hrql5fBwDgNdzKtQNIUJM8Tr5Dw==","signature_status":"signed_v1","signed_at":"2026-07-08T01:19:25.470907Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.06445","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55d762247a6d9676c54356ae0ffce8ceb6c6ff8242387ce893367c4cf312a3ce","sha256:c5660e1c608633a9ec121b71f19f4d11f0d7a97fa2c02a5d1556805c7061edf9"],"state_sha256":"d89996152ea3988002c6d13a27045e29bb5b6ba84905bd826775aca00a272013"}