{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:66ASLZTCZ5RXYHRH6LBBL36XXH","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":"af31b1c07bee10ad6f4aac82beb3e479ba9a4c9e990071f9a4f049ec3118acd3","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T17:59:56Z","title_canon_sha256":"2d04648c4c7ecdbb5cf3fe0152d60e9bea8ce8b2c8b9f018825c8fc641b48f10"},"schema_version":"1.0","source":{"id":"2506.01955","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01955","created_at":"2026-07-05T11:14:22Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01955v1","created_at":"2026-07-05T11:14:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01955","created_at":"2026-07-05T11:14:22Z"},{"alias_kind":"pith_short_12","alias_value":"66ASLZTCZ5RX","created_at":"2026-07-05T11:14:22Z"},{"alias_kind":"pith_short_16","alias_value":"66ASLZTCZ5RXYHRH","created_at":"2026-07-05T11:14:22Z"},{"alias_kind":"pith_short_8","alias_value":"66ASLZTC","created_at":"2026-07-05T11:14:22Z"}],"graph_snapshots":[{"event_id":"sha256:87b43c930036ea89d1b29942803e58545c7ca38da1dda119c67da287214d0cce","target":"graph","created_at":"2026-07-05T11:14:22Z","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/2506.01955/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prior methods for controlling image generation are limited in their ability to be taught new tasks. In contrast, vision-language models, or VLMs, can learn tasks in-context and produce the correct outputs for a given input. We propose a dual-process distillation scheme that allows feed-forward image generators to learn new tasks from deliberative VLMs. Our scheme uses a VLM to rate the generated images and backpropagates this gradient to update the weights of the image generator. Our general framework enables a wide variety of new control tasks through the same text-and-image based interface. ","authors_text":"Aleksander Holynski, Grace Luo, Jonathan Granskog, Trevor Darrell","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T17:59:56Z","title":"Dual-Process Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01955","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:c63ccdc06963b352009566b06cb347a24b85d73f82836a41a5b2d0d0acd4dce0","target":"record","created_at":"2026-07-05T11:14:22Z","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":"af31b1c07bee10ad6f4aac82beb3e479ba9a4c9e990071f9a4f049ec3118acd3","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T17:59:56Z","title_canon_sha256":"2d04648c4c7ecdbb5cf3fe0152d60e9bea8ce8b2c8b9f018825c8fc641b48f10"},"schema_version":"1.0","source":{"id":"2506.01955","kind":"arxiv","version":1}},"canonical_sha256":"f78125e662cf637c1e27f2c215efd7b9cd52d3a3f376758cdd1faf88fdbaafc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f78125e662cf637c1e27f2c215efd7b9cd52d3a3f376758cdd1faf88fdbaafc1","first_computed_at":"2026-07-05T11:14:22.076186Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:22.076186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RPoySKRSh7scDNHLecoufWAiKOwiNXU/etF7DI5MZBcM8RI0CPycA4MgQMx3oxzJ5HdyBmOP3hmlr2WavHFpCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:22.076612Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01955","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c63ccdc06963b352009566b06cb347a24b85d73f82836a41a5b2d0d0acd4dce0","sha256:87b43c930036ea89d1b29942803e58545c7ca38da1dda119c67da287214d0cce"],"state_sha256":"a4c19ded317703483a3d9f140692b880f8b28b59931ea66d9274b55b0eee6ea9"}