{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZHKUQMU7DFLI53HUDAKIHCBGFB","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":"08cb14b5f8ea08998c7403a9dbaefe4706af5e777544f9224a3b5110998b243d","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T01:47:40Z","title_canon_sha256":"b4b1eb0dd1fcf965b9c153c29548fa26a60f4d35b47271e1b857cb74c31f9552"},"schema_version":"1.0","source":{"id":"2412.10419","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10419","created_at":"2026-07-05T11:11:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10419v2","created_at":"2026-07-05T11:11:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10419","created_at":"2026-07-05T11:11:21Z"},{"alias_kind":"pith_short_12","alias_value":"ZHKUQMU7DFLI","created_at":"2026-07-05T11:11:21Z"},{"alias_kind":"pith_short_16","alias_value":"ZHKUQMU7DFLI53HU","created_at":"2026-07-05T11:11:21Z"},{"alias_kind":"pith_short_8","alias_value":"ZHKUQMU7","created_at":"2026-07-05T11:11:21Z"}],"graph_snapshots":[{"event_id":"sha256:ce0f5b0a6b0ff6b96b08757a8bce8c613e44c6169fd822df4e4e2b585dab8188","target":"graph","created_at":"2026-07-05T11:11:21Z","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/2412.10419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We address the problem of interactive text-to-image (T2I) generation, designing a reinforcement learning (RL) agent which iteratively improves a set of generated images for a user through a sequence of prompt expansions. Using human raters, we create a novel dataset of sequential preferences, which we leverage, together with large-scale open-source (non-sequential) datasets. We construct user-preference and user-choice models using an EM strategy and identify varying user preference types. We then leverage a large multimodal language model (LMM) and a value-based RL approach to suggest an adap","authors_text":"ChihWei Hsu, Craig Boutilier, Deepak Ramachandran, Guy Tennenholtz, Moonkyung Ryu, Ofir Nabati, Xiang Li, Yinlam Chow","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T01:47:40Z","title":"Preference Adaptive and Sequential Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10419","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":"sha256:490bb94b8bd3d11e19c142eea0814f94fb871c51176c2ebe1886b73c177a4e75","target":"record","created_at":"2026-07-05T11:11:21Z","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":"08cb14b5f8ea08998c7403a9dbaefe4706af5e777544f9224a3b5110998b243d","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T01:47:40Z","title_canon_sha256":"b4b1eb0dd1fcf965b9c153c29548fa26a60f4d35b47271e1b857cb74c31f9552"},"schema_version":"1.0","source":{"id":"2412.10419","kind":"arxiv","version":2}},"canonical_sha256":"c9d548329f19568eecf418148388262877372ee222a575827839c0466fb0e5d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9d548329f19568eecf418148388262877372ee222a575827839c0466fb0e5d8","first_computed_at":"2026-07-05T11:11:21.182904Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:21.182904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h4lCB8k0SFUP5oD/L+GHhQR8SLL+7VePeiHgmNGIq5/TpT6KD7KGNvivKEvEiCw3SRaVueHN+23pnW0TL1DABQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:21.183423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10419","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:490bb94b8bd3d11e19c142eea0814f94fb871c51176c2ebe1886b73c177a4e75","sha256:ce0f5b0a6b0ff6b96b08757a8bce8c613e44c6169fd822df4e4e2b585dab8188"],"state_sha256":"29e8adf893a75e6c2733d3a044c7ece64f92eecc18bc9b48cbaedc37adc6b3ef"}