{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HJSZSVMQLUPEV4QL6TP22JT25Q","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":"66e5e4f767a4c107f73ffe0628bf46f5c01817650447ad91bee49b4fb0c60a59","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T14:10:08Z","title_canon_sha256":"5624d36a38b7d2cd021f9d1f85f569f0bb350faa4cb40fda28de617092aa61f2"},"schema_version":"1.0","source":{"id":"2310.16656","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16656","created_at":"2026-07-05T07:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16656v1","created_at":"2026-07-05T07:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16656","created_at":"2026-07-05T07:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"HJSZSVMQLUPE","created_at":"2026-07-05T07:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"HJSZSVMQLUPEV4QL","created_at":"2026-07-05T07:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"HJSZSVMQ","created_at":"2026-07-05T07:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:712bf9f19f5961b3cd32b0850597eeec0739e9c3ce73421cfc92105b3fee3717","target":"graph","created_at":"2026-07-05T07:05:00Z","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/2310.16656/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-image diffusion models achieved a remarkable leap in capabilities over the last few years, enabling high-quality and diverse synthesis of images from a textual prompt. However, even the most advanced models often struggle to precisely follow all of the directions in their prompts. The vast majority of these models are trained on datasets consisting of (image, caption) pairs where the images often come from the web, and the captions are their HTML alternate text. A notable example is the LAION dataset, used by Stable Diffusion and other models. In this work we observe that these caption","authors_text":"Dani Valevski, Danny Lumen, Eyal Segalis, Yaniv Leviathan, Yossi Matias","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T14:10:08Z","title":"A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16656","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":"sha256:00d46e28a0eea7afbb92c32424f8b6bc64af5c3f0eed2799031940bc9ce08575","target":"record","created_at":"2026-07-05T07:05:00Z","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":"66e5e4f767a4c107f73ffe0628bf46f5c01817650447ad91bee49b4fb0c60a59","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T14:10:08Z","title_canon_sha256":"5624d36a38b7d2cd021f9d1f85f569f0bb350faa4cb40fda28de617092aa61f2"},"schema_version":"1.0","source":{"id":"2310.16656","kind":"arxiv","version":1}},"canonical_sha256":"3a659955905d1e4af20bf4dfad267aec0ae699c0df32c03153aeaeb7be814bfd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a659955905d1e4af20bf4dfad267aec0ae699c0df32c03153aeaeb7be814bfd","first_computed_at":"2026-07-05T07:05:00.813659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:00.813659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WWg60POPKxm2syk6AcjSdyQK+/i9s771BUW/IimBd5zNubJG/Y9+D5VjHw0BR8u/HzA1cMGWUPSXGp8cOjnJAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:00.814132Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16656","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00d46e28a0eea7afbb92c32424f8b6bc64af5c3f0eed2799031940bc9ce08575","sha256:712bf9f19f5961b3cd32b0850597eeec0739e9c3ce73421cfc92105b3fee3717"],"state_sha256":"d5d8df6351dcd814112f9d594f7c466aaf80bf7cd93188a4eb565c619a6e6b10"}