{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IAZWZ22GIRXUUU4PQDV367RXBU","short_pith_number":"pith:IAZWZ22G","canonical_record":{"source":{"id":"2311.17946","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T03:42:16Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"dfcf483dcece6e4a72edee760b130ea87b378a58b66d898b58d993da383d293c","abstract_canon_sha256":"32a82d656e9c07a2fa3b8acc68060649cc9b37d9e035e6833e041253b34f6cc4"},"schema_version":"1.0"},"canonical_sha256":"40336ceb46446f4a538f80ebbf7e370d38fbb0ba47b612b8e0c109f0071f1fb0","source":{"kind":"arxiv","id":"2311.17946","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17946","created_at":"2026-07-05T07:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17946v1","created_at":"2026-07-05T07:18:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17946","created_at":"2026-07-05T07:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"IAZWZ22GIRXU","created_at":"2026-07-05T07:18:33Z"},{"alias_kind":"pith_short_16","alias_value":"IAZWZ22GIRXUUU4P","created_at":"2026-07-05T07:18:33Z"},{"alias_kind":"pith_short_8","alias_value":"IAZWZ22G","created_at":"2026-07-05T07:18:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IAZWZ22GIRXUUU4PQDV367RXBU","target":"record","payload":{"canonical_record":{"source":{"id":"2311.17946","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T03:42:16Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"dfcf483dcece6e4a72edee760b130ea87b378a58b66d898b58d993da383d293c","abstract_canon_sha256":"32a82d656e9c07a2fa3b8acc68060649cc9b37d9e035e6833e041253b34f6cc4"},"schema_version":"1.0"},"canonical_sha256":"40336ceb46446f4a538f80ebbf7e370d38fbb0ba47b612b8e0c109f0071f1fb0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:33.964901Z","signature_b64":"k7HcU6c6TAMWdwIJyreeTFnqavktD2Pwy2aFFtrh9qv9SjXiJJk7Kijbxu6vkewZgkZtnSmjx8HuBo3eFIQ7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40336ceb46446f4a538f80ebbf7e370d38fbb0ba47b612b8e0c109f0071f1fb0","last_reissued_at":"2026-07-05T07:18:33.964370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:33.964370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.17946","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:18:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/qSkZy6iEpfdGQtzt0/zDGxxLIQ95v8hGBUxCymtjN1LwEcBtyoh6HC4S7R6RxvhFkr9dsPrWVYA9i+QUUicCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:22:22.050668Z"},"content_sha256":"dca1084cd8c39066f87b0ee6a8f86f0b7e5afc7be2ae7e0ebcd9c59e787aa758","schema_version":"1.0","event_id":"sha256:dca1084cd8c39066f87b0ee6a8f86f0b7e5afc7be2ae7e0ebcd9c59e787aa758"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IAZWZ22GIRXUUU4PQDV367RXBU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Charles Herrmann, Cyrus Rashtchian, Da-Cheng Juan, Dana Alon, Deqing Fu, Jiao Sun, Ranjay Krishna, Royi Rassin, Sjoerd van Steenkiste, Su Wang, Yushi Hu","submitted_at":"2023-11-29T03:42:16Z","abstract_excerpt":"Despite their wide-spread success, Text-to-Image models (T2I) still struggle to produce images that are both aesthetically pleasing and faithful to the user's input text. We introduce DreamSync, a model-agnostic training algorithm by design that improves T2I models to be faithful to the text input. DreamSync builds off a recent insight from TIFA's evaluation framework -- that large vision-language models (VLMs) can effectively identify the fine-grained discrepancies between generated images and the text inputs. DreamSync uses this insight to train T2I models without any labeled data; it improv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17946","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.17946/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:18:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tm9hUBZS7qj9FoLX9SGDPjDAmvalqKtcf9ZmnIDvqmWjPXUeemrcWYM6HzBeOAjWhZ17jyUHOI/gpiNYmUNhCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:22:22.051251Z"},"content_sha256":"c95628aa7a1ac54c5654d692e1947d3a4bcb44d5bc7248e0b4bdbd75c9c2ed19","schema_version":"1.0","event_id":"sha256:c95628aa7a1ac54c5654d692e1947d3a4bcb44d5bc7248e0b4bdbd75c9c2ed19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IAZWZ22GIRXUUU4PQDV367RXBU/bundle.json","state_url":"https://pith.science/pith/IAZWZ22GIRXUUU4PQDV367RXBU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IAZWZ22GIRXUUU4PQDV367RXBU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T21:22:22Z","links":{"resolver":"https://pith.science/pith/IAZWZ22GIRXUUU4PQDV367RXBU","bundle":"https://pith.science/pith/IAZWZ22GIRXUUU4PQDV367RXBU/bundle.json","state":"https://pith.science/pith/IAZWZ22GIRXUUU4PQDV367RXBU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IAZWZ22GIRXUUU4PQDV367RXBU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IAZWZ22GIRXUUU4PQDV367RXBU","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":"32a82d656e9c07a2fa3b8acc68060649cc9b37d9e035e6833e041253b34f6cc4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T03:42:16Z","title_canon_sha256":"dfcf483dcece6e4a72edee760b130ea87b378a58b66d898b58d993da383d293c"},"schema_version":"1.0","source":{"id":"2311.17946","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17946","created_at":"2026-07-05T07:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17946v1","created_at":"2026-07-05T07:18:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17946","created_at":"2026-07-05T07:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"IAZWZ22GIRXU","created_at":"2026-07-05T07:18:33Z"},{"alias_kind":"pith_short_16","alias_value":"IAZWZ22GIRXUUU4P","created_at":"2026-07-05T07:18:33Z"},{"alias_kind":"pith_short_8","alias_value":"IAZWZ22G","created_at":"2026-07-05T07:18:33Z"}],"graph_snapshots":[{"event_id":"sha256:c95628aa7a1ac54c5654d692e1947d3a4bcb44d5bc7248e0b4bdbd75c9c2ed19","target":"graph","created_at":"2026-07-05T07:18:33Z","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/2311.17946/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite their wide-spread success, Text-to-Image models (T2I) still struggle to produce images that are both aesthetically pleasing and faithful to the user's input text. We introduce DreamSync, a model-agnostic training algorithm by design that improves T2I models to be faithful to the text input. DreamSync builds off a recent insight from TIFA's evaluation framework -- that large vision-language models (VLMs) can effectively identify the fine-grained discrepancies between generated images and the text inputs. DreamSync uses this insight to train T2I models without any labeled data; it improv","authors_text":"Charles Herrmann, Cyrus Rashtchian, Da-Cheng Juan, Dana Alon, Deqing Fu, Jiao Sun, Ranjay Krishna, Royi Rassin, Sjoerd van Steenkiste, Su Wang, Yushi Hu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T03:42:16Z","title":"DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17946","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:dca1084cd8c39066f87b0ee6a8f86f0b7e5afc7be2ae7e0ebcd9c59e787aa758","target":"record","created_at":"2026-07-05T07:18:33Z","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":"32a82d656e9c07a2fa3b8acc68060649cc9b37d9e035e6833e041253b34f6cc4","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T03:42:16Z","title_canon_sha256":"dfcf483dcece6e4a72edee760b130ea87b378a58b66d898b58d993da383d293c"},"schema_version":"1.0","source":{"id":"2311.17946","kind":"arxiv","version":1}},"canonical_sha256":"40336ceb46446f4a538f80ebbf7e370d38fbb0ba47b612b8e0c109f0071f1fb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40336ceb46446f4a538f80ebbf7e370d38fbb0ba47b612b8e0c109f0071f1fb0","first_computed_at":"2026-07-05T07:18:33.964370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:18:33.964370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k7HcU6c6TAMWdwIJyreeTFnqavktD2Pwy2aFFtrh9qv9SjXiJJk7Kijbxu6vkewZgkZtnSmjx8HuBo3eFIQ7DA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:18:33.964901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.17946","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dca1084cd8c39066f87b0ee6a8f86f0b7e5afc7be2ae7e0ebcd9c59e787aa758","sha256:c95628aa7a1ac54c5654d692e1947d3a4bcb44d5bc7248e0b4bdbd75c9c2ed19"],"state_sha256":"0611d572461cb94cc033ed7550dbea7d6a1da1e3a83e67be1586348261412833"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9KkjabrnqGY6GQYRfvR46/RgUZUbNGtEBdtXT+74nZH0GhNLdybetxmyR/ekPKXAbdZLT63GgzfnaAWTUvBCAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T21:22:22.056051Z","bundle_sha256":"0f6cd16ad78656e0f7904bfbdc352525d9727343ce351373773da394170f0aae"}}