{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4SF6SHTWVSTQ7ISYMPB25XFBS5","short_pith_number":"pith:4SF6SHTW","canonical_record":{"source":{"id":"2310.06311","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-10T05:09:05Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"bc65a25ff96a8ba33a536696f625853a34606aad57942b62acabf2f32ba57bb7","abstract_canon_sha256":"d80d53c83ca5d4edbaf224933205648cd628eb7425bad25eb58da9af68f46720"},"schema_version":"1.0"},"canonical_sha256":"e48be91e76aca70fa25863c3aedca1975b506028263336c7ea286448d3c6b26e","source":{"kind":"arxiv","id":"2310.06311","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06311","created_at":"2026-07-05T06:59:09Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06311v1","created_at":"2026-07-05T06:59:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06311","created_at":"2026-07-05T06:59:09Z"},{"alias_kind":"pith_short_12","alias_value":"4SF6SHTWVSTQ","created_at":"2026-07-05T06:59:09Z"},{"alias_kind":"pith_short_16","alias_value":"4SF6SHTWVSTQ7ISY","created_at":"2026-07-05T06:59:09Z"},{"alias_kind":"pith_short_8","alias_value":"4SF6SHTW","created_at":"2026-07-05T06:59:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4SF6SHTWVSTQ7ISYMPB25XFBS5","target":"record","payload":{"canonical_record":{"source":{"id":"2310.06311","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-10T05:09:05Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"bc65a25ff96a8ba33a536696f625853a34606aad57942b62acabf2f32ba57bb7","abstract_canon_sha256":"d80d53c83ca5d4edbaf224933205648cd628eb7425bad25eb58da9af68f46720"},"schema_version":"1.0"},"canonical_sha256":"e48be91e76aca70fa25863c3aedca1975b506028263336c7ea286448d3c6b26e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:09.140658Z","signature_b64":"pFopN6NnlRtSKzfVDnFmxMj06TL5HuEaKJWWzDye7vCasMe1Z7kRBIluOycIqZiAKwrjsrCf/ZEGj/POxZErBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e48be91e76aca70fa25863c3aedca1975b506028263336c7ea286448d3c6b26e","last_reissued_at":"2026-07-05T06:59:09.140172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:09.140172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.06311","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":"2026-07-05T06:59:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fvjDSfxMoRYIr5V36qcCLLA2bNa2RSqhjUAv5oMIMXgq3btcUZNnzcMHDc/5H40wBj2sWPDTcQBvj2To/lSgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T07:41:38.243865Z"},"content_sha256":"685a8681e3dabb78f0d61f7567f6905b151c8896e8525466f064f552ccab28a1","schema_version":"1.0","event_id":"sha256:685a8681e3dabb78f0d61f7567f6905b151c8896e8525466f064f552ccab28a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4SF6SHTWVSTQ7ISYMPB25XFBS5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Compositional Text-to-image Generation with Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Dimitris Metaxas, Guian Fang, Hao Dong, Peng Gao, Renrui Zhang, Song Wen","submitted_at":"2023-10-10T05:09:05Z","abstract_excerpt":"Recent advancements in text-to-image models, particularly diffusion models, have shown significant promise. However, compositional text-to-image models frequently encounter difficulties in generating high-quality images that accurately align with input texts describing multiple objects, variable attributes, and intricate spatial relationships. To address this limitation, we employ large vision-language models (LVLMs) for multi-dimensional assessment of the alignment between generated images and their corresponding input texts. Utilizing this assessment, we fine-tune the diffusion model to enha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06311","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/2310.06311/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":"2026-07-05T06:59:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8oBxv6iJ94pb/aJ0RVg8q/Y8VrDcQU2trNgtVNvQCfy6vcBkKCDrWGlHeMe9+oQfBkKioEDzOs1vGYiKo8nkDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T07:41:38.244227Z"},"content_sha256":"52c8a765361229bfc261c076dcb035f8c7cd1d813925da56c4299476cd60b3aa","schema_version":"1.0","event_id":"sha256:52c8a765361229bfc261c076dcb035f8c7cd1d813925da56c4299476cd60b3aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4SF6SHTWVSTQ7ISYMPB25XFBS5/bundle.json","state_url":"https://pith.science/pith/4SF6SHTWVSTQ7ISYMPB25XFBS5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4SF6SHTWVSTQ7ISYMPB25XFBS5/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":"2026-07-22T07:41:38Z","links":{"resolver":"https://pith.science/pith/4SF6SHTWVSTQ7ISYMPB25XFBS5","bundle":"https://pith.science/pith/4SF6SHTWVSTQ7ISYMPB25XFBS5/bundle.json","state":"https://pith.science/pith/4SF6SHTWVSTQ7ISYMPB25XFBS5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4SF6SHTWVSTQ7ISYMPB25XFBS5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4SF6SHTWVSTQ7ISYMPB25XFBS5","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":"d80d53c83ca5d4edbaf224933205648cd628eb7425bad25eb58da9af68f46720","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-10T05:09:05Z","title_canon_sha256":"bc65a25ff96a8ba33a536696f625853a34606aad57942b62acabf2f32ba57bb7"},"schema_version":"1.0","source":{"id":"2310.06311","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06311","created_at":"2026-07-05T06:59:09Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06311v1","created_at":"2026-07-05T06:59:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06311","created_at":"2026-07-05T06:59:09Z"},{"alias_kind":"pith_short_12","alias_value":"4SF6SHTWVSTQ","created_at":"2026-07-05T06:59:09Z"},{"alias_kind":"pith_short_16","alias_value":"4SF6SHTWVSTQ7ISY","created_at":"2026-07-05T06:59:09Z"},{"alias_kind":"pith_short_8","alias_value":"4SF6SHTW","created_at":"2026-07-05T06:59:09Z"}],"graph_snapshots":[{"event_id":"sha256:52c8a765361229bfc261c076dcb035f8c7cd1d813925da56c4299476cd60b3aa","target":"graph","created_at":"2026-07-05T06:59:09Z","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/2310.06311/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in text-to-image models, particularly diffusion models, have shown significant promise. However, compositional text-to-image models frequently encounter difficulties in generating high-quality images that accurately align with input texts describing multiple objects, variable attributes, and intricate spatial relationships. To address this limitation, we employ large vision-language models (LVLMs) for multi-dimensional assessment of the alignment between generated images and their corresponding input texts. Utilizing this assessment, we fine-tune the diffusion model to enha","authors_text":"Dimitris Metaxas, Guian Fang, Hao Dong, Peng Gao, Renrui Zhang, Song Wen","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-10T05:09:05Z","title":"Improving Compositional Text-to-image Generation with Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06311","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":"sha256:685a8681e3dabb78f0d61f7567f6905b151c8896e8525466f064f552ccab28a1","target":"record","created_at":"2026-07-05T06:59:09Z","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":"d80d53c83ca5d4edbaf224933205648cd628eb7425bad25eb58da9af68f46720","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-10T05:09:05Z","title_canon_sha256":"bc65a25ff96a8ba33a536696f625853a34606aad57942b62acabf2f32ba57bb7"},"schema_version":"1.0","source":{"id":"2310.06311","kind":"arxiv","version":1}},"canonical_sha256":"e48be91e76aca70fa25863c3aedca1975b506028263336c7ea286448d3c6b26e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e48be91e76aca70fa25863c3aedca1975b506028263336c7ea286448d3c6b26e","first_computed_at":"2026-07-05T06:59:09.140172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:09.140172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pFopN6NnlRtSKzfVDnFmxMj06TL5HuEaKJWWzDye7vCasMe1Z7kRBIluOycIqZiAKwrjsrCf/ZEGj/POxZErBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:09.140658Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.06311","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:685a8681e3dabb78f0d61f7567f6905b151c8896e8525466f064f552ccab28a1","sha256:52c8a765361229bfc261c076dcb035f8c7cd1d813925da56c4299476cd60b3aa"],"state_sha256":"c19195ced9378f92d3055e83ed71892cde50b3e2bd384ba40d9761b6397b06b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XVH0m9bOSs8ya8eo/S3TgUMJ6klhc2yYgZGp1oPKigZE4A8q4yzkUZmA8DFUNeQkm3C3jmNXVue2EE0Hu+IGBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T07:41:38.246693Z","bundle_sha256":"3c81b3dd4c2b43eb00a2fdc322bb149d622811d7bf971321fa419a0da115d385"}}