{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BMMMNBT3ULP3VBY35HVI3AIW3Z","short_pith_number":"pith:BMMMNBT3","canonical_record":{"source":{"id":"2507.05300","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T01:18:40Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"3d5d84ad7ebf855c8a9a125564657e23e9ba59348868a289c168c93eff33c6e6","abstract_canon_sha256":"2ac56503c832276ab2913a465932f4b5905f941b3e9b8168edb2fc7b84a78613"},"schema_version":"1.0"},"canonical_sha256":"0b18c6867ba2dfba871be9ea8d8116de472aae08e2657671787359c82a3155e5","source":{"kind":"arxiv","id":"2507.05300","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05300","created_at":"2026-07-05T11:33:27Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05300v1","created_at":"2026-07-05T11:33:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05300","created_at":"2026-07-05T11:33:27Z"},{"alias_kind":"pith_short_12","alias_value":"BMMMNBT3ULP3","created_at":"2026-07-05T11:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"BMMMNBT3ULP3VBY3","created_at":"2026-07-05T11:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"BMMMNBT3","created_at":"2026-07-05T11:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BMMMNBT3ULP3VBY35HVI3AIW3Z","target":"record","payload":{"canonical_record":{"source":{"id":"2507.05300","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T01:18:40Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"3d5d84ad7ebf855c8a9a125564657e23e9ba59348868a289c168c93eff33c6e6","abstract_canon_sha256":"2ac56503c832276ab2913a465932f4b5905f941b3e9b8168edb2fc7b84a78613"},"schema_version":"1.0"},"canonical_sha256":"0b18c6867ba2dfba871be9ea8d8116de472aae08e2657671787359c82a3155e5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:27.861673Z","signature_b64":"schB9DAYA8wQWSZ87ASliERRC3fOZ74We14mCqnrdc+8UnlWR9oO6YLfaP4tZwvq4iKpRHZ3B4NLlHLr79YdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b18c6867ba2dfba871be9ea8d8116de472aae08e2657671787359c82a3155e5","last_reissued_at":"2026-07-05T11:33:27.861254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:27.861254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.05300","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":"2026-07-05T11:33:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8z/mB9Epg3wXNO6zWSVQP/cTgOodFFM7bMR40zgLRiC+3O4JbbV/7DOAxZk+fpDoa4locBWBtnXi7S7Xd9HUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:08:40.089211Z"},"content_sha256":"d5e06ca8390e5ad6db497401c92543056c52528435ed93660ec70a17d3d8e35c","schema_version":"1.0","event_id":"sha256:d5e06ca8390e5ad6db497401c92543056c52528435ed93660ec70a17d3d8e35c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BMMMNBT3ULP3VBY35HVI3AIW3Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structured Captions Improve Prompt Adherence in Text-to-Image Models (Re-LAION-Caption 19M)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrei Cristian Popescu, Carlos Garcia Jurado Suarez, Haitz S\\'aez de Oc\\'ariz Borde, Nicholas Merchant","submitted_at":"2025-07-07T01:18:40Z","abstract_excerpt":"We argue that generative text-to-image models often struggle with prompt adherence due to the noisy and unstructured nature of large-scale datasets like LAION-5B. This forces users to rely heavily on prompt engineering to elicit desirable outputs. In this work, we propose that enforcing a consistent caption structure during training can significantly improve model controllability and alignment. We introduce Re-LAION-Caption 19M, a high-quality subset of Re-LAION-5B, comprising 19 million 1024x1024 images with captions generated by a Mistral 7B Instruct-based LLaVA-Next model. Each caption foll"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05300","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/2507.05300/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":"2026-07-05T11:33:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xa2t6iRyNoILWOYNAhR1SYH7dF+MFJga9jnNICFO7BOhF4xtTGYOalYS7wIRs/T6J8I/SZuw3NC2M0mvYVSRAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:08:40.089612Z"},"content_sha256":"143a2d721ea811ae417d6d87a0ec8ccbfda681c908ac2ca58676f259252a4a4e","schema_version":"1.0","event_id":"sha256:143a2d721ea811ae417d6d87a0ec8ccbfda681c908ac2ca58676f259252a4a4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BMMMNBT3ULP3VBY35HVI3AIW3Z/bundle.json","state_url":"https://pith.science/pith/BMMMNBT3ULP3VBY35HVI3AIW3Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BMMMNBT3ULP3VBY35HVI3AIW3Z/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":"2026-07-06T23:08:40Z","links":{"resolver":"https://pith.science/pith/BMMMNBT3ULP3VBY35HVI3AIW3Z","bundle":"https://pith.science/pith/BMMMNBT3ULP3VBY35HVI3AIW3Z/bundle.json","state":"https://pith.science/pith/BMMMNBT3ULP3VBY35HVI3AIW3Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BMMMNBT3ULP3VBY35HVI3AIW3Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BMMMNBT3ULP3VBY35HVI3AIW3Z","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":"2ac56503c832276ab2913a465932f4b5905f941b3e9b8168edb2fc7b84a78613","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T01:18:40Z","title_canon_sha256":"3d5d84ad7ebf855c8a9a125564657e23e9ba59348868a289c168c93eff33c6e6"},"schema_version":"1.0","source":{"id":"2507.05300","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05300","created_at":"2026-07-05T11:33:27Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05300v1","created_at":"2026-07-05T11:33:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05300","created_at":"2026-07-05T11:33:27Z"},{"alias_kind":"pith_short_12","alias_value":"BMMMNBT3ULP3","created_at":"2026-07-05T11:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"BMMMNBT3ULP3VBY3","created_at":"2026-07-05T11:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"BMMMNBT3","created_at":"2026-07-05T11:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:143a2d721ea811ae417d6d87a0ec8ccbfda681c908ac2ca58676f259252a4a4e","target":"graph","created_at":"2026-07-05T11:33:27Z","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/2507.05300/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We argue that generative text-to-image models often struggle with prompt adherence due to the noisy and unstructured nature of large-scale datasets like LAION-5B. This forces users to rely heavily on prompt engineering to elicit desirable outputs. In this work, we propose that enforcing a consistent caption structure during training can significantly improve model controllability and alignment. We introduce Re-LAION-Caption 19M, a high-quality subset of Re-LAION-5B, comprising 19 million 1024x1024 images with captions generated by a Mistral 7B Instruct-based LLaVA-Next model. Each caption foll","authors_text":"Andrei Cristian Popescu, Carlos Garcia Jurado Suarez, Haitz S\\'aez de Oc\\'ariz Borde, Nicholas Merchant","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T01:18:40Z","title":"Structured Captions Improve Prompt Adherence in Text-to-Image Models (Re-LAION-Caption 19M)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05300","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:d5e06ca8390e5ad6db497401c92543056c52528435ed93660ec70a17d3d8e35c","target":"record","created_at":"2026-07-05T11:33:27Z","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":"2ac56503c832276ab2913a465932f4b5905f941b3e9b8168edb2fc7b84a78613","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T01:18:40Z","title_canon_sha256":"3d5d84ad7ebf855c8a9a125564657e23e9ba59348868a289c168c93eff33c6e6"},"schema_version":"1.0","source":{"id":"2507.05300","kind":"arxiv","version":1}},"canonical_sha256":"0b18c6867ba2dfba871be9ea8d8116de472aae08e2657671787359c82a3155e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b18c6867ba2dfba871be9ea8d8116de472aae08e2657671787359c82a3155e5","first_computed_at":"2026-07-05T11:33:27.861254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:27.861254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"schB9DAYA8wQWSZ87ASliERRC3fOZ74We14mCqnrdc+8UnlWR9oO6YLfaP4tZwvq4iKpRHZ3B4NLlHLr79YdAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:27.861673Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05300","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5e06ca8390e5ad6db497401c92543056c52528435ed93660ec70a17d3d8e35c","sha256:143a2d721ea811ae417d6d87a0ec8ccbfda681c908ac2ca58676f259252a4a4e"],"state_sha256":"e0599057c505d0ea5cde4c1df8d21ee38a21dda14557422e3961bf1f9a76b912"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sg7/3OVrRg7yrgHAtw87vNYO1eATBDt3as0A9pL+l2ZreNJkMVGCvXViQYAZXjZfaxSLVyECefjKxyOkw834Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:08:40.091601Z","bundle_sha256":"01be90d76da0ed9affcd61c7b9e01d180a2d73f42edd9885d8d8ede037aa64c8"}}