{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NB7XOPQDTRF3TFYPG2UEGCM5PG","short_pith_number":"pith:NB7XOPQD","canonical_record":{"source":{"id":"2506.16679","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T01:52:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"45e40dd139471c1ae65482c12113baaa791f65115ccdbcf5c81f3afe7809af7e","abstract_canon_sha256":"9dcf489602c04484501111f57c6b69711b878e276e81c3224661352a48d0383c"},"schema_version":"1.0"},"canonical_sha256":"687f773e039c4bb9970f36a843099d79adaf2109e80c300aa4546fb4c236f985","source":{"kind":"arxiv","id":"2506.16679","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16679","created_at":"2026-07-05T11:24:40Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16679v1","created_at":"2026-07-05T11:24:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16679","created_at":"2026-07-05T11:24:40Z"},{"alias_kind":"pith_short_12","alias_value":"NB7XOPQDTRF3","created_at":"2026-07-05T11:24:40Z"},{"alias_kind":"pith_short_16","alias_value":"NB7XOPQDTRF3TFYP","created_at":"2026-07-05T11:24:40Z"},{"alias_kind":"pith_short_8","alias_value":"NB7XOPQD","created_at":"2026-07-05T11:24:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NB7XOPQDTRF3TFYPG2UEGCM5PG","target":"record","payload":{"canonical_record":{"source":{"id":"2506.16679","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T01:52:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"45e40dd139471c1ae65482c12113baaa791f65115ccdbcf5c81f3afe7809af7e","abstract_canon_sha256":"9dcf489602c04484501111f57c6b69711b878e276e81c3224661352a48d0383c"},"schema_version":"1.0"},"canonical_sha256":"687f773e039c4bb9970f36a843099d79adaf2109e80c300aa4546fb4c236f985","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:40.585971Z","signature_b64":"yrhbX1aiAk5lI1joOjNteALX22gJLOgRF/4BVhL8J3NK1OpTqGQsqrsxg8CHw1NP/m8UOFRpNLLX81l5uHJ0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"687f773e039c4bb9970f36a843099d79adaf2109e80c300aa4546fb4c236f985","last_reissued_at":"2026-07-05T11:24:40.585443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:40.585443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.16679","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":"2026-07-05T11:24:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XRznEzv2bDW6cA5f6fzNzyIahjI6c+ErkWx6HHlLrVQimSTnrLmQUAEfQHTIahnrls2Sz4QC/cxqfQ9S1v7BAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:36:07.933232Z"},"content_sha256":"311988fc76d7d631ed5f228a2165eabbcb38e3dac9aeb9222750598f77cf6ada","schema_version":"1.0","event_id":"sha256:311988fc76d7d631ed5f228a2165eabbcb38e3dac9aeb9222750598f77cf6ada"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NB7XOPQDTRF3TFYPG2UEGCM5PG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to Train your Text-to-Image Model: Evaluating Design Choices for Synthetic Training Captions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ajinkya Kale, Felix Friedrich, Hareesh Ravi, Kristian Kersting, Manuel Brack, Patrick Schramowski, Sudeep Katakol","submitted_at":"2025-06-20T01:52:17Z","abstract_excerpt":"Training data is at the core of any successful text-to-image models. The quality and descriptiveness of image text are crucial to a model's performance. Given the noisiness and inconsistency in web-scraped datasets, recent works shifted towards synthetic training captions. While this setup is generally believed to produce more capable models, current literature does not provide any insights into its design choices. This study closes this gap by systematically investigating how different synthetic captioning strategies impact the downstream performance of text-to-image models. Our experiments d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16679","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/2506.16679/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":"2026-07-05T11:24:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yeQIhGK7xpThp2UhvOsCOA+xVaTCnNUEHwysYTcq0C4GwZkMqoqnA5EJL9OM8JbovnJzkC3D1qj3/FFHO/TvBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:36:07.933801Z"},"content_sha256":"48ee95f381323115b7203f9eac331b2be3a88575a1c00022d9712326a579df24","schema_version":"1.0","event_id":"sha256:48ee95f381323115b7203f9eac331b2be3a88575a1c00022d9712326a579df24"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NB7XOPQDTRF3TFYPG2UEGCM5PG/bundle.json","state_url":"https://pith.science/pith/NB7XOPQDTRF3TFYPG2UEGCM5PG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NB7XOPQDTRF3TFYPG2UEGCM5PG/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":"2026-08-10T13:36:07Z","links":{"resolver":"https://pith.science/pith/NB7XOPQDTRF3TFYPG2UEGCM5PG","bundle":"https://pith.science/pith/NB7XOPQDTRF3TFYPG2UEGCM5PG/bundle.json","state":"https://pith.science/pith/NB7XOPQDTRF3TFYPG2UEGCM5PG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NB7XOPQDTRF3TFYPG2UEGCM5PG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NB7XOPQDTRF3TFYPG2UEGCM5PG","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":"9dcf489602c04484501111f57c6b69711b878e276e81c3224661352a48d0383c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T01:52:17Z","title_canon_sha256":"45e40dd139471c1ae65482c12113baaa791f65115ccdbcf5c81f3afe7809af7e"},"schema_version":"1.0","source":{"id":"2506.16679","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16679","created_at":"2026-07-05T11:24:40Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16679v1","created_at":"2026-07-05T11:24:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16679","created_at":"2026-07-05T11:24:40Z"},{"alias_kind":"pith_short_12","alias_value":"NB7XOPQDTRF3","created_at":"2026-07-05T11:24:40Z"},{"alias_kind":"pith_short_16","alias_value":"NB7XOPQDTRF3TFYP","created_at":"2026-07-05T11:24:40Z"},{"alias_kind":"pith_short_8","alias_value":"NB7XOPQD","created_at":"2026-07-05T11:24:40Z"}],"graph_snapshots":[{"event_id":"sha256:48ee95f381323115b7203f9eac331b2be3a88575a1c00022d9712326a579df24","target":"graph","created_at":"2026-07-05T11:24:40Z","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/2506.16679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training data is at the core of any successful text-to-image models. The quality and descriptiveness of image text are crucial to a model's performance. Given the noisiness and inconsistency in web-scraped datasets, recent works shifted towards synthetic training captions. While this setup is generally believed to produce more capable models, current literature does not provide any insights into its design choices. This study closes this gap by systematically investigating how different synthetic captioning strategies impact the downstream performance of text-to-image models. Our experiments d","authors_text":"Ajinkya Kale, Felix Friedrich, Hareesh Ravi, Kristian Kersting, Manuel Brack, Patrick Schramowski, Sudeep Katakol","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T01:52:17Z","title":"How to Train your Text-to-Image Model: Evaluating Design Choices for Synthetic Training Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16679","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":"sha256:311988fc76d7d631ed5f228a2165eabbcb38e3dac9aeb9222750598f77cf6ada","target":"record","created_at":"2026-07-05T11:24:40Z","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":"9dcf489602c04484501111f57c6b69711b878e276e81c3224661352a48d0383c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T01:52:17Z","title_canon_sha256":"45e40dd139471c1ae65482c12113baaa791f65115ccdbcf5c81f3afe7809af7e"},"schema_version":"1.0","source":{"id":"2506.16679","kind":"arxiv","version":1}},"canonical_sha256":"687f773e039c4bb9970f36a843099d79adaf2109e80c300aa4546fb4c236f985","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"687f773e039c4bb9970f36a843099d79adaf2109e80c300aa4546fb4c236f985","first_computed_at":"2026-07-05T11:24:40.585443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:40.585443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yrhbX1aiAk5lI1joOjNteALX22gJLOgRF/4BVhL8J3NK1OpTqGQsqrsxg8CHw1NP/m8UOFRpNLLX81l5uHJ0CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:40.585971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16679","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:311988fc76d7d631ed5f228a2165eabbcb38e3dac9aeb9222750598f77cf6ada","sha256:48ee95f381323115b7203f9eac331b2be3a88575a1c00022d9712326a579df24"],"state_sha256":"3ceeaec79ff7c5b5955ee9f75f8048f3e00343886451dace3bef41016c75b52d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w6+I5ijW4mxNkbDZlKs4e6KIHDVxS2IACTqP88o0f0jD2fKxuzAYXvaDU02yqcgwVc+58santmqCccKJssvTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T13:36:07.938735Z","bundle_sha256":"dbf299c8690274a8c2092b2f9274a6718e492fea14249286286386d7c15d5aa3"}}