{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:EXYWER247DPAC6SWSE5TGVGBJN","short_pith_number":"pith:EXYWER24","canonical_record":{"source":{"id":"2505.15172","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T06:42:17Z","cross_cats_sorted":[],"title_canon_sha256":"e2e2dc57760afe674a9f6665169fd27a6931a8c0eda9ea1f35bd89bab2989a1d","abstract_canon_sha256":"d5cee3a7be66b79d89b28a8f5ccac7a18aa1fe43cf26e862f427c7a9e3716d89"},"schema_version":"1.0"},"canonical_sha256":"25f162475cf8de017a56913b3354c14b787dd0b1774d51337071545dea4a526f","source":{"kind":"arxiv","id":"2505.15172","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15172","created_at":"2026-07-05T11:06:41Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15172v1","created_at":"2026-07-05T11:06:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15172","created_at":"2026-07-05T11:06:41Z"},{"alias_kind":"pith_short_12","alias_value":"EXYWER247DPA","created_at":"2026-07-05T11:06:41Z"},{"alias_kind":"pith_short_16","alias_value":"EXYWER247DPAC6SW","created_at":"2026-07-05T11:06:41Z"},{"alias_kind":"pith_short_8","alias_value":"EXYWER24","created_at":"2026-07-05T11:06:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:EXYWER247DPAC6SWSE5TGVGBJN","target":"record","payload":{"canonical_record":{"source":{"id":"2505.15172","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T06:42:17Z","cross_cats_sorted":[],"title_canon_sha256":"e2e2dc57760afe674a9f6665169fd27a6931a8c0eda9ea1f35bd89bab2989a1d","abstract_canon_sha256":"d5cee3a7be66b79d89b28a8f5ccac7a18aa1fe43cf26e862f427c7a9e3716d89"},"schema_version":"1.0"},"canonical_sha256":"25f162475cf8de017a56913b3354c14b787dd0b1774d51337071545dea4a526f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:41.676510Z","signature_b64":"xcTObK05IoPr0JIEvWVjiMwgMcDEs6wj3YDxAxSA3dQIZKVPMuu4Zdxtn42UEQkc7yPFSOYiNpVFP7fDTVORAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25f162475cf8de017a56913b3354c14b787dd0b1774d51337071545dea4a526f","last_reissued_at":"2026-07-05T11:06:41.676008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:41.676008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.15172","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":"2026-07-05T11:06:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wdC4RHLc943okwqrXKCLM4u4fgjNcdpaX2Nct3j8ovf9Ud233qpo4FeUI1BL4HTbFWlfashmcjK1pT5au3AlDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:51:57.362362Z"},"content_sha256":"3b36bc6bab79a21679b086ccbd5e4e1aaef5feb6716b46ad7bc8dbeaa19c71d0","schema_version":"1.0","event_id":"sha256:3b36bc6bab79a21679b086ccbd5e4e1aaef5feb6716b46ad7bc8dbeaa19c71d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:EXYWER247DPAC6SWSE5TGVGBJN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Harnessing Caption Detailness for Data-Efficient Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunyu Wang, Jun Guo, Kongming Liang, Muxi Diao, Xinran Wang, Yuanzhi Liu, Zhanyu Ma","submitted_at":"2025-05-21T06:42:17Z","abstract_excerpt":"Training text-to-image (T2I) models with detailed captions can significantly improve their generation quality. Existing methods often rely on simplistic metrics like caption length to represent the detailness of the caption in the T2I training set. In this paper, we propose a new metric to estimate caption detailness based on two aspects: image coverage rate (ICR), which evaluates whether the caption covers all regions/objects in the image, and average object detailness (AOD), which quantifies the detailness of each object's description. Through experiments on the COCO dataset using ShareGPT4V"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15172","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/2505.15172/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":"2026-07-05T11:06:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ipa4lybDeKUrIe5tnX+Svrh2C9kGNKYiCfaVi0QwaM8bxJyFSVE6X64q0rOg1SimfZ5Uc2q/PQut90RlkQyGDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:51:57.362734Z"},"content_sha256":"b178be972553c64d712e585aeb8d75fb18e2770d7ec93409e9a9023d677f25fc","schema_version":"1.0","event_id":"sha256:b178be972553c64d712e585aeb8d75fb18e2770d7ec93409e9a9023d677f25fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EXYWER247DPAC6SWSE5TGVGBJN/bundle.json","state_url":"https://pith.science/pith/EXYWER247DPAC6SWSE5TGVGBJN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EXYWER247DPAC6SWSE5TGVGBJN/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":"2026-07-06T12:51:57Z","links":{"resolver":"https://pith.science/pith/EXYWER247DPAC6SWSE5TGVGBJN","bundle":"https://pith.science/pith/EXYWER247DPAC6SWSE5TGVGBJN/bundle.json","state":"https://pith.science/pith/EXYWER247DPAC6SWSE5TGVGBJN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EXYWER247DPAC6SWSE5TGVGBJN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EXYWER247DPAC6SWSE5TGVGBJN","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":"d5cee3a7be66b79d89b28a8f5ccac7a18aa1fe43cf26e862f427c7a9e3716d89","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T06:42:17Z","title_canon_sha256":"e2e2dc57760afe674a9f6665169fd27a6931a8c0eda9ea1f35bd89bab2989a1d"},"schema_version":"1.0","source":{"id":"2505.15172","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15172","created_at":"2026-07-05T11:06:41Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15172v1","created_at":"2026-07-05T11:06:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15172","created_at":"2026-07-05T11:06:41Z"},{"alias_kind":"pith_short_12","alias_value":"EXYWER247DPA","created_at":"2026-07-05T11:06:41Z"},{"alias_kind":"pith_short_16","alias_value":"EXYWER247DPAC6SW","created_at":"2026-07-05T11:06:41Z"},{"alias_kind":"pith_short_8","alias_value":"EXYWER24","created_at":"2026-07-05T11:06:41Z"}],"graph_snapshots":[{"event_id":"sha256:b178be972553c64d712e585aeb8d75fb18e2770d7ec93409e9a9023d677f25fc","target":"graph","created_at":"2026-07-05T11:06:41Z","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/2505.15172/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training text-to-image (T2I) models with detailed captions can significantly improve their generation quality. Existing methods often rely on simplistic metrics like caption length to represent the detailness of the caption in the T2I training set. In this paper, we propose a new metric to estimate caption detailness based on two aspects: image coverage rate (ICR), which evaluates whether the caption covers all regions/objects in the image, and average object detailness (AOD), which quantifies the detailness of each object's description. Through experiments on the COCO dataset using ShareGPT4V","authors_text":"Chunyu Wang, Jun Guo, Kongming Liang, Muxi Diao, Xinran Wang, Yuanzhi Liu, Zhanyu Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T06:42:17Z","title":"Harnessing Caption Detailness for Data-Efficient Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15172","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":"sha256:3b36bc6bab79a21679b086ccbd5e4e1aaef5feb6716b46ad7bc8dbeaa19c71d0","target":"record","created_at":"2026-07-05T11:06:41Z","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":"d5cee3a7be66b79d89b28a8f5ccac7a18aa1fe43cf26e862f427c7a9e3716d89","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T06:42:17Z","title_canon_sha256":"e2e2dc57760afe674a9f6665169fd27a6931a8c0eda9ea1f35bd89bab2989a1d"},"schema_version":"1.0","source":{"id":"2505.15172","kind":"arxiv","version":1}},"canonical_sha256":"25f162475cf8de017a56913b3354c14b787dd0b1774d51337071545dea4a526f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25f162475cf8de017a56913b3354c14b787dd0b1774d51337071545dea4a526f","first_computed_at":"2026-07-05T11:06:41.676008Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:41.676008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xcTObK05IoPr0JIEvWVjiMwgMcDEs6wj3YDxAxSA3dQIZKVPMuu4Zdxtn42UEQkc7yPFSOYiNpVFP7fDTVORAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:41.676510Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15172","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b36bc6bab79a21679b086ccbd5e4e1aaef5feb6716b46ad7bc8dbeaa19c71d0","sha256:b178be972553c64d712e585aeb8d75fb18e2770d7ec93409e9a9023d677f25fc"],"state_sha256":"ef3d4befba8782765f58d0a7dc2cd2f945aeb4dc4991ff5204c4b0c54ec4a559"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i64eGSc6AFOx57+GF7l/PEPCXUt1a7TVZSq3qP/On0snK9DZL7aNqnFz05K6KqEXvnvrgKqCyEhmghIwTSxBBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T12:51:57.364688Z","bundle_sha256":"33a8ab0058c1d0ccc6e592ee6e435fd02d042575680641e95428553427836586"}}