{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OMHEN2T635FHDWPOY57YQ6SFOX","short_pith_number":"pith:OMHEN2T6","canonical_record":{"source":{"id":"2403.17007","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:59:42Z","cross_cats_sorted":[],"title_canon_sha256":"77617be863844c6d0ca82ddf3a77da60b04441446c572cf29966aa64da198773","abstract_canon_sha256":"9ef5f64196f9bd6c46b54cbb9919d27a10eeb66133cefb12f5f7d2cf5b4e3895"},"schema_version":"1.0"},"canonical_sha256":"730e46ea7edf4a71d9eec77f887a4575c69d7d92c54a660bf12a3e7589cb7a0d","source":{"kind":"arxiv","id":"2403.17007","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.17007","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"arxiv_version","alias_value":"2403.17007v1","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17007","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"pith_short_12","alias_value":"OMHEN2T635FH","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"pith_short_16","alias_value":"OMHEN2T635FHDWPO","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"pith_short_8","alias_value":"OMHEN2T6","created_at":"2026-07-05T08:00:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OMHEN2T635FHDWPOY57YQ6SFOX","target":"record","payload":{"canonical_record":{"source":{"id":"2403.17007","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:59:42Z","cross_cats_sorted":[],"title_canon_sha256":"77617be863844c6d0ca82ddf3a77da60b04441446c572cf29966aa64da198773","abstract_canon_sha256":"9ef5f64196f9bd6c46b54cbb9919d27a10eeb66133cefb12f5f7d2cf5b4e3895"},"schema_version":"1.0"},"canonical_sha256":"730e46ea7edf4a71d9eec77f887a4575c69d7d92c54a660bf12a3e7589cb7a0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:23.841766Z","signature_b64":"ZT4H9rIVR31V4XsXpofHpx/k1P4uzAewjVKXBwW6zMtFY5UDlI/3u5ivKh5ewY98j9h3VpjJfzr1Z3HuXXQAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"730e46ea7edf4a71d9eec77f887a4575c69d7d92c54a660bf12a3e7589cb7a0d","last_reissued_at":"2026-07-05T08:00:23.841271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:23.841271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.17007","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":"2026-07-05T08:00:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IFx/iVrBCt5D2L1fqDMFvzjjMU8BwWT1lwvA+npF/ZUntE5Ax/McvRzVQZAj+XgNkQ5X2CqKc7CnxggEhRbxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:38:37.887504Z"},"content_sha256":"eb84d194e98180d38fa39a5250e7fb35638b11b3d0d4901dbb493f9fa87d4603","schema_version":"1.0","event_id":"sha256:eb84d194e98180d38fa39a5250e7fb35638b11b3d0d4901dbb493f9fa87d4603"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OMHEN2T635FHDWPOY57YQ6SFOX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DreamLIP: Language-Image Pre-training with Long Captions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Lu, Kecheng Zheng, Shuailei Ma, Wei Chen, Wei Wu, Xin Jin, Yifei Zhang, Yujun Shen","submitted_at":"2024-03-25T17:59:42Z","abstract_excerpt":"Language-image pre-training largely relies on how precisely and thoroughly a text describes its paired image. In practice, however, the contents of an image can be so rich that well describing them requires lengthy captions (e.g., with 10 sentences), which are usually missing in existing datasets. Consequently, there are currently no clear evidences on whether and how language-image pre-training could benefit from long captions. To figure this out, we first re-caption 30M images with detailed descriptions using a pre-trained Multi-modality Large Language Model (MLLM), and then study the usage "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17007","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/2403.17007/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":"2026-07-05T08:00:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y3L1pEQ5NAvtcqOGSrazj9jDaY/cNs23RBtJ5ush17cVDTOmyKlV2I32j0CzrU299s6ZqziAFX+M/YNvnnkPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:38:37.888061Z"},"content_sha256":"9f915595fea856b7d48123bc8550a3c689aa89b07b1dd0a36fcd8cc519ffff05","schema_version":"1.0","event_id":"sha256:9f915595fea856b7d48123bc8550a3c689aa89b07b1dd0a36fcd8cc519ffff05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OMHEN2T635FHDWPOY57YQ6SFOX/bundle.json","state_url":"https://pith.science/pith/OMHEN2T635FHDWPOY57YQ6SFOX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OMHEN2T635FHDWPOY57YQ6SFOX/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":"2026-08-04T09:38:37Z","links":{"resolver":"https://pith.science/pith/OMHEN2T635FHDWPOY57YQ6SFOX","bundle":"https://pith.science/pith/OMHEN2T635FHDWPOY57YQ6SFOX/bundle.json","state":"https://pith.science/pith/OMHEN2T635FHDWPOY57YQ6SFOX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OMHEN2T635FHDWPOY57YQ6SFOX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OMHEN2T635FHDWPOY57YQ6SFOX","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":"9ef5f64196f9bd6c46b54cbb9919d27a10eeb66133cefb12f5f7d2cf5b4e3895","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:59:42Z","title_canon_sha256":"77617be863844c6d0ca82ddf3a77da60b04441446c572cf29966aa64da198773"},"schema_version":"1.0","source":{"id":"2403.17007","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.17007","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"arxiv_version","alias_value":"2403.17007v1","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17007","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"pith_short_12","alias_value":"OMHEN2T635FH","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"pith_short_16","alias_value":"OMHEN2T635FHDWPO","created_at":"2026-07-05T08:00:23Z"},{"alias_kind":"pith_short_8","alias_value":"OMHEN2T6","created_at":"2026-07-05T08:00:23Z"}],"graph_snapshots":[{"event_id":"sha256:9f915595fea856b7d48123bc8550a3c689aa89b07b1dd0a36fcd8cc519ffff05","target":"graph","created_at":"2026-07-05T08:00:23Z","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/2403.17007/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language-image pre-training largely relies on how precisely and thoroughly a text describes its paired image. In practice, however, the contents of an image can be so rich that well describing them requires lengthy captions (e.g., with 10 sentences), which are usually missing in existing datasets. Consequently, there are currently no clear evidences on whether and how language-image pre-training could benefit from long captions. To figure this out, we first re-caption 30M images with detailed descriptions using a pre-trained Multi-modality Large Language Model (MLLM), and then study the usage ","authors_text":"Fan Lu, Kecheng Zheng, Shuailei Ma, Wei Chen, Wei Wu, Xin Jin, Yifei Zhang, Yujun Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:59:42Z","title":"DreamLIP: Language-Image Pre-training with Long Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17007","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:eb84d194e98180d38fa39a5250e7fb35638b11b3d0d4901dbb493f9fa87d4603","target":"record","created_at":"2026-07-05T08:00:23Z","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":"9ef5f64196f9bd6c46b54cbb9919d27a10eeb66133cefb12f5f7d2cf5b4e3895","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T17:59:42Z","title_canon_sha256":"77617be863844c6d0ca82ddf3a77da60b04441446c572cf29966aa64da198773"},"schema_version":"1.0","source":{"id":"2403.17007","kind":"arxiv","version":1}},"canonical_sha256":"730e46ea7edf4a71d9eec77f887a4575c69d7d92c54a660bf12a3e7589cb7a0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"730e46ea7edf4a71d9eec77f887a4575c69d7d92c54a660bf12a3e7589cb7a0d","first_computed_at":"2026-07-05T08:00:23.841271Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:00:23.841271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZT4H9rIVR31V4XsXpofHpx/k1P4uzAewjVKXBwW6zMtFY5UDlI/3u5ivKh5ewY98j9h3VpjJfzr1Z3HuXXQAAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:00:23.841766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.17007","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb84d194e98180d38fa39a5250e7fb35638b11b3d0d4901dbb493f9fa87d4603","sha256:9f915595fea856b7d48123bc8550a3c689aa89b07b1dd0a36fcd8cc519ffff05"],"state_sha256":"df1483ae2204f05f37c4e2e6bb1bfdaddfdcb6062d3f8967f87052c60a7edab1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sSeUy1BSz5xc5/OKxO1YfhkVDA/uroiqdmLl5sTPgjss3+b08yk+VBNsTpPL58DDtSJnMXuEfi76JGdAipYHCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:38:37.891629Z","bundle_sha256":"8edae25a8ca81d405bc929a5dfb3c8419311c083d328f6acb43a64669325d0a1"}}