{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GJZZ22DRTBUR5ZNMUGWE6ZQ3C5","short_pith_number":"pith:GJZZ22DR","canonical_record":{"source":{"id":"2411.07461","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T00:52:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"de046e70030d8d1c8c86c63473698e6a8d5906e11230ed1db93459637179cd0b","abstract_canon_sha256":"5b0de3305ee5611cbcef7b5dfafbb74ce10b9322ef273e6e9e31671286a29d2a"},"schema_version":"1.0"},"canonical_sha256":"32739d687198691ee5aca1ac4f661b175bca1d84083b6b5d83e64fc3fe56ffb0","source":{"kind":"arxiv","id":"2411.07461","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07461","created_at":"2026-07-05T09:34:24Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07461v1","created_at":"2026-07-05T09:34:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07461","created_at":"2026-07-05T09:34:24Z"},{"alias_kind":"pith_short_12","alias_value":"GJZZ22DRTBUR","created_at":"2026-07-05T09:34:24Z"},{"alias_kind":"pith_short_16","alias_value":"GJZZ22DRTBUR5ZNM","created_at":"2026-07-05T09:34:24Z"},{"alias_kind":"pith_short_8","alias_value":"GJZZ22DR","created_at":"2026-07-05T09:34:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GJZZ22DRTBUR5ZNMUGWE6ZQ3C5","target":"record","payload":{"canonical_record":{"source":{"id":"2411.07461","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T00:52:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"de046e70030d8d1c8c86c63473698e6a8d5906e11230ed1db93459637179cd0b","abstract_canon_sha256":"5b0de3305ee5611cbcef7b5dfafbb74ce10b9322ef273e6e9e31671286a29d2a"},"schema_version":"1.0"},"canonical_sha256":"32739d687198691ee5aca1ac4f661b175bca1d84083b6b5d83e64fc3fe56ffb0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:24.318418Z","signature_b64":"w7MR1iIi97Dy3YxCpubIfPuvM6+ndWP4pigB+DiODEJIfkeo2JJwscABumSr3mfr55RbFtgPdqTx5aLEUU3PAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32739d687198691ee5aca1ac4f661b175bca1d84083b6b5d83e64fc3fe56ffb0","last_reissued_at":"2026-07-05T09:34:24.317982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:24.317982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.07461","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":"2026-07-05T09:34:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gz56lYaB3OH7cAfIM21+7lgJHECQWB0L3N/oVS9z1MtiidhN0gLlAJvWsa46jvkhoYUWevDD3nY91ZmQfA2ICQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T19:28:40.277961Z"},"content_sha256":"8665f80486ce7f7b8a08ab1f3f58701e8040a96a8864476713d7ec745d646334","schema_version":"1.0","event_id":"sha256:8665f80486ce7f7b8a08ab1f3f58701e8040a96a8864476713d7ec745d646334"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GJZZ22DRTBUR5ZNMUGWE6ZQ3C5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BLIP3-KALE: Knowledge Augmented Large-Scale Dense Captions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anas Awadalla, An Yan, Caiming Xiong, Etash Guha, Hannah Lee, Jae Sung Park, Jun Wang, Le Xue, Ludwig Schmidt, Manli Shu, Oscar Lo, Ran Xu, Senthil Purushwalkam, Sheng Shen, Silvio Savarese, Yejin Choi","submitted_at":"2024-11-12T00:52:52Z","abstract_excerpt":"We introduce BLIP3-KALE, a dataset of 218 million image-text pairs that bridges the gap between descriptive synthetic captions and factual web-scale alt-text. KALE augments synthetic dense image captions with web-scale alt-text to generate factually grounded image captions. Our two-stage approach leverages large vision-language models and language models to create knowledge-augmented captions, which are then used to train a specialized VLM for scaling up the dataset. We train vision-language models on KALE and demonstrate improvements on vision-language tasks. Our experiments show the utility "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07461","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/2411.07461/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":"2026-07-05T09:34:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9XQOKdbn79g7eniMuny6w2tShYGWcBOpc8IFBMx/szIwtG/qwF45Cka5+oWl5be0PA6w+9Uds/utQCEswMchAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T19:28:40.278476Z"},"content_sha256":"d3f58a6f054e09b72a55d8b1b18aa5a36333f8b8575c2f95a5bd576256699c93","schema_version":"1.0","event_id":"sha256:d3f58a6f054e09b72a55d8b1b18aa5a36333f8b8575c2f95a5bd576256699c93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GJZZ22DRTBUR5ZNMUGWE6ZQ3C5/bundle.json","state_url":"https://pith.science/pith/GJZZ22DRTBUR5ZNMUGWE6ZQ3C5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GJZZ22DRTBUR5ZNMUGWE6ZQ3C5/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":"2026-08-23T19:28:40Z","links":{"resolver":"https://pith.science/pith/GJZZ22DRTBUR5ZNMUGWE6ZQ3C5","bundle":"https://pith.science/pith/GJZZ22DRTBUR5ZNMUGWE6ZQ3C5/bundle.json","state":"https://pith.science/pith/GJZZ22DRTBUR5ZNMUGWE6ZQ3C5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GJZZ22DRTBUR5ZNMUGWE6ZQ3C5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GJZZ22DRTBUR5ZNMUGWE6ZQ3C5","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":"5b0de3305ee5611cbcef7b5dfafbb74ce10b9322ef273e6e9e31671286a29d2a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T00:52:52Z","title_canon_sha256":"de046e70030d8d1c8c86c63473698e6a8d5906e11230ed1db93459637179cd0b"},"schema_version":"1.0","source":{"id":"2411.07461","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.07461","created_at":"2026-07-05T09:34:24Z"},{"alias_kind":"arxiv_version","alias_value":"2411.07461v1","created_at":"2026-07-05T09:34:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07461","created_at":"2026-07-05T09:34:24Z"},{"alias_kind":"pith_short_12","alias_value":"GJZZ22DRTBUR","created_at":"2026-07-05T09:34:24Z"},{"alias_kind":"pith_short_16","alias_value":"GJZZ22DRTBUR5ZNM","created_at":"2026-07-05T09:34:24Z"},{"alias_kind":"pith_short_8","alias_value":"GJZZ22DR","created_at":"2026-07-05T09:34:24Z"}],"graph_snapshots":[{"event_id":"sha256:d3f58a6f054e09b72a55d8b1b18aa5a36333f8b8575c2f95a5bd576256699c93","target":"graph","created_at":"2026-07-05T09:34:24Z","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/2411.07461/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce BLIP3-KALE, a dataset of 218 million image-text pairs that bridges the gap between descriptive synthetic captions and factual web-scale alt-text. KALE augments synthetic dense image captions with web-scale alt-text to generate factually grounded image captions. Our two-stage approach leverages large vision-language models and language models to create knowledge-augmented captions, which are then used to train a specialized VLM for scaling up the dataset. We train vision-language models on KALE and demonstrate improvements on vision-language tasks. Our experiments show the utility ","authors_text":"Anas Awadalla, An Yan, Caiming Xiong, Etash Guha, Hannah Lee, Jae Sung Park, Jun Wang, Le Xue, Ludwig Schmidt, Manli Shu, Oscar Lo, Ran Xu, Senthil Purushwalkam, Sheng Shen, Silvio Savarese, Yejin Choi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T00:52:52Z","title":"BLIP3-KALE: Knowledge Augmented Large-Scale Dense Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07461","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":"sha256:8665f80486ce7f7b8a08ab1f3f58701e8040a96a8864476713d7ec745d646334","target":"record","created_at":"2026-07-05T09:34:24Z","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":"5b0de3305ee5611cbcef7b5dfafbb74ce10b9322ef273e6e9e31671286a29d2a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T00:52:52Z","title_canon_sha256":"de046e70030d8d1c8c86c63473698e6a8d5906e11230ed1db93459637179cd0b"},"schema_version":"1.0","source":{"id":"2411.07461","kind":"arxiv","version":1}},"canonical_sha256":"32739d687198691ee5aca1ac4f661b175bca1d84083b6b5d83e64fc3fe56ffb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32739d687198691ee5aca1ac4f661b175bca1d84083b6b5d83e64fc3fe56ffb0","first_computed_at":"2026-07-05T09:34:24.317982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:24.317982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w7MR1iIi97Dy3YxCpubIfPuvM6+ndWP4pigB+DiODEJIfkeo2JJwscABumSr3mfr55RbFtgPdqTx5aLEUU3PAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:24.318418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.07461","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8665f80486ce7f7b8a08ab1f3f58701e8040a96a8864476713d7ec745d646334","sha256:d3f58a6f054e09b72a55d8b1b18aa5a36333f8b8575c2f95a5bd576256699c93"],"state_sha256":"ab04656043663991e1217345139f4b387e8619001969eb72f46973389742f1be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RLG3iKWvw7p3aPCz3ZfFi8lcJqBzYMNJDK6uSWyeNQVr8VtaEh5VXkAb9eJF/IbFueoIpft9PHRLcnbMiRAZDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T19:28:40.284381Z","bundle_sha256":"8757d7184eb973fc22f2e36918191744f255fc85e8273db02f1d6d1252547507"}}