{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VK76W57UJ7BQTLIURIOM5RL5C6","short_pith_number":"pith:VK76W57U","canonical_record":{"source":{"id":"2201.12086","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-28T12:49:48Z","cross_cats_sorted":[],"title_canon_sha256":"55c2083b78cdd879b4126ccc806bc030dea530747cbd767f4552963e178bf054","abstract_canon_sha256":"b1e393b0ed6306570df95f871cce2cd51723d8122d0156f27ea73a55ad4903c7"},"schema_version":"1.0"},"canonical_sha256":"aabfeb77f44fc309ad148a1ccec57d17bd6de359a1ac04a13fcd56082cdc85db","source":{"kind":"arxiv","id":"2201.12086","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.12086","created_at":"2026-07-05T03:56:54Z"},{"alias_kind":"arxiv_version","alias_value":"2201.12086v2","created_at":"2026-07-05T03:56:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12086","created_at":"2026-07-05T03:56:54Z"},{"alias_kind":"pith_short_12","alias_value":"VK76W57UJ7BQ","created_at":"2026-07-05T03:56:54Z"},{"alias_kind":"pith_short_16","alias_value":"VK76W57UJ7BQTLIU","created_at":"2026-07-05T03:56:54Z"},{"alias_kind":"pith_short_8","alias_value":"VK76W57U","created_at":"2026-07-05T03:56:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VK76W57UJ7BQTLIURIOM5RL5C6","target":"record","payload":{"canonical_record":{"source":{"id":"2201.12086","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-28T12:49:48Z","cross_cats_sorted":[],"title_canon_sha256":"55c2083b78cdd879b4126ccc806bc030dea530747cbd767f4552963e178bf054","abstract_canon_sha256":"b1e393b0ed6306570df95f871cce2cd51723d8122d0156f27ea73a55ad4903c7"},"schema_version":"1.0"},"canonical_sha256":"aabfeb77f44fc309ad148a1ccec57d17bd6de359a1ac04a13fcd56082cdc85db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:54.279243Z","signature_b64":"rjGav3wGUGZSeZV2IW7C/CF+KnS1EtOEGds/Rqm5JJp2Ib8IINoIJeibRzbUywJanLlq69Rp6C00xFncOqU/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aabfeb77f44fc309ad148a1ccec57d17bd6de359a1ac04a13fcd56082cdc85db","last_reissued_at":"2026-07-05T03:56:54.278823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:54.278823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.12086","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:56:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FpnP4ilX9zYRrbh0VNOv4XSXEuaZg+22PPW9gITU06X9MUt9yQOnWLkxzV0ms8imLF+BUCAXuOprsoGR8wh1AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:37:21.298886Z"},"content_sha256":"4a1e3f5587acaac11439eb6e36f46b3edd281a8626142a09f48b6b70e955002e","schema_version":"1.0","event_id":"sha256:4a1e3f5587acaac11439eb6e36f46b3edd281a8626142a09f48b6b70e955002e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VK76W57UJ7BQTLIURIOM5RL5C6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Caiming Xiong, Dongxu Li, Junnan Li, Steven Hoi","submitted_at":"2022-01-28T12:49:48Z","abstract_excerpt":"Vision-Language Pre-training (VLP) has advanced the performance for many vision-language tasks. However, most existing pre-trained models only excel in either understanding-based tasks or generation-based tasks. Furthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image-text pairs collected from the web, which is a suboptimal source of supervision. In this paper, we propose BLIP, a new VLP framework which transfers flexibly to both vision-language understanding and generation tasks. BLIP effectively utilizes the noisy web data by bootstrapping the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12086","kind":"arxiv","version":2},"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/2201.12086/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":"2026-07-05T03:56:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bI1NDxmjmhhDpasrffKS4TZbitZ1TB8ZkHO+zzRPqnN1lzs2zYNlkegevSvNfgLNLgUwGzmAjYexo3R5ZCOoDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:37:21.299556Z"},"content_sha256":"df1c92b376413f611c01e5321c61101671da4dc6f93bc28934d6dfb9876a57e4","schema_version":"1.0","event_id":"sha256:df1c92b376413f611c01e5321c61101671da4dc6f93bc28934d6dfb9876a57e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VK76W57UJ7BQTLIURIOM5RL5C6/bundle.json","state_url":"https://pith.science/pith/VK76W57UJ7BQTLIURIOM5RL5C6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VK76W57UJ7BQTLIURIOM5RL5C6/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":"2026-08-01T05:37:21Z","links":{"resolver":"https://pith.science/pith/VK76W57UJ7BQTLIURIOM5RL5C6","bundle":"https://pith.science/pith/VK76W57UJ7BQTLIURIOM5RL5C6/bundle.json","state":"https://pith.science/pith/VK76W57UJ7BQTLIURIOM5RL5C6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VK76W57UJ7BQTLIURIOM5RL5C6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VK76W57UJ7BQTLIURIOM5RL5C6","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":"b1e393b0ed6306570df95f871cce2cd51723d8122d0156f27ea73a55ad4903c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-28T12:49:48Z","title_canon_sha256":"55c2083b78cdd879b4126ccc806bc030dea530747cbd767f4552963e178bf054"},"schema_version":"1.0","source":{"id":"2201.12086","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.12086","created_at":"2026-07-05T03:56:54Z"},{"alias_kind":"arxiv_version","alias_value":"2201.12086v2","created_at":"2026-07-05T03:56:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12086","created_at":"2026-07-05T03:56:54Z"},{"alias_kind":"pith_short_12","alias_value":"VK76W57UJ7BQ","created_at":"2026-07-05T03:56:54Z"},{"alias_kind":"pith_short_16","alias_value":"VK76W57UJ7BQTLIU","created_at":"2026-07-05T03:56:54Z"},{"alias_kind":"pith_short_8","alias_value":"VK76W57U","created_at":"2026-07-05T03:56:54Z"}],"graph_snapshots":[{"event_id":"sha256:df1c92b376413f611c01e5321c61101671da4dc6f93bc28934d6dfb9876a57e4","target":"graph","created_at":"2026-07-05T03:56:54Z","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/2201.12086/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Pre-training (VLP) has advanced the performance for many vision-language tasks. However, most existing pre-trained models only excel in either understanding-based tasks or generation-based tasks. Furthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image-text pairs collected from the web, which is a suboptimal source of supervision. In this paper, we propose BLIP, a new VLP framework which transfers flexibly to both vision-language understanding and generation tasks. BLIP effectively utilizes the noisy web data by bootstrapping the","authors_text":"Caiming Xiong, Dongxu Li, Junnan Li, Steven Hoi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-28T12:49:48Z","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12086","kind":"arxiv","version":2},"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":"sha256:4a1e3f5587acaac11439eb6e36f46b3edd281a8626142a09f48b6b70e955002e","target":"record","created_at":"2026-07-05T03:56:54Z","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":"b1e393b0ed6306570df95f871cce2cd51723d8122d0156f27ea73a55ad4903c7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-28T12:49:48Z","title_canon_sha256":"55c2083b78cdd879b4126ccc806bc030dea530747cbd767f4552963e178bf054"},"schema_version":"1.0","source":{"id":"2201.12086","kind":"arxiv","version":2}},"canonical_sha256":"aabfeb77f44fc309ad148a1ccec57d17bd6de359a1ac04a13fcd56082cdc85db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aabfeb77f44fc309ad148a1ccec57d17bd6de359a1ac04a13fcd56082cdc85db","first_computed_at":"2026-07-05T03:56:54.278823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:56:54.278823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rjGav3wGUGZSeZV2IW7C/CF+KnS1EtOEGds/Rqm5JJp2Ib8IINoIJeibRzbUywJanLlq69Rp6C00xFncOqU/BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:56:54.279243Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.12086","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a1e3f5587acaac11439eb6e36f46b3edd281a8626142a09f48b6b70e955002e","sha256:df1c92b376413f611c01e5321c61101671da4dc6f93bc28934d6dfb9876a57e4"],"state_sha256":"76f427d9607959e732230ee72df66163e980755a6a619014401574b1080e4e09"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ksv7puwPvN8Y/o6ies+BwwFUR6iHSJ5zN5qfgQ2OgnzWDg4Sl2rZQuDql1DcDRnOmJd41Nt7l7j6D0pxnQdxBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T05:37:21.308866Z","bundle_sha256":"bf9b52e4c992dde2758d14d7b38a4dcc0b34c43e9f8fd19169aa5e15f8e7fd26"}}