{"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"}