{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RLJKGZFDYFCWIP5QEK7B4UOXTU","short_pith_number":"pith:RLJKGZFD","canonical_record":{"source":{"id":"2210.08773","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-17T06:29:54Z","cross_cats_sorted":[],"title_canon_sha256":"a458fd6c30286e089d8e07ce2aee76bfc29b91a5eed7bc6425fb968125a92ce2","abstract_canon_sha256":"8ea280ef6ddd5c9456a60e01b00fa8674b8f3d54b46de3c923eb859713e1adcb"},"schema_version":"1.0"},"canonical_sha256":"8ad2a364a3c145643fb022be1e51d79d27546627bf282a4f011d0437b7749a26","source":{"kind":"arxiv","id":"2210.08773","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.08773","created_at":"2026-07-05T05:52:22Z"},{"alias_kind":"arxiv_version","alias_value":"2210.08773v3","created_at":"2026-07-05T05:52:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.08773","created_at":"2026-07-05T05:52:22Z"},{"alias_kind":"pith_short_12","alias_value":"RLJKGZFDYFCW","created_at":"2026-07-05T05:52:22Z"},{"alias_kind":"pith_short_16","alias_value":"RLJKGZFDYFCWIP5Q","created_at":"2026-07-05T05:52:22Z"},{"alias_kind":"pith_short_8","alias_value":"RLJKGZFD","created_at":"2026-07-05T05:52:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RLJKGZFDYFCWIP5QEK7B4UOXTU","target":"record","payload":{"canonical_record":{"source":{"id":"2210.08773","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-17T06:29:54Z","cross_cats_sorted":[],"title_canon_sha256":"a458fd6c30286e089d8e07ce2aee76bfc29b91a5eed7bc6425fb968125a92ce2","abstract_canon_sha256":"8ea280ef6ddd5c9456a60e01b00fa8674b8f3d54b46de3c923eb859713e1adcb"},"schema_version":"1.0"},"canonical_sha256":"8ad2a364a3c145643fb022be1e51d79d27546627bf282a4f011d0437b7749a26","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:22.992573Z","signature_b64":"B3HIErJu2eSb//w1AEkOkdm37Tnea+Gh9DZa/CpRGUZ8eS71fiVyQeiSkxoKZj/hKtpgoFr7j5s2n1ZlqpZ9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ad2a364a3c145643fb022be1e51d79d27546627bf282a4f011d0437b7749a26","last_reissued_at":"2026-07-05T05:52:22.992058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:22.992058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.08773","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:52:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iLljI7e6dQ20/nPROhrhM2/kLBopnjYtmZmiRJGtg9MEwfzDa/4pPvP5SI38Qb+HMYktCX0U23x97mzX39+OCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:52:35.776365Z"},"content_sha256":"3d8133afe2e0bbbf61b4852d0a8e6f262039cf9fee3d214c027892d5c3576393","schema_version":"1.0","event_id":"sha256:3d8133afe2e0bbbf61b4852d0a8e6f262039cf9fee3d214c027892d5c3576393"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RLJKGZFDYFCWIP5QEK7B4UOXTU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anthony Meng Huat Tiong, Boyang Li, Junnan Li, Silvio Savarese, Steven C.H. Hoi","submitted_at":"2022-10-17T06:29:54Z","abstract_excerpt":"Visual question answering (VQA) is a hallmark of vision and language reasoning and a challenging task under the zero-shot setting. We propose Plug-and-Play VQA (PNP-VQA), a modular framework for zero-shot VQA. In contrast to most existing works, which require substantial adaptation of pretrained language models (PLMs) for the vision modality, PNP-VQA requires no additional training of the PLMs. Instead, we propose to use natural language and network interpretation as an intermediate representation that glues pretrained models together. We first generate question-guided informative image captio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.08773","kind":"arxiv","version":3},"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/2210.08773/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":"2026-07-05T05:52:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DFzCfGulx7sWbBmf3IqDwDUUD8wheVrNbpJ9pDVRnpj2CN56Nah7CHnLJFm1O19A6MDlqN0MPIfv1yjzCmtMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:52:35.777280Z"},"content_sha256":"4044a48e010ac58fb5275c490959a59b4e6b084e6d1dedaf34c95f538e2a7dd3","schema_version":"1.0","event_id":"sha256:4044a48e010ac58fb5275c490959a59b4e6b084e6d1dedaf34c95f538e2a7dd3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RLJKGZFDYFCWIP5QEK7B4UOXTU/bundle.json","state_url":"https://pith.science/pith/RLJKGZFDYFCWIP5QEK7B4UOXTU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RLJKGZFDYFCWIP5QEK7B4UOXTU/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":"2026-08-08T04:52:35Z","links":{"resolver":"https://pith.science/pith/RLJKGZFDYFCWIP5QEK7B4UOXTU","bundle":"https://pith.science/pith/RLJKGZFDYFCWIP5QEK7B4UOXTU/bundle.json","state":"https://pith.science/pith/RLJKGZFDYFCWIP5QEK7B4UOXTU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RLJKGZFDYFCWIP5QEK7B4UOXTU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RLJKGZFDYFCWIP5QEK7B4UOXTU","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":"8ea280ef6ddd5c9456a60e01b00fa8674b8f3d54b46de3c923eb859713e1adcb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-17T06:29:54Z","title_canon_sha256":"a458fd6c30286e089d8e07ce2aee76bfc29b91a5eed7bc6425fb968125a92ce2"},"schema_version":"1.0","source":{"id":"2210.08773","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.08773","created_at":"2026-07-05T05:52:22Z"},{"alias_kind":"arxiv_version","alias_value":"2210.08773v3","created_at":"2026-07-05T05:52:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.08773","created_at":"2026-07-05T05:52:22Z"},{"alias_kind":"pith_short_12","alias_value":"RLJKGZFDYFCW","created_at":"2026-07-05T05:52:22Z"},{"alias_kind":"pith_short_16","alias_value":"RLJKGZFDYFCWIP5Q","created_at":"2026-07-05T05:52:22Z"},{"alias_kind":"pith_short_8","alias_value":"RLJKGZFD","created_at":"2026-07-05T05:52:22Z"}],"graph_snapshots":[{"event_id":"sha256:4044a48e010ac58fb5275c490959a59b4e6b084e6d1dedaf34c95f538e2a7dd3","target":"graph","created_at":"2026-07-05T05:52:22Z","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/2210.08773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual question answering (VQA) is a hallmark of vision and language reasoning and a challenging task under the zero-shot setting. We propose Plug-and-Play VQA (PNP-VQA), a modular framework for zero-shot VQA. In contrast to most existing works, which require substantial adaptation of pretrained language models (PLMs) for the vision modality, PNP-VQA requires no additional training of the PLMs. Instead, we propose to use natural language and network interpretation as an intermediate representation that glues pretrained models together. We first generate question-guided informative image captio","authors_text":"Anthony Meng Huat Tiong, Boyang Li, Junnan Li, Silvio Savarese, Steven C.H. Hoi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-17T06:29:54Z","title":"Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.08773","kind":"arxiv","version":3},"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":"sha256:3d8133afe2e0bbbf61b4852d0a8e6f262039cf9fee3d214c027892d5c3576393","target":"record","created_at":"2026-07-05T05:52:22Z","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":"8ea280ef6ddd5c9456a60e01b00fa8674b8f3d54b46de3c923eb859713e1adcb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-17T06:29:54Z","title_canon_sha256":"a458fd6c30286e089d8e07ce2aee76bfc29b91a5eed7bc6425fb968125a92ce2"},"schema_version":"1.0","source":{"id":"2210.08773","kind":"arxiv","version":3}},"canonical_sha256":"8ad2a364a3c145643fb022be1e51d79d27546627bf282a4f011d0437b7749a26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ad2a364a3c145643fb022be1e51d79d27546627bf282a4f011d0437b7749a26","first_computed_at":"2026-07-05T05:52:22.992058Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:52:22.992058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B3HIErJu2eSb//w1AEkOkdm37Tnea+Gh9DZa/CpRGUZ8eS71fiVyQeiSkxoKZj/hKtpgoFr7j5s2n1ZlqpZ9BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:52:22.992573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.08773","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d8133afe2e0bbbf61b4852d0a8e6f262039cf9fee3d214c027892d5c3576393","sha256:4044a48e010ac58fb5275c490959a59b4e6b084e6d1dedaf34c95f538e2a7dd3"],"state_sha256":"3d87986448c2ad98581b5177e4ca3ceccd199b60632d8aaff1453bae792826b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LH+ln9ZJcmyd9KMiyTMSWUnDBnsI0/OnzGbYx1K7+I7z69rFj6E8RKzLXYYykzfb3mqg0uRycqx+yW5AG+xPDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:52:35.783349Z","bundle_sha256":"e0a74dee60fd60d9fdae33d3323e0a495d046504ff8147aa4e3971688951a30f"}}