{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GKBAWWW77LAY3Y3AROUUBJBRZR","short_pith_number":"pith:GKBAWWW7","canonical_record":{"source":{"id":"2305.17006","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-26T15:04:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e7230eb471703cfdcd8e3d9d5e746b2e3b207c80f8dbde3920209f4918db1886","abstract_canon_sha256":"42eef278a706d513b802b3306bdb5edeeacce00d24f5481c87e507ead140c2e2"},"schema_version":"1.0"},"canonical_sha256":"32820b5adffac18de3608ba940a431cc63c5834e77f2a06832a7727670d4662c","source":{"kind":"arxiv","id":"2305.17006","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17006","created_at":"2026-07-05T06:14:19Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17006v1","created_at":"2026-07-05T06:14:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17006","created_at":"2026-07-05T06:14:19Z"},{"alias_kind":"pith_short_12","alias_value":"GKBAWWW77LAY","created_at":"2026-07-05T06:14:19Z"},{"alias_kind":"pith_short_16","alias_value":"GKBAWWW77LAY3Y3A","created_at":"2026-07-05T06:14:19Z"},{"alias_kind":"pith_short_8","alias_value":"GKBAWWW7","created_at":"2026-07-05T06:14:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GKBAWWW77LAY3Y3AROUUBJBRZR","target":"record","payload":{"canonical_record":{"source":{"id":"2305.17006","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-26T15:04:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e7230eb471703cfdcd8e3d9d5e746b2e3b207c80f8dbde3920209f4918db1886","abstract_canon_sha256":"42eef278a706d513b802b3306bdb5edeeacce00d24f5481c87e507ead140c2e2"},"schema_version":"1.0"},"canonical_sha256":"32820b5adffac18de3608ba940a431cc63c5834e77f2a06832a7727670d4662c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:19.962408Z","signature_b64":"q1eKLxRXSMkASg13JGYHHkvX3ACjZSlSIrr2rwTat27fUq9shrscM3U4dvWTeFH2Ko8WY2rwHWimNQ9lygzaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32820b5adffac18de3608ba940a431cc63c5834e77f2a06832a7727670d4662c","last_reissued_at":"2026-07-05T06:14:19.962059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:19.962059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.17006","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":"2026-07-05T06:14:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WJlNQSBQjRAkJXeNX3Gqpo8lxd9LnHdpKDqxMYF1G6PMHZ4EiX7Uppp7iEO8KGnTMTwF+66JoVfVaK3UNo0tAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:33:48.207519Z"},"content_sha256":"abcc6acc1fe242866693a6844f3c5c161e176387aa852d23d7b77538f334236a","schema_version":"1.0","event_id":"sha256:abcc6acc1fe242866693a6844f3c5c161e176387aa852d23d7b77538f334236a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GKBAWWW77LAY3Y3AROUUBJBRZR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-shot Visual Question Answering with Language Model Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Ji-Rong Wen, Junyi Li, Tianyi Tang, Wayne Xin Zhao, Yifan Du","submitted_at":"2023-05-26T15:04:20Z","abstract_excerpt":"In this paper, we propose a novel language model guided captioning approach, LAMOC, for knowledge-based visual question answering (VQA). Our approach employs the generated captions by a captioning model as the context of an answer prediction model, which is a Pre-trained Language model (PLM). As the major contribution, we leverage the guidance and feedback of the prediction model to improve the capability of the captioning model. In this way, the captioning model can become aware of the task goal and information need from the PLM. To develop our approach, we design two specific training stages"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17006","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/2305.17006/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":"2026-07-05T06:14:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hvOKsf4dhz9CGqhZHMuyTwA5y7g10E8ZI2WMgzPjBIZA/4OOiHBgxwv4GBEBCWOi9pTIoBuhM0UOCxOrDONCCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:33:48.208017Z"},"content_sha256":"b38352ca46e7a5c72c4ae336afafa0b916f2ddb31ce8c3e44f72c30347326b9c","schema_version":"1.0","event_id":"sha256:b38352ca46e7a5c72c4ae336afafa0b916f2ddb31ce8c3e44f72c30347326b9c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GKBAWWW77LAY3Y3AROUUBJBRZR/bundle.json","state_url":"https://pith.science/pith/GKBAWWW77LAY3Y3AROUUBJBRZR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GKBAWWW77LAY3Y3AROUUBJBRZR/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":"2026-08-08T17:33:48Z","links":{"resolver":"https://pith.science/pith/GKBAWWW77LAY3Y3AROUUBJBRZR","bundle":"https://pith.science/pith/GKBAWWW77LAY3Y3AROUUBJBRZR/bundle.json","state":"https://pith.science/pith/GKBAWWW77LAY3Y3AROUUBJBRZR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GKBAWWW77LAY3Y3AROUUBJBRZR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GKBAWWW77LAY3Y3AROUUBJBRZR","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":"42eef278a706d513b802b3306bdb5edeeacce00d24f5481c87e507ead140c2e2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-26T15:04:20Z","title_canon_sha256":"e7230eb471703cfdcd8e3d9d5e746b2e3b207c80f8dbde3920209f4918db1886"},"schema_version":"1.0","source":{"id":"2305.17006","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17006","created_at":"2026-07-05T06:14:19Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17006v1","created_at":"2026-07-05T06:14:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17006","created_at":"2026-07-05T06:14:19Z"},{"alias_kind":"pith_short_12","alias_value":"GKBAWWW77LAY","created_at":"2026-07-05T06:14:19Z"},{"alias_kind":"pith_short_16","alias_value":"GKBAWWW77LAY3Y3A","created_at":"2026-07-05T06:14:19Z"},{"alias_kind":"pith_short_8","alias_value":"GKBAWWW7","created_at":"2026-07-05T06:14:19Z"}],"graph_snapshots":[{"event_id":"sha256:b38352ca46e7a5c72c4ae336afafa0b916f2ddb31ce8c3e44f72c30347326b9c","target":"graph","created_at":"2026-07-05T06:14:19Z","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/2305.17006/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a novel language model guided captioning approach, LAMOC, for knowledge-based visual question answering (VQA). Our approach employs the generated captions by a captioning model as the context of an answer prediction model, which is a Pre-trained Language model (PLM). As the major contribution, we leverage the guidance and feedback of the prediction model to improve the capability of the captioning model. In this way, the captioning model can become aware of the task goal and information need from the PLM. To develop our approach, we design two specific training stages","authors_text":"Ji-Rong Wen, Junyi Li, Tianyi Tang, Wayne Xin Zhao, Yifan Du","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-26T15:04:20Z","title":"Zero-shot Visual Question Answering with Language Model Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17006","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:abcc6acc1fe242866693a6844f3c5c161e176387aa852d23d7b77538f334236a","target":"record","created_at":"2026-07-05T06:14:19Z","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":"42eef278a706d513b802b3306bdb5edeeacce00d24f5481c87e507ead140c2e2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-26T15:04:20Z","title_canon_sha256":"e7230eb471703cfdcd8e3d9d5e746b2e3b207c80f8dbde3920209f4918db1886"},"schema_version":"1.0","source":{"id":"2305.17006","kind":"arxiv","version":1}},"canonical_sha256":"32820b5adffac18de3608ba940a431cc63c5834e77f2a06832a7727670d4662c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32820b5adffac18de3608ba940a431cc63c5834e77f2a06832a7727670d4662c","first_computed_at":"2026-07-05T06:14:19.962059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:19.962059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q1eKLxRXSMkASg13JGYHHkvX3ACjZSlSIrr2rwTat27fUq9shrscM3U4dvWTeFH2Ko8WY2rwHWimNQ9lygzaBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:19.962408Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17006","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:abcc6acc1fe242866693a6844f3c5c161e176387aa852d23d7b77538f334236a","sha256:b38352ca46e7a5c72c4ae336afafa0b916f2ddb31ce8c3e44f72c30347326b9c"],"state_sha256":"5e21ca41e4b988e6df20e34cb97ebafaccb0abaa1ff46ce46a7e7c326f23fc61"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VofbgWWKF/fGNFWAPcd9/iuWLr70FZX6HXK2OKNG4mzInhsUVVv8YKzdyN5R5wZdOYLQhY+jpQmYB7P0NW+eDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:33:48.213426Z","bundle_sha256":"5678c339f12efdc4d7fee4d28b63886b3218234eb4aeab1e63bbe8f9db4cfcfe"}}