{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:J666W3XERI4XRJOHIMPNELREQX","short_pith_number":"pith:J666W3XE","canonical_record":{"source":{"id":"2305.18842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T08:34:13Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"25e6dcfcbb43e756f8ede50d77995ef499179f060058282439a577e30e21bf7e","abstract_canon_sha256":"ba43fd3f9c3b5581ccf8521f5dbea6b870e3f393fea05bf7d0cf2fd8a95718c6"},"schema_version":"1.0"},"canonical_sha256":"4fbdeb6ee48a3978a5c7431ed22e2485f76a61966e232a06d48b90da875bea00","source":{"kind":"arxiv","id":"2305.18842","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18842","created_at":"2026-07-05T06:15:05Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18842v1","created_at":"2026-07-05T06:15:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18842","created_at":"2026-07-05T06:15:05Z"},{"alias_kind":"pith_short_12","alias_value":"J666W3XERI4X","created_at":"2026-07-05T06:15:05Z"},{"alias_kind":"pith_short_16","alias_value":"J666W3XERI4XRJOH","created_at":"2026-07-05T06:15:05Z"},{"alias_kind":"pith_short_8","alias_value":"J666W3XE","created_at":"2026-07-05T06:15:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:J666W3XERI4XRJOHIMPNELREQX","target":"record","payload":{"canonical_record":{"source":{"id":"2305.18842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T08:34:13Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"25e6dcfcbb43e756f8ede50d77995ef499179f060058282439a577e30e21bf7e","abstract_canon_sha256":"ba43fd3f9c3b5581ccf8521f5dbea6b870e3f393fea05bf7d0cf2fd8a95718c6"},"schema_version":"1.0"},"canonical_sha256":"4fbdeb6ee48a3978a5c7431ed22e2485f76a61966e232a06d48b90da875bea00","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:05.695459Z","signature_b64":"z93OEd4vBAJ1HHzboSLijPiCPapOfbRElh/qBPF3SQS8N5eYlF8fKS64+yWw+1DWFxT4NjRc8F9XBuFv/lMlAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fbdeb6ee48a3978a5c7431ed22e2485f76a61966e232a06d48b90da875bea00","last_reissued_at":"2026-07-05T06:15:05.694953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:05.694953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.18842","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":"2026-07-05T06:15:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lr64omwCTCzBBPV6nirGFpC9661ZW3eOVs3mCrcLS8gnvzbX0PLT6DkB4A2Tp149YK0055BzUTk+1wyTrlbiBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:18:44.241741Z"},"content_sha256":"8ee336ee440274e3d37327651624730339b2f3c2f05fa9c42f93816b105e8e11","schema_version":"1.0","event_id":"sha256:8ee336ee440274e3d37327651624730339b2f3c2f05fa9c42f93816b105e8e11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:J666W3XERI4XRJOHIMPNELREQX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Alexander Hanbo Li, Bing Xiang, Dan Roth, Gukyeong Kwon, Henghui Zhu, Patrick Ng, Pramuditha Perera, Sheng Zhang, Vittorio Castelli, William Yang Wang, Xingyu Fu, Yuhao Zhang, Zhiguo Wang","submitted_at":"2023-05-30T08:34:13Z","abstract_excerpt":"The open-ended Visual Question Answering (VQA) task requires AI models to jointly reason over visual and natural language inputs using world knowledge. Recently, pre-trained Language Models (PLM) such as GPT-3 have been applied to the task and shown to be powerful world knowledge sources. However, these methods suffer from low knowledge coverage caused by PLM bias -- the tendency to generate certain tokens over other tokens regardless of prompt changes, and high dependency on the PLM quality -- only models using GPT-3 can achieve the best result.\n  To address the aforementioned challenges, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18842","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/2305.18842/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":"2026-07-05T06:15:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U69DOOFicUbHAXzsf03brccsPiMUlmcN/a8wmdzZHpgdeGgYLndYie6BeoIBx1A+ayA+nunfOS1EbtRFRKLqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T17:18:44.242348Z"},"content_sha256":"30775c1026cf3ed7faa574975c876f3ca910bd78dd58f51aeb757e55aa7ae1e3","schema_version":"1.0","event_id":"sha256:30775c1026cf3ed7faa574975c876f3ca910bd78dd58f51aeb757e55aa7ae1e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J666W3XERI4XRJOHIMPNELREQX/bundle.json","state_url":"https://pith.science/pith/J666W3XERI4XRJOHIMPNELREQX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J666W3XERI4XRJOHIMPNELREQX/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":"2026-08-21T17:18:44Z","links":{"resolver":"https://pith.science/pith/J666W3XERI4XRJOHIMPNELREQX","bundle":"https://pith.science/pith/J666W3XERI4XRJOHIMPNELREQX/bundle.json","state":"https://pith.science/pith/J666W3XERI4XRJOHIMPNELREQX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J666W3XERI4XRJOHIMPNELREQX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:J666W3XERI4XRJOHIMPNELREQX","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":"ba43fd3f9c3b5581ccf8521f5dbea6b870e3f393fea05bf7d0cf2fd8a95718c6","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T08:34:13Z","title_canon_sha256":"25e6dcfcbb43e756f8ede50d77995ef499179f060058282439a577e30e21bf7e"},"schema_version":"1.0","source":{"id":"2305.18842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18842","created_at":"2026-07-05T06:15:05Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18842v1","created_at":"2026-07-05T06:15:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18842","created_at":"2026-07-05T06:15:05Z"},{"alias_kind":"pith_short_12","alias_value":"J666W3XERI4X","created_at":"2026-07-05T06:15:05Z"},{"alias_kind":"pith_short_16","alias_value":"J666W3XERI4XRJOH","created_at":"2026-07-05T06:15:05Z"},{"alias_kind":"pith_short_8","alias_value":"J666W3XE","created_at":"2026-07-05T06:15:05Z"}],"graph_snapshots":[{"event_id":"sha256:30775c1026cf3ed7faa574975c876f3ca910bd78dd58f51aeb757e55aa7ae1e3","target":"graph","created_at":"2026-07-05T06:15:05Z","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/2305.18842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The open-ended Visual Question Answering (VQA) task requires AI models to jointly reason over visual and natural language inputs using world knowledge. Recently, pre-trained Language Models (PLM) such as GPT-3 have been applied to the task and shown to be powerful world knowledge sources. However, these methods suffer from low knowledge coverage caused by PLM bias -- the tendency to generate certain tokens over other tokens regardless of prompt changes, and high dependency on the PLM quality -- only models using GPT-3 can achieve the best result.\n  To address the aforementioned challenges, we ","authors_text":"Alexander Hanbo Li, Bing Xiang, Dan Roth, Gukyeong Kwon, Henghui Zhu, Patrick Ng, Pramuditha Perera, Sheng Zhang, Vittorio Castelli, William Yang Wang, Xingyu Fu, Yuhao Zhang, Zhiguo Wang","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T08:34:13Z","title":"Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18842","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":"sha256:8ee336ee440274e3d37327651624730339b2f3c2f05fa9c42f93816b105e8e11","target":"record","created_at":"2026-07-05T06:15:05Z","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":"ba43fd3f9c3b5581ccf8521f5dbea6b870e3f393fea05bf7d0cf2fd8a95718c6","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T08:34:13Z","title_canon_sha256":"25e6dcfcbb43e756f8ede50d77995ef499179f060058282439a577e30e21bf7e"},"schema_version":"1.0","source":{"id":"2305.18842","kind":"arxiv","version":1}},"canonical_sha256":"4fbdeb6ee48a3978a5c7431ed22e2485f76a61966e232a06d48b90da875bea00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4fbdeb6ee48a3978a5c7431ed22e2485f76a61966e232a06d48b90da875bea00","first_computed_at":"2026-07-05T06:15:05.694953Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:05.694953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z93OEd4vBAJ1HHzboSLijPiCPapOfbRElh/qBPF3SQS8N5eYlF8fKS64+yWw+1DWFxT4NjRc8F9XBuFv/lMlAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:05.695459Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.18842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ee336ee440274e3d37327651624730339b2f3c2f05fa9c42f93816b105e8e11","sha256:30775c1026cf3ed7faa574975c876f3ca910bd78dd58f51aeb757e55aa7ae1e3"],"state_sha256":"7be5dfd18817c050b3d6371c013083ba8cfb48239382c99db79eaf5f25bb871b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6+6vuZeVoMzLjobXaoqw7nUfiEyzqipq6mqcWw6CW6nfdR6UOX7yUL44Whn84qcbVYq4QXm3S+wYsZCZvWvSAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T17:18:44.247813Z","bundle_sha256":"5c6124e37e8f9bf88011d80f9dec98f83f49a9c0cc417a5ac33db41364e1a3a6"}}