{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ENLCXHM4Z4MVYCWW3GZ347DMS4","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":"5f0cbf3faa289893ac7ec71a046f10a372da2d5e0aa04753ec19ae72e22da7a2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T16:06:38Z","title_canon_sha256":"34d03371c39f93da7e0a6332c71cf21e3a6029f6868e8778e3c88a6fd4cd9e1b"},"schema_version":"1.0","source":{"id":"2406.12746","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12746","created_at":"2026-07-05T09:17:43Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12746v5","created_at":"2026-07-05T09:17:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12746","created_at":"2026-07-05T09:17:43Z"},{"alias_kind":"pith_short_12","alias_value":"ENLCXHM4Z4MV","created_at":"2026-07-05T09:17:43Z"},{"alias_kind":"pith_short_16","alias_value":"ENLCXHM4Z4MVYCWW","created_at":"2026-07-05T09:17:43Z"},{"alias_kind":"pith_short_8","alias_value":"ENLCXHM4","created_at":"2026-07-05T09:17:43Z"}],"graph_snapshots":[{"event_id":"sha256:3639c055a60cbffbbb284c111f464a3b0f0d5b2d9e7f810914ef5cea88f46a79","target":"graph","created_at":"2026-07-05T09:17:43Z","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/2406.12746/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge-based Visual Question-answering (K-VQA) often requires the use of background knowledge beyond the image. However, we discover that a single knowledge generation strategy is often insufficient for all K-VQA questions. To this end, we propose Diversification, Evidence Truncation, and Combination for Knowledge-based Elucidation (DietCoke), which utilizes a bundle of complementary question-answering tactics and aggregates their answers using textual rationales. DietCoke comprises of three stages: diversification, rationalization, and ensemble. The diversification stage generates three di","authors_text":"Boyang Li, Haoxin Li, Miaoyu Li, Zilin Du","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T16:06:38Z","title":"Diversify, Rationalize, and Combine: Ensembling Multiple QA Strategies for Zero-shot Knowledge-based VQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12746","kind":"arxiv","version":5},"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":"sha256:55ec5eebb06d6d5ec5596bd47e8c34decaa6433fc920ff4c07d93cd808954bd6","target":"record","created_at":"2026-07-05T09:17:43Z","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":"5f0cbf3faa289893ac7ec71a046f10a372da2d5e0aa04753ec19ae72e22da7a2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T16:06:38Z","title_canon_sha256":"34d03371c39f93da7e0a6332c71cf21e3a6029f6868e8778e3c88a6fd4cd9e1b"},"schema_version":"1.0","source":{"id":"2406.12746","kind":"arxiv","version":5}},"canonical_sha256":"23562b9d9ccf195c0ad6d9b3be7c6c97039a91a73aa59a931a5447ceb2652ed9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23562b9d9ccf195c0ad6d9b3be7c6c97039a91a73aa59a931a5447ceb2652ed9","first_computed_at":"2026-07-05T09:17:43.572850Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:43.572850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rv9XkG83ilTNfWLI0GSZaWKjFtwbvXpN2nNiW87YovKaimWLstmrMpwcVYOsqw+smgifBF1MmS4LVC3KrBC0BA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:43.573330Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12746","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55ec5eebb06d6d5ec5596bd47e8c34decaa6433fc920ff4c07d93cd808954bd6","sha256:3639c055a60cbffbbb284c111f464a3b0f0d5b2d9e7f810914ef5cea88f46a79"],"state_sha256":"91c582bd84b4331deee2f90cf562fcff47f7b304f34545954c2d54a14eddaec6"}