{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WFWZ2IQET733P3GFVZ2XPCAUHL","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":"f444e9b01db0af94c96aff22889a8c14a47d7346e25007ba2703176304ac229d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T06:41:39Z","title_canon_sha256":"6085d8ec9fb20802cb77978af5dd25f943194432c7a69961dddb62f12ba8132c"},"schema_version":"1.0","source":{"id":"2407.01983","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.01983","created_at":"2026-07-05T08:39:08Z"},{"alias_kind":"arxiv_version","alias_value":"2407.01983v1","created_at":"2026-07-05T08:39:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01983","created_at":"2026-07-05T08:39:08Z"},{"alias_kind":"pith_short_12","alias_value":"WFWZ2IQET733","created_at":"2026-07-05T08:39:08Z"},{"alias_kind":"pith_short_16","alias_value":"WFWZ2IQET733P3GF","created_at":"2026-07-05T08:39:08Z"},{"alias_kind":"pith_short_8","alias_value":"WFWZ2IQE","created_at":"2026-07-05T08:39:08Z"}],"graph_snapshots":[{"event_id":"sha256:5ae56079257456966a1b124e74bf6a5d3d3178ac40d17b307ec2d28014b98e40","target":"graph","created_at":"2026-07-05T08:39:08Z","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/2407.01983/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large vision-language models (LVLMs) offer a novel capability for performing in-context learning (ICL) in Visual QA. When prompted with a few demonstrations of image-question-answer triplets, LVLMs have demonstrated the ability to discern underlying patterns and transfer this latent knowledge to answer new questions about unseen images without the need for expensive supervised fine-tuning. However, designing effective vision-language prompts, especially for compositional questions, remains poorly understood. Adapting language-only ICL techniques may not necessarily work because we need to brid","authors_text":"Long Hoang Dang, Thao Minh Le, Truyen Tran, Tu Minh Phuong, Vuong Le","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T06:41:39Z","title":"SADL: An Effective In-Context Learning Method for Compositional Visual QA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01983","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":"sha256:1eba03a4069b46d3f754f1702fd7e98dc3b46b51f3203661b5ed22cb09fe9fa1","target":"record","created_at":"2026-07-05T08:39:08Z","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":"f444e9b01db0af94c96aff22889a8c14a47d7346e25007ba2703176304ac229d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T06:41:39Z","title_canon_sha256":"6085d8ec9fb20802cb77978af5dd25f943194432c7a69961dddb62f12ba8132c"},"schema_version":"1.0","source":{"id":"2407.01983","kind":"arxiv","version":1}},"canonical_sha256":"b16d9d22049ff7b7ecc5ae757788143aff494220bdeca25f3cea0e5c9cab261d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b16d9d22049ff7b7ecc5ae757788143aff494220bdeca25f3cea0e5c9cab261d","first_computed_at":"2026-07-05T08:39:08.224146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:08.224146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fHop6NYo6H53P4/Y6NRbiLw2YzYmuVFmzY2DZXT1QYgV5Dov/VmzfXB/ui9a9dqwV8jp6gM1Lk8hRUfH4P9kBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:08.224568Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.01983","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1eba03a4069b46d3f754f1702fd7e98dc3b46b51f3203661b5ed22cb09fe9fa1","sha256:5ae56079257456966a1b124e74bf6a5d3d3178ac40d17b307ec2d28014b98e40"],"state_sha256":"818df0cdd427c901a7449ddb8ad801f6dbde434793d6c69cebd429f102d6b539"}