{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:44BLWDB2OXNEOWZXHQQZ4GSEFK","short_pith_number":"pith:44BLWDB2","schema_version":"1.0","canonical_sha256":"e702bb0c3a75da475b373c219e1a442ab256dcd252be3ac001f9b3e199ab2f59","source":{"kind":"arxiv","id":"2405.19773","version":1},"attestation_state":"computed","paper":{"title":"VQA Training Sets are Self-play Environments for Generating Few-shot Pools","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hassan Mansoor, Jasper Uijlings, Oriana Riva, Tautvydas Misiunas, Victor Carbune","submitted_at":"2024-05-30T07:38:58Z","abstract_excerpt":"Large-language models and large-vision models are increasingly capable of solving compositional reasoning tasks, as measured by breakthroughs in visual-question answering benchmarks. However, state-of-the-art solutions often involve careful construction of large pre-training and fine-tuning datasets, which can be expensive. The use of external tools, whether other ML models, search engines, or APIs, can significantly improve performance by breaking down high-level reasoning questions into sub-questions that are answerable by individual tools, but this approach has similar dataset construction "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.19773","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T07:38:58Z","cross_cats_sorted":[],"title_canon_sha256":"076c5a41d866b0379832c37b6b341f694d9a02b98223325d52c1d52928f03835","abstract_canon_sha256":"4f7ca1b421c3aa2005a3d8b415f94773b27c72f5244abea0267d13aee35ec5a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:12.264880Z","signature_b64":"NXMay99uh7+MXqyXalRQo1J5+0jluzvOWfiXPsD6NzsK2p+gxpb565U6s5GvT53vdNDpI96gpjNY/zfPh0ikDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e702bb0c3a75da475b373c219e1a442ab256dcd252be3ac001f9b3e199ab2f59","last_reissued_at":"2026-07-05T08:25:12.264416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:12.264416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VQA Training Sets are Self-play Environments for Generating Few-shot Pools","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hassan Mansoor, Jasper Uijlings, Oriana Riva, Tautvydas Misiunas, Victor Carbune","submitted_at":"2024-05-30T07:38:58Z","abstract_excerpt":"Large-language models and large-vision models are increasingly capable of solving compositional reasoning tasks, as measured by breakthroughs in visual-question answering benchmarks. However, state-of-the-art solutions often involve careful construction of large pre-training and fine-tuning datasets, which can be expensive. The use of external tools, whether other ML models, search engines, or APIs, can significantly improve performance by breaking down high-level reasoning questions into sub-questions that are answerable by individual tools, but this approach has similar dataset construction "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19773","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/2405.19773/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.19773","created_at":"2026-07-05T08:25:12.264473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19773v1","created_at":"2026-07-05T08:25:12.264473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19773","created_at":"2026-07-05T08:25:12.264473+00:00"},{"alias_kind":"pith_short_12","alias_value":"44BLWDB2OXNE","created_at":"2026-07-05T08:25:12.264473+00:00"},{"alias_kind":"pith_short_16","alias_value":"44BLWDB2OXNEOWZX","created_at":"2026-07-05T08:25:12.264473+00:00"},{"alias_kind":"pith_short_8","alias_value":"44BLWDB2","created_at":"2026-07-05T08:25:12.264473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22933","citing_title":"Augmented Vision-Language Models: A Systematic Review","ref_index":75,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/44BLWDB2OXNEOWZXHQQZ4GSEFK","json":"https://pith.science/pith/44BLWDB2OXNEOWZXHQQZ4GSEFK.json","graph_json":"https://pith.science/api/pith-number/44BLWDB2OXNEOWZXHQQZ4GSEFK/graph.json","events_json":"https://pith.science/api/pith-number/44BLWDB2OXNEOWZXHQQZ4GSEFK/events.json","paper":"https://pith.science/paper/44BLWDB2"},"agent_actions":{"view_html":"https://pith.science/pith/44BLWDB2OXNEOWZXHQQZ4GSEFK","download_json":"https://pith.science/pith/44BLWDB2OXNEOWZXHQQZ4GSEFK.json","view_paper":"https://pith.science/paper/44BLWDB2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19773&json=true","fetch_graph":"https://pith.science/api/pith-number/44BLWDB2OXNEOWZXHQQZ4GSEFK/graph.json","fetch_events":"https://pith.science/api/pith-number/44BLWDB2OXNEOWZXHQQZ4GSEFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/44BLWDB2OXNEOWZXHQQZ4GSEFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/44BLWDB2OXNEOWZXHQQZ4GSEFK/action/storage_attestation","attest_author":"https://pith.science/pith/44BLWDB2OXNEOWZXHQQZ4GSEFK/action/author_attestation","sign_citation":"https://pith.science/pith/44BLWDB2OXNEOWZXHQQZ4GSEFK/action/citation_signature","submit_replication":"https://pith.science/pith/44BLWDB2OXNEOWZXHQQZ4GSEFK/action/replication_record"}},"created_at":"2026-07-05T08:25:12.264473+00:00","updated_at":"2026-07-05T08:25:12.264473+00:00"}