{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PMULYQ76ID3PE7HSDG2M5LKZSV","short_pith_number":"pith:PMULYQ76","schema_version":"1.0","canonical_sha256":"7b28bc43fe40f6f27cf219b4cead59954291e4f24862db06e3aaee545ac91f48","source":{"kind":"arxiv","id":"2505.21755","version":2},"attestation_state":"computed","paper":{"title":"FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Brisa Maneechotesuwan, Chengyue Huang, Shivang Chopra, Zsolt Kira","submitted_at":"2025-05-27T20:44:44Z","abstract_excerpt":"Visual question answering (VQA) systems face significant challenges when adapting to real-world data shifts, especially in multi-modal contexts. While robust fine-tuning strategies are essential for maintaining performance across in-distribution (ID) and out-of-distribution (OOD) scenarios, current evaluation settings are primarily unimodal or particular to some types of OOD, offering limited insight into the complexities of multi-modal contexts. In this work, we propose a new benchmark FRAMES-VQA (Fine-Tuning Robustness across Multi-Modal Shifts in VQA) for evaluating robust fine-tuning for V"},"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":"2505.21755","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T20:44:44Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"fed97e0eecd952b0c0762ac647add5fd41213dbd543df3861ca9aaecfdf12d0e","abstract_canon_sha256":"d74207508c193b1cda6efbc97320b7060f2d63faec9dea38c13cd2c0053608e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:11.227245Z","signature_b64":"zqRGFxoLjsc1OU8a1AtA9yzFEYBox7nQzlHd6sdnx+AhYUQRzRPwhQ+W0GtN3aJjFd+kqfCvxgkxn/T8O1X/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b28bc43fe40f6f27cf219b4cead59954291e4f24862db06e3aaee545ac91f48","last_reissued_at":"2026-07-05T11:25:11.226750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:11.226750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Brisa Maneechotesuwan, Chengyue Huang, Shivang Chopra, Zsolt Kira","submitted_at":"2025-05-27T20:44:44Z","abstract_excerpt":"Visual question answering (VQA) systems face significant challenges when adapting to real-world data shifts, especially in multi-modal contexts. While robust fine-tuning strategies are essential for maintaining performance across in-distribution (ID) and out-of-distribution (OOD) scenarios, current evaluation settings are primarily unimodal or particular to some types of OOD, offering limited insight into the complexities of multi-modal contexts. In this work, we propose a new benchmark FRAMES-VQA (Fine-Tuning Robustness across Multi-Modal Shifts in VQA) for evaluating robust fine-tuning for V"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21755","kind":"arxiv","version":2},"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/2505.21755/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":"2505.21755","created_at":"2026-07-05T11:25:11.226809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21755v2","created_at":"2026-07-05T11:25:11.226809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21755","created_at":"2026-07-05T11:25:11.226809+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMULYQ76ID3P","created_at":"2026-07-05T11:25:11.226809+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMULYQ76ID3PE7HS","created_at":"2026-07-05T11:25:11.226809+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMULYQ76","created_at":"2026-07-05T11:25:11.226809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PMULYQ76ID3PE7HSDG2M5LKZSV","json":"https://pith.science/pith/PMULYQ76ID3PE7HSDG2M5LKZSV.json","graph_json":"https://pith.science/api/pith-number/PMULYQ76ID3PE7HSDG2M5LKZSV/graph.json","events_json":"https://pith.science/api/pith-number/PMULYQ76ID3PE7HSDG2M5LKZSV/events.json","paper":"https://pith.science/paper/PMULYQ76"},"agent_actions":{"view_html":"https://pith.science/pith/PMULYQ76ID3PE7HSDG2M5LKZSV","download_json":"https://pith.science/pith/PMULYQ76ID3PE7HSDG2M5LKZSV.json","view_paper":"https://pith.science/paper/PMULYQ76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21755&json=true","fetch_graph":"https://pith.science/api/pith-number/PMULYQ76ID3PE7HSDG2M5LKZSV/graph.json","fetch_events":"https://pith.science/api/pith-number/PMULYQ76ID3PE7HSDG2M5LKZSV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMULYQ76ID3PE7HSDG2M5LKZSV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMULYQ76ID3PE7HSDG2M5LKZSV/action/storage_attestation","attest_author":"https://pith.science/pith/PMULYQ76ID3PE7HSDG2M5LKZSV/action/author_attestation","sign_citation":"https://pith.science/pith/PMULYQ76ID3PE7HSDG2M5LKZSV/action/citation_signature","submit_replication":"https://pith.science/pith/PMULYQ76ID3PE7HSDG2M5LKZSV/action/replication_record"}},"created_at":"2026-07-05T11:25:11.226809+00:00","updated_at":"2026-07-05T11:25:11.226809+00:00"}