{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PMULYQ76ID3PE7HSDG2M5LKZSV","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":"d74207508c193b1cda6efbc97320b7060f2d63faec9dea38c13cd2c0053608e3","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T20:44:44Z","title_canon_sha256":"fed97e0eecd952b0c0762ac647add5fd41213dbd543df3861ca9aaecfdf12d0e"},"schema_version":"1.0","source":{"id":"2505.21755","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21755","created_at":"2026-07-05T11:25:11Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21755v2","created_at":"2026-07-05T11:25:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21755","created_at":"2026-07-05T11:25:11Z"},{"alias_kind":"pith_short_12","alias_value":"PMULYQ76ID3P","created_at":"2026-07-05T11:25:11Z"},{"alias_kind":"pith_short_16","alias_value":"PMULYQ76ID3PE7HS","created_at":"2026-07-05T11:25:11Z"},{"alias_kind":"pith_short_8","alias_value":"PMULYQ76","created_at":"2026-07-05T11:25:11Z"}],"graph_snapshots":[{"event_id":"sha256:0104a8f564b65236c93f804564ba7c245495e994a78357abeb488e4a263da747","target":"graph","created_at":"2026-07-05T11:25:11Z","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/2505.21755/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Brisa Maneechotesuwan, Chengyue Huang, Shivang Chopra, Zsolt Kira","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T20:44:44Z","title":"FRAMES-VQA: Benchmarking Fine-Tuning Robustness across Multi-Modal Shifts in Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21755","kind":"arxiv","version":2},"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:ae4f8547e808a3852d8a80a922ecddb780b710f64bed2cfa2a8b6658253ba5a9","target":"record","created_at":"2026-07-05T11:25:11Z","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":"d74207508c193b1cda6efbc97320b7060f2d63faec9dea38c13cd2c0053608e3","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T20:44:44Z","title_canon_sha256":"fed97e0eecd952b0c0762ac647add5fd41213dbd543df3861ca9aaecfdf12d0e"},"schema_version":"1.0","source":{"id":"2505.21755","kind":"arxiv","version":2}},"canonical_sha256":"7b28bc43fe40f6f27cf219b4cead59954291e4f24862db06e3aaee545ac91f48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b28bc43fe40f6f27cf219b4cead59954291e4f24862db06e3aaee545ac91f48","first_computed_at":"2026-07-05T11:25:11.226750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:11.226750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zqRGFxoLjsc1OU8a1AtA9yzFEYBox7nQzlHd6sdnx+AhYUQRzRPwhQ+W0GtN3aJjFd+kqfCvxgkxn/T8O1X/CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:11.227245Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21755","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae4f8547e808a3852d8a80a922ecddb780b710f64bed2cfa2a8b6658253ba5a9","sha256:0104a8f564b65236c93f804564ba7c245495e994a78357abeb488e4a263da747"],"state_sha256":"8ea57b118b5774f32001a0d5beaec596a408fe1997884fc0a30f9da642da415f"}