{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:F5765DHDI5QPA3LCLX4RADHMRC","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":"79990fe26eb676272e7d8e95384d47113fb1fae7be8926d5482e3390173e5a72","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-18T00:22:54Z","title_canon_sha256":"20b65a50e04b675f1b1108e7314aa57b223fdbbc401eb63092573fe95c6039d9"},"schema_version":"1.0","source":{"id":"2009.08566","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.08566","created_at":"2026-07-05T01:43:28Z"},{"alias_kind":"arxiv_version","alias_value":"2009.08566v2","created_at":"2026-07-05T01:43:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.08566","created_at":"2026-07-05T01:43:28Z"},{"alias_kind":"pith_short_12","alias_value":"F5765DHDI5QP","created_at":"2026-07-05T01:43:28Z"},{"alias_kind":"pith_short_16","alias_value":"F5765DHDI5QPA3LC","created_at":"2026-07-05T01:43:28Z"},{"alias_kind":"pith_short_8","alias_value":"F5765DHD","created_at":"2026-07-05T01:43:28Z"}],"graph_snapshots":[{"event_id":"sha256:ddfef6298b3e4bbe633a37bca064de6dbbf48a8b0fc18b8059da7180ecf6bd12","target":"graph","created_at":"2026-07-05T01:43:28Z","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/2009.08566/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While progress has been made on the visual question answering leaderboards, models often utilize spurious correlations and priors in datasets under the i.i.d. setting. As such, evaluation on out-of-distribution (OOD) test samples has emerged as a proxy for generalization. In this paper, we present MUTANT, a training paradigm that exposes the model to perceptually similar, yet semantically distinct mutations of the input, to improve OOD generalization, such as the VQA-CP challenge. Under this paradigm, models utilize a consistency-constrained training objective to understand the effect of seman","authors_text":"Chitta Baral, Pratyay Banerjee, Tejas Gokhale, Yezhou Yang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-18T00:22:54Z","title":"MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.08566","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:c3da85b4c0a2c84645c46b4a74972fd33b1bfd2cb466a59badbce34d3eef8351","target":"record","created_at":"2026-07-05T01:43:28Z","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":"79990fe26eb676272e7d8e95384d47113fb1fae7be8926d5482e3390173e5a72","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-18T00:22:54Z","title_canon_sha256":"20b65a50e04b675f1b1108e7314aa57b223fdbbc401eb63092573fe95c6039d9"},"schema_version":"1.0","source":{"id":"2009.08566","kind":"arxiv","version":2}},"canonical_sha256":"2f7fee8ce34760f06d625df9100cec88b887a7941e6dff96d7f71ebf437f151b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f7fee8ce34760f06d625df9100cec88b887a7941e6dff96d7f71ebf437f151b","first_computed_at":"2026-07-05T01:43:28.344916Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:43:28.344916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wsFtPNx6X12TBG9JgrbKPS3/EFY5ZSHbVRFGgQKxfMF1KATX3UMzNnxq7biGtCJrFv2GpQTOMKXYeHfTl7ZpCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:43:28.345416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.08566","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3da85b4c0a2c84645c46b4a74972fd33b1bfd2cb466a59badbce34d3eef8351","sha256:ddfef6298b3e4bbe633a37bca064de6dbbf48a8b0fc18b8059da7180ecf6bd12"],"state_sha256":"4327856666b0be88408fca0049cf36ea2ef827fee06b85444e74e769f39a9e4b"}