{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7OCYAB4WD25OUEDZR45A47D4GR","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":"0164f6dd6ba8922531d7447fb081bce90c2a5b26d4b17170edfc6b9e07a8a16d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T02:58:41Z","title_canon_sha256":"9e48b8210f4459a953aee776c0bbfebcda2bca25f035d61897cd98545f3d7ae9"},"schema_version":"1.0","source":{"id":"2608.04396","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04396","created_at":"2026-08-06T01:34:54Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04396v1","created_at":"2026-08-06T01:34:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04396","created_at":"2026-08-06T01:34:54Z"},{"alias_kind":"pith_short_12","alias_value":"7OCYAB4WD25O","created_at":"2026-08-06T01:34:54Z"},{"alias_kind":"pith_short_16","alias_value":"7OCYAB4WD25OUEDZ","created_at":"2026-08-06T01:34:54Z"},{"alias_kind":"pith_short_8","alias_value":"7OCYAB4W","created_at":"2026-08-06T01:34:54Z"}],"graph_snapshots":[{"event_id":"sha256:31821dd4b34ab1f9dbe3ca06de4284038e542b6f43499819d440343ca0ad5b39","target":"graph","created_at":"2026-08-06T01:34:54Z","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/2608.04396/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models have driven significant progress in robotic manipulation, yet they fundamentally struggle with the vision-override phenomenon. Driven by the severe modality imbalance between dense visual streams and sparse linguistic instructions, VLAs frequently fall prey to causal confusion. Instead of treating language as the primary causal driver, the policy entirely bypasses the original instruction by overfitting to spurious visual confounders, such as prominent objects or familiar layouts. To systematically alleviate this bias, we formalize the process of action gene","authors_text":"Haoran Duan, Jungong Han, Yan Zhang, Yinan Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T02:58:41Z","title":"CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Intervention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04396","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":"sha256:63a189906161f09f39ae9e68c41293e33c06368429e1dce2f5c096154c5efded","target":"record","created_at":"2026-08-06T01:34:54Z","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":"0164f6dd6ba8922531d7447fb081bce90c2a5b26d4b17170edfc6b9e07a8a16d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T02:58:41Z","title_canon_sha256":"9e48b8210f4459a953aee776c0bbfebcda2bca25f035d61897cd98545f3d7ae9"},"schema_version":"1.0","source":{"id":"2608.04396","kind":"arxiv","version":1}},"canonical_sha256":"fb858007961ebaea10798f3a0e7c7c34442ed92618261d83c474b0c8d90785e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb858007961ebaea10798f3a0e7c7c34442ed92618261d83c474b0c8d90785e5","first_computed_at":"2026-08-06T01:34:54.026565Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:34:54.026565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uoX/k/EDK+CJXebi/xz7rUgJBp4LzOx0R2g2CyAqN0eMJ8Wvq3Axcc+1EAC0lnxyyDAq8tOKG8PutWgVM0fuBg==","signature_status":"signed_v1","signed_at":"2026-08-06T01:34:54.028146Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.04396","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63a189906161f09f39ae9e68c41293e33c06368429e1dce2f5c096154c5efded","sha256:31821dd4b34ab1f9dbe3ca06de4284038e542b6f43499819d440343ca0ad5b39"],"state_sha256":"8a9df7de0ffe4ee5220eacf4feb05dac94d7aad0536dda1b4c50669cb8ede853"}