{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HKIK7EMP3XQ2PUC25AE3H26PUC","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":"c79e9ce24803fa462447e2b9cf7b700d424d3029e7d7a537e88028ad8f9640f7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T08:45:37Z","title_canon_sha256":"c17cb96fe3caa252142af322a234f45bf3b0931584957a0d0863dddbeb1f706c"},"schema_version":"1.0","source":{"id":"2605.15735","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15735","created_at":"2026-05-20T00:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15735v2","created_at":"2026-05-20T00:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15735","created_at":"2026-05-20T00:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"HKIK7EMP3XQ2","created_at":"2026-05-20T00:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"HKIK7EMP3XQ2PUC2","created_at":"2026-05-20T00:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"HKIK7EMP","created_at":"2026-05-20T00:04:38Z"}],"graph_snapshots":[{"event_id":"sha256:be29d1a96cb2ed2638cb14f4996a7a69c64088dece6d73ee2a85a155784b36a8","target":"graph","created_at":"2026-05-20T00:04:38Z","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/2605.15735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision--language--action (VLA) models are typically built by fine-tuning a pretrained vision--language model (VLM) on action data. However, we show that this standard recipe systematically erodes the VLM's multimodal competence, a side effect we call the embodiment tax. But do VLAs have to forget? Inspired by the two-stream organization of biological vision, we trace this degradation to a structural bottleneck: current VLAs ask a single encoder to support both language-grounded semantics and control-relevant visual features, whereas biological vision separates recognition and visuomotor contro","authors_text":"Hongbin Xu, Jianke Zhang, Jianyu Chen, Tian Lan, Xiaoyu Chen, Yanjiang Guo, Yuanfei Luo, Yucheng Hu, Ziyang Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T08:45:37Z","title":"UAM: A Dual-Stream Perspective on Forgetting in VLA Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15735","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":"sha256:01f3494a108b028781b0b61cec34079c7b71374f29a7f05efe9699685847d25b","target":"record","created_at":"2026-05-20T00:04:38Z","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":"c79e9ce24803fa462447e2b9cf7b700d424d3029e7d7a537e88028ad8f9640f7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-15T08:45:37Z","title_canon_sha256":"c17cb96fe3caa252142af322a234f45bf3b0931584957a0d0863dddbeb1f706c"},"schema_version":"1.0","source":{"id":"2605.15735","kind":"arxiv","version":2}},"canonical_sha256":"3a90af918fdde1a7d05ae809b3ebcfa0a06f5faf9e806000468895117dcea8d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a90af918fdde1a7d05ae809b3ebcfa0a06f5faf9e806000468895117dcea8d2","first_computed_at":"2026-05-20T00:04:38.427703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:38.427703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"be3YGjRYdo1kKO4Hs/bGmGjGl2kEoEt8u+aNhJ5mW2veJyCKS07TWGdheCxh+riB7AXdQTufbxsiMdslZ8xlBg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:38.428720Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15735","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01f3494a108b028781b0b61cec34079c7b71374f29a7f05efe9699685847d25b","sha256:be29d1a96cb2ed2638cb14f4996a7a69c64088dece6d73ee2a85a155784b36a8"],"state_sha256":"045ad2c12009b3033635818252641313ba095c92060ec91d1b68e256e2ef255b"}