{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ADW757Y4EJSFNHRABIXZZYAKUX","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":"6d487718f0d5b219a44862db25319bfedafa361b34066f1755d06e901a42f97e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T12:51:35Z","title_canon_sha256":"7923c47f09844c1909baf364e4a254b46ed055ac3c78c7e8ba1f7bd068cc7989"},"schema_version":"1.0","source":{"id":"2605.25802","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25802","created_at":"2026-05-26T02:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25802v1","created_at":"2026-05-26T02:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25802","created_at":"2026-05-26T02:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"ADW757Y4EJSF","created_at":"2026-05-26T02:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"ADW757Y4EJSFNHRA","created_at":"2026-05-26T02:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"ADW757Y4","created_at":"2026-05-26T02:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:fea7cb6ecefad86adb06c612f76f27aa2e0f91cdcc687aa952099776fef697a5","target":"graph","created_at":"2026-05-26T02:05:12Z","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/2605.25802/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models widely adopt pretrained Vision-Language Models (VLMs) as policy backbones, yet it remains unclear what kind of pretrained VLM representation is useful as a VLA initialization. In this paper, we study VLA initialization as a controlled representation-design problem along three axes: capability-level embodied VQA supervision, parameter-update strategy, and robot-data pretraining. Our experiments show that the original pretrained VLM representation is a key source of action performance. However, embodied VQA adaptation does not yield uniform gains: its benefit ","authors_text":"Hao Li, Hongsheng Li, Jianbo Liu, Ruichuan An, Siyuan Huang, Tingwei Chen, Weifeng Lin, Xinyu Wei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T12:51:35Z","title":"Rethinking VLM Representation for VLA Initialization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25802","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":"sha256:0568c8ac0d093d7a1e24dc1636c585901b333fa7c268d2a29b9e002f1bffa5a3","target":"record","created_at":"2026-05-26T02:05:12Z","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":"6d487718f0d5b219a44862db25319bfedafa361b34066f1755d06e901a42f97e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T12:51:35Z","title_canon_sha256":"7923c47f09844c1909baf364e4a254b46ed055ac3c78c7e8ba1f7bd068cc7989"},"schema_version":"1.0","source":{"id":"2605.25802","kind":"arxiv","version":1}},"canonical_sha256":"00edfeff1c2264569e200a2f9ce00aa5c8d6bf25c3c20ed79ed11dbd754fec12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00edfeff1c2264569e200a2f9ce00aa5c8d6bf25c3c20ed79ed11dbd754fec12","first_computed_at":"2026-05-26T02:05:12.442210Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:12.442210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g4iSAVWA3hQc/2pnCUlx+C4wy6CM3DHI0AwzGWcyHj82WbaPji70Uuht4J+zd5RliTb9SY8WTWYhZqmzuwXxAQ==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:12.443414Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25802","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0568c8ac0d093d7a1e24dc1636c585901b333fa7c268d2a29b9e002f1bffa5a3","sha256:fea7cb6ecefad86adb06c612f76f27aa2e0f91cdcc687aa952099776fef697a5"],"state_sha256":"55fe49da9c819ea5d7c27bd1816c8cf9ca46e0273511b15f8c6e139c0888c81d"}