{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6IOGKYLOGQ6SGOGSX2YSXUVJE4","short_pith_number":"pith:6IOGKYLO","schema_version":"1.0","canonical_sha256":"f21c65616e343d2338d2beb12bd2a92734cf1b8dab4df8492b868e910bdb3bd7","source":{"kind":"arxiv","id":"2608.03052","version":1},"attestation_state":"computed","paper":{"title":"How Should Vision-Language-Action Models Use Proprioceptive State?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"He Zhang, Pengteng Li, Rushi Dai, Weiyu Guo, Yandong Guo, Yiren Zhao, Ziyang Chen, Ziyang Rao","submitted_at":"2026-08-04T03:05:47Z","abstract_excerpt":"Recent Vision-Language-Action (VLA) models almost universally take robot proprioceptive state as input, yet wire it in incompatible ways -- serialized into text prompts, projected into the vision-language prefix, or fed directly to the action expert -- and almost always as a single current frame. Three questions remain open: (1) whether, and on which tasks, current state actually improves closed-loop control; (2) how much state history helps, and whether its benefit reflects genuine temporal variation rather than added conditioning capacity; and (3) where state should enter the model -- the vi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.03052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-08-04T03:05:47Z","cross_cats_sorted":[],"title_canon_sha256":"5b4602b1bcbb7d7fa9d159a109ff53b6104996a7d737ab48df4b855a0d372175","abstract_canon_sha256":"8856a212be875a4fa7342676e6542dbd2fce3c65a02c12970e49c0a2e09ff3ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:45:01.070066Z","signature_b64":"DkKNQATbfSSIVIiDMd+eIkckZU9/xdLZGI0kSzu6Re6z4UicPqYe4+yTKa/W7OxTXpVu2mXDaAYZnDE1W8MVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f21c65616e343d2338d2beb12bd2a92734cf1b8dab4df8492b868e910bdb3bd7","last_reissued_at":"2026-08-05T00:45:01.067448Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:45:01.067448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Should Vision-Language-Action Models Use Proprioceptive State?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"He Zhang, Pengteng Li, Rushi Dai, Weiyu Guo, Yandong Guo, Yiren Zhao, Ziyang Chen, Ziyang Rao","submitted_at":"2026-08-04T03:05:47Z","abstract_excerpt":"Recent Vision-Language-Action (VLA) models almost universally take robot proprioceptive state as input, yet wire it in incompatible ways -- serialized into text prompts, projected into the vision-language prefix, or fed directly to the action expert -- and almost always as a single current frame. Three questions remain open: (1) whether, and on which tasks, current state actually improves closed-loop control; (2) how much state history helps, and whether its benefit reflects genuine temporal variation rather than added conditioning capacity; and (3) where state should enter the model -- the vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03052","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.03052/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.03052","created_at":"2026-08-05T00:45:01.068461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03052v1","created_at":"2026-08-05T00:45:01.068461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03052","created_at":"2026-08-05T00:45:01.068461+00:00"},{"alias_kind":"pith_short_12","alias_value":"6IOGKYLOGQ6S","created_at":"2026-08-05T00:45:01.068461+00:00"},{"alias_kind":"pith_short_16","alias_value":"6IOGKYLOGQ6SGOGS","created_at":"2026-08-05T00:45:01.068461+00:00"},{"alias_kind":"pith_short_8","alias_value":"6IOGKYLO","created_at":"2026-08-05T00:45:01.068461+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6IOGKYLOGQ6SGOGSX2YSXUVJE4","json":"https://pith.science/pith/6IOGKYLOGQ6SGOGSX2YSXUVJE4.json","graph_json":"https://pith.science/api/pith-number/6IOGKYLOGQ6SGOGSX2YSXUVJE4/graph.json","events_json":"https://pith.science/api/pith-number/6IOGKYLOGQ6SGOGSX2YSXUVJE4/events.json","paper":"https://pith.science/paper/6IOGKYLO"},"agent_actions":{"view_html":"https://pith.science/pith/6IOGKYLOGQ6SGOGSX2YSXUVJE4","download_json":"https://pith.science/pith/6IOGKYLOGQ6SGOGSX2YSXUVJE4.json","view_paper":"https://pith.science/paper/6IOGKYLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03052&json=true","fetch_graph":"https://pith.science/api/pith-number/6IOGKYLOGQ6SGOGSX2YSXUVJE4/graph.json","fetch_events":"https://pith.science/api/pith-number/6IOGKYLOGQ6SGOGSX2YSXUVJE4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6IOGKYLOGQ6SGOGSX2YSXUVJE4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6IOGKYLOGQ6SGOGSX2YSXUVJE4/action/storage_attestation","attest_author":"https://pith.science/pith/6IOGKYLOGQ6SGOGSX2YSXUVJE4/action/author_attestation","sign_citation":"https://pith.science/pith/6IOGKYLOGQ6SGOGSX2YSXUVJE4/action/citation_signature","submit_replication":"https://pith.science/pith/6IOGKYLOGQ6SGOGSX2YSXUVJE4/action/replication_record"}},"created_at":"2026-08-05T00:45:01.068461+00:00","updated_at":"2026-08-05T00:45:01.068461+00:00"}