{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2PWW7PLKGN745JMGUWN562MYFK","short_pith_number":"pith:2PWW7PLK","schema_version":"1.0","canonical_sha256":"d3ed6fbd6a337fcea586a59bdf69982aa0b8bfb64c08e6909809358ba2045245","source":{"kind":"arxiv","id":"2605.24890","version":1},"attestation_state":"computed","paper":{"title":"QuoVLA: Quotient Space for Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Duan, Jungong Han, Xuan Wang, Yinan Wu","submitted_at":"2026-05-24T06:28:53Z","abstract_excerpt":"Vision-Language-Action (VLA) models commonly adapt pretrained Vision-Language Models (VLMs) to robot control by mapping visual observations and language instructions to continuous actions. Existing approaches typically take an action-insufficiency view, assuming that pretrained VLM latents either lack directly usable action information or should be shielded from action-learning signals. Against this view, our \\textit{Quotient Theory for VLA} shows that pretrained VLM latents are not action-insufficient but action-sufficient: they already contain the information needed for control, yet remain o"},"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":"2605.24890","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T06:28:53Z","cross_cats_sorted":[],"title_canon_sha256":"84023be06b2daea7dea86d0e050ed8dc546e13efe27a6dbb6dc8fd0b6bc77423","abstract_canon_sha256":"69657f9613a808fc644bab0099534362ea137ec3e5f3b278b4b89d3df1c6f515"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:04:03.741454Z","signature_b64":"WhVOwG8BxIBHmyijQCXWKfJmuYM4zWfIK6Ck975KSWTU0Nn+fzn2hIleUuFeWO15WQhivivcpV/g1NlRjmQtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3ed6fbd6a337fcea586a59bdf69982aa0b8bfb64c08e6909809358ba2045245","last_reissued_at":"2026-05-26T01:04:03.740664Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:04:03.740664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QuoVLA: Quotient Space for Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Duan, Jungong Han, Xuan Wang, Yinan Wu","submitted_at":"2026-05-24T06:28:53Z","abstract_excerpt":"Vision-Language-Action (VLA) models commonly adapt pretrained Vision-Language Models (VLMs) to robot control by mapping visual observations and language instructions to continuous actions. Existing approaches typically take an action-insufficiency view, assuming that pretrained VLM latents either lack directly usable action information or should be shielded from action-learning signals. Against this view, our \\textit{Quotient Theory for VLA} shows that pretrained VLM latents are not action-insufficient but action-sufficient: they already contain the information needed for control, yet remain o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24890","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/2605.24890/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":"2605.24890","created_at":"2026-05-26T01:04:03.740796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24890v1","created_at":"2026-05-26T01:04:03.740796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24890","created_at":"2026-05-26T01:04:03.740796+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PWW7PLKGN74","created_at":"2026-05-26T01:04:03.740796+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PWW7PLKGN745JMG","created_at":"2026-05-26T01:04:03.740796+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PWW7PLK","created_at":"2026-05-26T01:04:03.740796+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/2PWW7PLKGN745JMGUWN562MYFK","json":"https://pith.science/pith/2PWW7PLKGN745JMGUWN562MYFK.json","graph_json":"https://pith.science/api/pith-number/2PWW7PLKGN745JMGUWN562MYFK/graph.json","events_json":"https://pith.science/api/pith-number/2PWW7PLKGN745JMGUWN562MYFK/events.json","paper":"https://pith.science/paper/2PWW7PLK"},"agent_actions":{"view_html":"https://pith.science/pith/2PWW7PLKGN745JMGUWN562MYFK","download_json":"https://pith.science/pith/2PWW7PLKGN745JMGUWN562MYFK.json","view_paper":"https://pith.science/paper/2PWW7PLK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24890&json=true","fetch_graph":"https://pith.science/api/pith-number/2PWW7PLKGN745JMGUWN562MYFK/graph.json","fetch_events":"https://pith.science/api/pith-number/2PWW7PLKGN745JMGUWN562MYFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PWW7PLKGN745JMGUWN562MYFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PWW7PLKGN745JMGUWN562MYFK/action/storage_attestation","attest_author":"https://pith.science/pith/2PWW7PLKGN745JMGUWN562MYFK/action/author_attestation","sign_citation":"https://pith.science/pith/2PWW7PLKGN745JMGUWN562MYFK/action/citation_signature","submit_replication":"https://pith.science/pith/2PWW7PLKGN745JMGUWN562MYFK/action/replication_record"}},"created_at":"2026-05-26T01:04:03.740796+00:00","updated_at":"2026-05-26T01:04:03.740796+00:00"}