{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YPUJMJSIJ4HV72ZWWOZZU3QVWR","short_pith_number":"pith:YPUJMJSI","schema_version":"1.0","canonical_sha256":"c3e89626484f0f5feb36b3b39a6e15b47587442d4949e610c606764df300ff08","source":{"kind":"arxiv","id":"2606.22540","version":1},"attestation_state":"computed","paper":{"title":"PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Li, Feng Chen, Hua Yan, Wenbo Zhang, Xianghui Wang, Yinjie Lei, Zixuan Wang","submitted_at":"2026-06-21T14:54:07Z","abstract_excerpt":"Vision-Language-Action (VLA) models provide a unified paradigm for robotic manipulation, yet their real-world deployment is often bottlenecked by execution efficiency. While existing efforts predominantly focus on compute-centric efficiency to reduce per-step inference latency, the intrinsic \\textbf{policy efficiency} of these models remains largely unexplored. Policy efficiency is fundamentally affected by two factors, namely the effective executable length of predicted action chunks and the total physical steps required to complete a task. These two factors jointly determine the total number"},"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":"2606.22540","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-21T14:54:07Z","cross_cats_sorted":[],"title_canon_sha256":"3c8919acadacac1ead4d2afd9d090414e05d717c8ed7069c557274f465cbab78","abstract_canon_sha256":"c6cac5080f40e473972d1d60e8fddc53f42629e148ea64559760b70f76ddd0c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:41.095464Z","signature_b64":"wNzrWf3OnOPqhs2UFQQD51iTEvmu5MQQkSXmFr+FUt4eoFYXphZxZyharQErcB76mMa6IrK3Y4Eymu70BS9WBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3e89626484f0f5feb36b3b39a6e15b47587442d4949e610c606764df300ff08","last_reissued_at":"2026-06-23T02:13:41.095053Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:41.095053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Li, Feng Chen, Hua Yan, Wenbo Zhang, Xianghui Wang, Yinjie Lei, Zixuan Wang","submitted_at":"2026-06-21T14:54:07Z","abstract_excerpt":"Vision-Language-Action (VLA) models provide a unified paradigm for robotic manipulation, yet their real-world deployment is often bottlenecked by execution efficiency. While existing efforts predominantly focus on compute-centric efficiency to reduce per-step inference latency, the intrinsic \\textbf{policy efficiency} of these models remains largely unexplored. Policy efficiency is fundamentally affected by two factors, namely the effective executable length of predicted action chunks and the total physical steps required to complete a task. These two factors jointly determine the total number"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22540","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/2606.22540/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":"2606.22540","created_at":"2026-06-23T02:13:41.095114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22540v1","created_at":"2026-06-23T02:13:41.095114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22540","created_at":"2026-06-23T02:13:41.095114+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPUJMJSIJ4HV","created_at":"2026-06-23T02:13:41.095114+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPUJMJSIJ4HV72ZW","created_at":"2026-06-23T02:13:41.095114+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPUJMJSI","created_at":"2026-06-23T02:13:41.095114+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/YPUJMJSIJ4HV72ZWWOZZU3QVWR","json":"https://pith.science/pith/YPUJMJSIJ4HV72ZWWOZZU3QVWR.json","graph_json":"https://pith.science/api/pith-number/YPUJMJSIJ4HV72ZWWOZZU3QVWR/graph.json","events_json":"https://pith.science/api/pith-number/YPUJMJSIJ4HV72ZWWOZZU3QVWR/events.json","paper":"https://pith.science/paper/YPUJMJSI"},"agent_actions":{"view_html":"https://pith.science/pith/YPUJMJSIJ4HV72ZWWOZZU3QVWR","download_json":"https://pith.science/pith/YPUJMJSIJ4HV72ZWWOZZU3QVWR.json","view_paper":"https://pith.science/paper/YPUJMJSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22540&json=true","fetch_graph":"https://pith.science/api/pith-number/YPUJMJSIJ4HV72ZWWOZZU3QVWR/graph.json","fetch_events":"https://pith.science/api/pith-number/YPUJMJSIJ4HV72ZWWOZZU3QVWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPUJMJSIJ4HV72ZWWOZZU3QVWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPUJMJSIJ4HV72ZWWOZZU3QVWR/action/storage_attestation","attest_author":"https://pith.science/pith/YPUJMJSIJ4HV72ZWWOZZU3QVWR/action/author_attestation","sign_citation":"https://pith.science/pith/YPUJMJSIJ4HV72ZWWOZZU3QVWR/action/citation_signature","submit_replication":"https://pith.science/pith/YPUJMJSIJ4HV72ZWWOZZU3QVWR/action/replication_record"}},"created_at":"2026-06-23T02:13:41.095114+00:00","updated_at":"2026-06-23T02:13:41.095114+00:00"}