{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NE73SSS6UJY26RLFVV6FVQOIA4","short_pith_number":"pith:NE73SSS6","schema_version":"1.0","canonical_sha256":"693fb94a5ea271af4565ad7c5ac1c80736409c884c3535ffed034d991d89ca72","source":{"kind":"arxiv","id":"2508.10259","version":1},"attestation_state":"computed","paper":{"title":"Leveraging OS-Level Primitives for Robotic Action Management","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.OS","authors_text":"Bin Xu, Boyang Li, Erhu Feng, Haibo Chen, Jinyu Gu, Wenxin Zheng","submitted_at":"2025-08-14T00:57:58Z","abstract_excerpt":"End-to-end imitation learning frameworks (e.g., VLA) are increasingly prominent in robotics, as they enable rapid task transfer by learning directly from perception to control, eliminating the need for complex hand-crafted features. However, even when employing SOTA VLA-based models, they still exhibit limited generalization capabilities and suboptimal action efficiency, due to the constraints imposed by insufficient robotic training datasets. In addition to addressing this problem using model-based approaches, we observe that robotic action slices, which consist of contiguous action steps, ex"},"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":"2508.10259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.OS","submitted_at":"2025-08-14T00:57:58Z","cross_cats_sorted":[],"title_canon_sha256":"f27a03fd9902c1b69b8633f3b17f6a4f42a7f51b55eb242ed0e055f9da1b291a","abstract_canon_sha256":"d0962840b377586363ed61862b50cc800a36fd31489f47106d34260192ae4313"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:52.336802Z","signature_b64":"/PL/NpKvPoXrT2TY30O+F59MufFIBPhhy5QlRzi63e+MFuP2tkZrlHia5LdldOnlDr2UeHi+0wxaT5kEVdhODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"693fb94a5ea271af4565ad7c5ac1c80736409c884c3535ffed034d991d89ca72","last_reissued_at":"2026-07-05T11:53:52.336245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:52.336245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging OS-Level Primitives for Robotic Action Management","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.OS","authors_text":"Bin Xu, Boyang Li, Erhu Feng, Haibo Chen, Jinyu Gu, Wenxin Zheng","submitted_at":"2025-08-14T00:57:58Z","abstract_excerpt":"End-to-end imitation learning frameworks (e.g., VLA) are increasingly prominent in robotics, as they enable rapid task transfer by learning directly from perception to control, eliminating the need for complex hand-crafted features. However, even when employing SOTA VLA-based models, they still exhibit limited generalization capabilities and suboptimal action efficiency, due to the constraints imposed by insufficient robotic training datasets. In addition to addressing this problem using model-based approaches, we observe that robotic action slices, which consist of contiguous action steps, ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10259","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/2508.10259/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":"2508.10259","created_at":"2026-07-05T11:53:52.336326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10259v1","created_at":"2026-07-05T11:53:52.336326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10259","created_at":"2026-07-05T11:53:52.336326+00:00"},{"alias_kind":"pith_short_12","alias_value":"NE73SSS6UJY2","created_at":"2026-07-05T11:53:52.336326+00:00"},{"alias_kind":"pith_short_16","alias_value":"NE73SSS6UJY26RLF","created_at":"2026-07-05T11:53:52.336326+00:00"},{"alias_kind":"pith_short_8","alias_value":"NE73SSS6","created_at":"2026-07-05T11:53:52.336326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22540","citing_title":"PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01581","citing_title":"KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07381","citing_title":"Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NE73SSS6UJY26RLFVV6FVQOIA4","json":"https://pith.science/pith/NE73SSS6UJY26RLFVV6FVQOIA4.json","graph_json":"https://pith.science/api/pith-number/NE73SSS6UJY26RLFVV6FVQOIA4/graph.json","events_json":"https://pith.science/api/pith-number/NE73SSS6UJY26RLFVV6FVQOIA4/events.json","paper":"https://pith.science/paper/NE73SSS6"},"agent_actions":{"view_html":"https://pith.science/pith/NE73SSS6UJY26RLFVV6FVQOIA4","download_json":"https://pith.science/pith/NE73SSS6UJY26RLFVV6FVQOIA4.json","view_paper":"https://pith.science/paper/NE73SSS6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10259&json=true","fetch_graph":"https://pith.science/api/pith-number/NE73SSS6UJY26RLFVV6FVQOIA4/graph.json","fetch_events":"https://pith.science/api/pith-number/NE73SSS6UJY26RLFVV6FVQOIA4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NE73SSS6UJY26RLFVV6FVQOIA4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NE73SSS6UJY26RLFVV6FVQOIA4/action/storage_attestation","attest_author":"https://pith.science/pith/NE73SSS6UJY26RLFVV6FVQOIA4/action/author_attestation","sign_citation":"https://pith.science/pith/NE73SSS6UJY26RLFVV6FVQOIA4/action/citation_signature","submit_replication":"https://pith.science/pith/NE73SSS6UJY26RLFVV6FVQOIA4/action/replication_record"}},"created_at":"2026-07-05T11:53:52.336326+00:00","updated_at":"2026-07-05T11:53:52.336326+00:00"}