{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RMVDNGSC4HRRFPQ6XBJLSRXC6T","short_pith_number":"pith:RMVDNGSC","schema_version":"1.0","canonical_sha256":"8b2a369a42e1e312be1eb852b946e2f4fb1ba844ab2f0ef2245b58e1a84eb042","source":{"kind":"arxiv","id":"2509.14143","version":2},"attestation_state":"computed","paper":{"title":"CLAW: A Vision-Language-Action Framework for Weight-Aware Robotic Grasping","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Lifeng Zhou, Ran Yang, Yiming Feng, Zijian An","submitted_at":"2025-09-17T16:22:25Z","abstract_excerpt":"Vision-language-action (VLA) models have recently emerged as a promising paradigm for robotic control, enabling end-to-end policies that ground natural language instructions into visuomotor actions. However, current VLAs often struggle to satisfy precise task constraints, such as stopping based on numeric thresholds, since their observation-to-action mappings are implicitly shaped by training data and lack explicit mechanisms for condition monitoring. In this work, we propose CLAW (CLIP-Language-Action for Weight), a framework that decouples condition evaluation from action generation. CLAW le"},"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":"2509.14143","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-17T16:22:25Z","cross_cats_sorted":[],"title_canon_sha256":"285fb9fa9d0b63e9412db0de2fdb051dc71cf2a7df386fba3b5f533d98f4bbf5","abstract_canon_sha256":"bdbf9e5e310fec835995dbd491ce03aa64dc09dea613cc26f3e7866a95d8f4af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:15.135035Z","signature_b64":"DnChGJEXjoy77BEaQaniAg9LDF/novUTf7KGNh1XoYAwSm7a7mEHZ86oLfGAGbHRgtPS0fRYeRbks9hdEcQ0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b2a369a42e1e312be1eb852b946e2f4fb1ba844ab2f0ef2245b58e1a84eb042","last_reissued_at":"2026-06-02T01:03:15.134510Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:15.134510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLAW: A Vision-Language-Action Framework for Weight-Aware Robotic Grasping","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Lifeng Zhou, Ran Yang, Yiming Feng, Zijian An","submitted_at":"2025-09-17T16:22:25Z","abstract_excerpt":"Vision-language-action (VLA) models have recently emerged as a promising paradigm for robotic control, enabling end-to-end policies that ground natural language instructions into visuomotor actions. However, current VLAs often struggle to satisfy precise task constraints, such as stopping based on numeric thresholds, since their observation-to-action mappings are implicitly shaped by training data and lack explicit mechanisms for condition monitoring. In this work, we propose CLAW (CLIP-Language-Action for Weight), a framework that decouples condition evaluation from action generation. CLAW le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.14143","kind":"arxiv","version":2},"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/2509.14143/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":"2509.14143","created_at":"2026-06-02T01:03:15.134592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.14143v2","created_at":"2026-06-02T01:03:15.134592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.14143","created_at":"2026-06-02T01:03:15.134592+00:00"},{"alias_kind":"pith_short_12","alias_value":"RMVDNGSC4HRR","created_at":"2026-06-02T01:03:15.134592+00:00"},{"alias_kind":"pith_short_16","alias_value":"RMVDNGSC4HRRFPQ6","created_at":"2026-06-02T01:03:15.134592+00:00"},{"alias_kind":"pith_short_8","alias_value":"RMVDNGSC","created_at":"2026-06-02T01:03:15.134592+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.02037","citing_title":"VILAS: A VLA-Integrated Low-cost Architecture with Soft Grasping for Robotic Manipulation","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00449","citing_title":"ROG-Grasp: Root-Oriented Geometry for Robotic Grasping and Placement","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02037","citing_title":"VILAS: A VLA-Integrated Low-cost Architecture with Soft Grasping for Robotic Manipulation","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RMVDNGSC4HRRFPQ6XBJLSRXC6T","json":"https://pith.science/pith/RMVDNGSC4HRRFPQ6XBJLSRXC6T.json","graph_json":"https://pith.science/api/pith-number/RMVDNGSC4HRRFPQ6XBJLSRXC6T/graph.json","events_json":"https://pith.science/api/pith-number/RMVDNGSC4HRRFPQ6XBJLSRXC6T/events.json","paper":"https://pith.science/paper/RMVDNGSC"},"agent_actions":{"view_html":"https://pith.science/pith/RMVDNGSC4HRRFPQ6XBJLSRXC6T","download_json":"https://pith.science/pith/RMVDNGSC4HRRFPQ6XBJLSRXC6T.json","view_paper":"https://pith.science/paper/RMVDNGSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.14143&json=true","fetch_graph":"https://pith.science/api/pith-number/RMVDNGSC4HRRFPQ6XBJLSRXC6T/graph.json","fetch_events":"https://pith.science/api/pith-number/RMVDNGSC4HRRFPQ6XBJLSRXC6T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RMVDNGSC4HRRFPQ6XBJLSRXC6T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RMVDNGSC4HRRFPQ6XBJLSRXC6T/action/storage_attestation","attest_author":"https://pith.science/pith/RMVDNGSC4HRRFPQ6XBJLSRXC6T/action/author_attestation","sign_citation":"https://pith.science/pith/RMVDNGSC4HRRFPQ6XBJLSRXC6T/action/citation_signature","submit_replication":"https://pith.science/pith/RMVDNGSC4HRRFPQ6XBJLSRXC6T/action/replication_record"}},"created_at":"2026-06-02T01:03:15.134592+00:00","updated_at":"2026-06-02T01:03:15.134592+00:00"}