{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TZGEQSTWSUDKRERPB5HIYALT22","short_pith_number":"pith:TZGEQSTW","schema_version":"1.0","canonical_sha256":"9e4c484a769506a8922f0f4e8c0173d6ba54ea70db80f6671b1b8023a86ec611","source":{"kind":"arxiv","id":"2606.26801","version":1},"attestation_state":"computed","paper":{"title":"Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Jiabing Yang, Kai Wang, Liang Wang, Peiyan Li, Qisen Ma, Yan Huang, Yixiang Chen, Yuan Xu","submitted_at":"2026-06-25T09:38:11Z","abstract_excerpt":"Vision-Language-Action (VLA) models have shown strong potential for generalizable robotic manipulation. During fine-tuning, however, action supervision applies equally across all timesteps, without structured supervision on which manipulation stage the robot is in or what the next gripper-event target should be. This causes failures to concentrate around challenging gripper-event transitions. To address this, we propose StaKe, a plug-in auxiliary supervision framework that automatically derives two complementary signals from demonstration gripper states without manual annotation: a stage class"},"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":"2606.26801","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-25T09:38:11Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5f8c0cda50e39bf7c6ce581b452d62ecdd585ec22e5d5474ae7b8f4c9603421a","abstract_canon_sha256":"ab0e0af33f936e2c63e77641aa3c9249aff7fed98593e42be7903ad7bf524a05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:00.165500Z","signature_b64":"cAX24MylKrYWT2KPFy1pkyqBFv8tSIYJEV906yeODIaJ/6KxJD5r39+IgrnIM3VZw8XYPm6nEMgKlzaSTd8hDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e4c484a769506a8922f0f4e8c0173d6ba54ea70db80f6671b1b8023a86ec611","last_reissued_at":"2026-06-26T01:16:00.165033Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:00.165033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Jiabing Yang, Kai Wang, Liang Wang, Peiyan Li, Qisen Ma, Yan Huang, Yixiang Chen, Yuan Xu","submitted_at":"2026-06-25T09:38:11Z","abstract_excerpt":"Vision-Language-Action (VLA) models have shown strong potential for generalizable robotic manipulation. During fine-tuning, however, action supervision applies equally across all timesteps, without structured supervision on which manipulation stage the robot is in or what the next gripper-event target should be. This causes failures to concentrate around challenging gripper-event transitions. To address this, we propose StaKe, a plug-in auxiliary supervision framework that automatically derives two complementary signals from demonstration gripper states without manual annotation: a stage class"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26801","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/2606.26801/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":"2606.26801","created_at":"2026-06-26T01:16:00.165101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26801v1","created_at":"2026-06-26T01:16:00.165101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26801","created_at":"2026-06-26T01:16:00.165101+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZGEQSTWSUDK","created_at":"2026-06-26T01:16:00.165101+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZGEQSTWSUDKRERP","created_at":"2026-06-26T01:16:00.165101+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZGEQSTW","created_at":"2026-06-26T01:16:00.165101+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/TZGEQSTWSUDKRERPB5HIYALT22","json":"https://pith.science/pith/TZGEQSTWSUDKRERPB5HIYALT22.json","graph_json":"https://pith.science/api/pith-number/TZGEQSTWSUDKRERPB5HIYALT22/graph.json","events_json":"https://pith.science/api/pith-number/TZGEQSTWSUDKRERPB5HIYALT22/events.json","paper":"https://pith.science/paper/TZGEQSTW"},"agent_actions":{"view_html":"https://pith.science/pith/TZGEQSTWSUDKRERPB5HIYALT22","download_json":"https://pith.science/pith/TZGEQSTWSUDKRERPB5HIYALT22.json","view_paper":"https://pith.science/paper/TZGEQSTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26801&json=true","fetch_graph":"https://pith.science/api/pith-number/TZGEQSTWSUDKRERPB5HIYALT22/graph.json","fetch_events":"https://pith.science/api/pith-number/TZGEQSTWSUDKRERPB5HIYALT22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZGEQSTWSUDKRERPB5HIYALT22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZGEQSTWSUDKRERPB5HIYALT22/action/storage_attestation","attest_author":"https://pith.science/pith/TZGEQSTWSUDKRERPB5HIYALT22/action/author_attestation","sign_citation":"https://pith.science/pith/TZGEQSTWSUDKRERPB5HIYALT22/action/citation_signature","submit_replication":"https://pith.science/pith/TZGEQSTWSUDKRERPB5HIYALT22/action/replication_record"}},"created_at":"2026-06-26T01:16:00.165101+00:00","updated_at":"2026-06-26T01:16:00.165101+00:00"}