{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TZGEQSTWSUDKRERPB5HIYALT22","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ab0e0af33f936e2c63e77641aa3c9249aff7fed98593e42be7903ad7bf524a05","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-25T09:38:11Z","title_canon_sha256":"5f8c0cda50e39bf7c6ce581b452d62ecdd585ec22e5d5474ae7b8f4c9603421a"},"schema_version":"1.0","source":{"id":"2606.26801","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26801","created_at":"2026-06-26T01:16:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26801v1","created_at":"2026-06-26T01:16:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26801","created_at":"2026-06-26T01:16:00Z"},{"alias_kind":"pith_short_12","alias_value":"TZGEQSTWSUDK","created_at":"2026-06-26T01:16:00Z"},{"alias_kind":"pith_short_16","alias_value":"TZGEQSTWSUDKRERP","created_at":"2026-06-26T01:16:00Z"},{"alias_kind":"pith_short_8","alias_value":"TZGEQSTW","created_at":"2026-06-26T01:16:00Z"}],"graph_snapshots":[{"event_id":"sha256:2a88d3ce09dc990d075ee4e7c2edaa30274ab3b5eed80fd0b2cbfa9adbbd273c","target":"graph","created_at":"2026-06-26T01:16:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.26801/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jiabing Yang, Kai Wang, Liang Wang, Peiyan Li, Qisen Ma, Yan Huang, Yixiang Chen, Yuan Xu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-25T09:38:11Z","title":"Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26801","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a524088d338802837670fec616546bfd29876373068fdce56b4ba123ca1502ec","target":"record","created_at":"2026-06-26T01:16:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ab0e0af33f936e2c63e77641aa3c9249aff7fed98593e42be7903ad7bf524a05","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-25T09:38:11Z","title_canon_sha256":"5f8c0cda50e39bf7c6ce581b452d62ecdd585ec22e5d5474ae7b8f4c9603421a"},"schema_version":"1.0","source":{"id":"2606.26801","kind":"arxiv","version":1}},"canonical_sha256":"9e4c484a769506a8922f0f4e8c0173d6ba54ea70db80f6671b1b8023a86ec611","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e4c484a769506a8922f0f4e8c0173d6ba54ea70db80f6671b1b8023a86ec611","first_computed_at":"2026-06-26T01:16:00.165033Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:16:00.165033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cAX24MylKrYWT2KPFy1pkyqBFv8tSIYJEV906yeODIaJ/6KxJD5r39+IgrnIM3VZw8XYPm6nEMgKlzaSTd8hDg==","signature_status":"signed_v1","signed_at":"2026-06-26T01:16:00.165500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.26801","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a524088d338802837670fec616546bfd29876373068fdce56b4ba123ca1502ec","sha256:2a88d3ce09dc990d075ee4e7c2edaa30274ab3b5eed80fd0b2cbfa9adbbd273c"],"state_sha256":"b5d10c547343af0e472a7c10c2d2ed8c4e92f9af1fa3cda9bf8c37c586396da3"}