{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GILP2EPZTEADYCJEVF4B4GGYEY","short_pith_number":"pith:GILP2EPZ","schema_version":"1.0","canonical_sha256":"3216fd11f999003c0924a9781e18d8260c3872c13420e2a4ec2663d79fe4d5e7","source":{"kind":"arxiv","id":"2606.21493","version":1},"attestation_state":"computed","paper":{"title":"Semi-Supervised Vision-Language-Action Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.ET"],"primary_cat":"cs.CV","authors_text":"Hongyang He, Jiuming Liu, Victor Sanchez","submitted_at":"2026-06-19T14:42:52Z","abstract_excerpt":"Vision-Language-Action (VLA) models enable robots to predict actions directly from visual observations and language instructions, but adapting them to new environments still depends on costly action-labeled demonstrations. To reduce this dependence, we study semi-supervised VLA adaptation under limited supervision signals, where only a small portion of trajectories contain robot actions and the remaining trajectories provide action-unlabeled vision-language observations. Unlike standard semi-supervised learning, the missing supervision is an embodied action signal that must be visually grounde"},"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":"2606.21493","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-19T14:42:52Z","cross_cats_sorted":["cs.ET"],"title_canon_sha256":"4ee6dce72a89636b3612d76dea2143a4b98ea7402b3926808a2cc7a4a916c5cf","abstract_canon_sha256":"c35f2e87cb6cbe6071690160507d0ad2d4a6e4caec3fef14da0b1044ec5c55ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:12.309975Z","signature_b64":"YLPByFX7uwUE9Dtr2tFH5MSN4MXp6jFxZ2kM17mibOyZ5TnsCdd7n4HkC8OTresWJSYzvvA/vXJ+EYSuScyGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3216fd11f999003c0924a9781e18d8260c3872c13420e2a4ec2663d79fe4d5e7","last_reissued_at":"2026-06-23T01:13:12.309436Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:12.309436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-Supervised Vision-Language-Action Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.ET"],"primary_cat":"cs.CV","authors_text":"Hongyang He, Jiuming Liu, Victor Sanchez","submitted_at":"2026-06-19T14:42:52Z","abstract_excerpt":"Vision-Language-Action (VLA) models enable robots to predict actions directly from visual observations and language instructions, but adapting them to new environments still depends on costly action-labeled demonstrations. To reduce this dependence, we study semi-supervised VLA adaptation under limited supervision signals, where only a small portion of trajectories contain robot actions and the remaining trajectories provide action-unlabeled vision-language observations. Unlike standard semi-supervised learning, the missing supervision is an embodied action signal that must be visually grounde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21493","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/2606.21493/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":"2606.21493","created_at":"2026-06-23T01:13:12.309506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21493v1","created_at":"2026-06-23T01:13:12.309506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21493","created_at":"2026-06-23T01:13:12.309506+00:00"},{"alias_kind":"pith_short_12","alias_value":"GILP2EPZTEAD","created_at":"2026-06-23T01:13:12.309506+00:00"},{"alias_kind":"pith_short_16","alias_value":"GILP2EPZTEADYCJE","created_at":"2026-06-23T01:13:12.309506+00:00"},{"alias_kind":"pith_short_8","alias_value":"GILP2EPZ","created_at":"2026-06-23T01:13:12.309506+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/GILP2EPZTEADYCJEVF4B4GGYEY","json":"https://pith.science/pith/GILP2EPZTEADYCJEVF4B4GGYEY.json","graph_json":"https://pith.science/api/pith-number/GILP2EPZTEADYCJEVF4B4GGYEY/graph.json","events_json":"https://pith.science/api/pith-number/GILP2EPZTEADYCJEVF4B4GGYEY/events.json","paper":"https://pith.science/paper/GILP2EPZ"},"agent_actions":{"view_html":"https://pith.science/pith/GILP2EPZTEADYCJEVF4B4GGYEY","download_json":"https://pith.science/pith/GILP2EPZTEADYCJEVF4B4GGYEY.json","view_paper":"https://pith.science/paper/GILP2EPZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21493&json=true","fetch_graph":"https://pith.science/api/pith-number/GILP2EPZTEADYCJEVF4B4GGYEY/graph.json","fetch_events":"https://pith.science/api/pith-number/GILP2EPZTEADYCJEVF4B4GGYEY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GILP2EPZTEADYCJEVF4B4GGYEY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GILP2EPZTEADYCJEVF4B4GGYEY/action/storage_attestation","attest_author":"https://pith.science/pith/GILP2EPZTEADYCJEVF4B4GGYEY/action/author_attestation","sign_citation":"https://pith.science/pith/GILP2EPZTEADYCJEVF4B4GGYEY/action/citation_signature","submit_replication":"https://pith.science/pith/GILP2EPZTEADYCJEVF4B4GGYEY/action/replication_record"}},"created_at":"2026-06-23T01:13:12.309506+00:00","updated_at":"2026-06-23T01:13:12.309506+00:00"}