{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ML4WTEX5SIQ2MP6CZTK5ROTTU4","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":"bebd9acdd92cecc5238596eaff7ce00078a6f2b1afb6c06a49198ff88d35ea17","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T17:21:58Z","title_canon_sha256":"d67629589ac47d7c36e18e83f982e853bd8aabca27c5a7408551d6a6eb5f823a"},"schema_version":"1.0","source":{"id":"2503.16365","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.16365","created_at":"2026-07-05T12:10:56Z"},{"alias_kind":"arxiv_version","alias_value":"2503.16365v2","created_at":"2026-07-05T12:10:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16365","created_at":"2026-07-05T12:10:56Z"},{"alias_kind":"pith_short_12","alias_value":"ML4WTEX5SIQ2","created_at":"2026-07-05T12:10:56Z"},{"alias_kind":"pith_short_16","alias_value":"ML4WTEX5SIQ2MP6C","created_at":"2026-07-05T12:10:56Z"},{"alias_kind":"pith_short_8","alias_value":"ML4WTEX5","created_at":"2026-07-05T12:10:56Z"}],"graph_snapshots":[{"event_id":"sha256:61b4b11241420f6a9878fdf1deb3267ca2782e39c2d5b1fb218e0bafbb36cf7a","target":"graph","created_at":"2026-07-05T12:10:56Z","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/2503.16365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, action-based decision-making in open-world environments has gained significant attention. Visual Language Action (VLA) models, pretrained on large-scale web datasets, have shown promise in decision-making tasks. However, previous work has primarily focused on action post-training, often neglecting enhancements to the foundational model itself. In response, we introduce a novel approach, Act from Visual Language Post-Training, which refines Visual Language Models (VLMs) through visual and linguistic guidance in a self-supervised manner. This enhancement improves the models' capabiliti","authors_text":"Kaichen He, Muyao Li, Xiaojian Ma, Yitao Liang, Zihao Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T17:21:58Z","title":"JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16365","kind":"arxiv","version":2},"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":"sha256:83450e283d8d522c0695c0d3267aac384336243bc0f371f3b4b85d6f465d22b7","target":"record","created_at":"2026-07-05T12:10:56Z","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":"bebd9acdd92cecc5238596eaff7ce00078a6f2b1afb6c06a49198ff88d35ea17","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T17:21:58Z","title_canon_sha256":"d67629589ac47d7c36e18e83f982e853bd8aabca27c5a7408551d6a6eb5f823a"},"schema_version":"1.0","source":{"id":"2503.16365","kind":"arxiv","version":2}},"canonical_sha256":"62f96992fd9221a63fc2ccd5d8ba73a7061186b55956ee86b954ac0e2f8f98dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62f96992fd9221a63fc2ccd5d8ba73a7061186b55956ee86b954ac0e2f8f98dc","first_computed_at":"2026-07-05T12:10:56.460974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:10:56.460974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iceuyfN+YUGYuEUSOirbG/m6xgHSg2JWxlzpJmEB7XlgzK/R+6/aETmrq3W2dVHtdFcG/wPjQm3JoBoFiRS5AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:10:56.461467Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.16365","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83450e283d8d522c0695c0d3267aac384336243bc0f371f3b4b85d6f465d22b7","sha256:61b4b11241420f6a9878fdf1deb3267ca2782e39c2d5b1fb218e0bafbb36cf7a"],"state_sha256":"e69362bd5929e71ac6cdaad38128474fbb4dafb829eb0e66b1fdcc50777e71ba"}