{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ML4WTEX5SIQ2MP6CZTK5ROTTU4","short_pith_number":"pith:ML4WTEX5","schema_version":"1.0","canonical_sha256":"62f96992fd9221a63fc2ccd5d8ba73a7061186b55956ee86b954ac0e2f8f98dc","source":{"kind":"arxiv","id":"2503.16365","version":2},"attestation_state":"computed","paper":{"title":"JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kaichen He, Muyao Li, Xiaojian Ma, Yitao Liang, Zihao Wang","submitted_at":"2025-03-20T17:21:58Z","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"},"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":"2503.16365","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T17:21:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d67629589ac47d7c36e18e83f982e853bd8aabca27c5a7408551d6a6eb5f823a","abstract_canon_sha256":"bebd9acdd92cecc5238596eaff7ce00078a6f2b1afb6c06a49198ff88d35ea17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:10:56.461467Z","signature_b64":"iceuyfN+YUGYuEUSOirbG/m6xgHSg2JWxlzpJmEB7XlgzK/R+6/aETmrq3W2dVHtdFcG/wPjQm3JoBoFiRS5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62f96992fd9221a63fc2ccd5d8ba73a7061186b55956ee86b954ac0e2f8f98dc","last_reissued_at":"2026-07-05T12:10:56.460974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:10:56.460974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kaichen He, Muyao Li, Xiaojian Ma, Yitao Liang, Zihao Wang","submitted_at":"2025-03-20T17:21:58Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16365","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/2503.16365/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":"2503.16365","created_at":"2026-07-05T12:10:56.461033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16365v2","created_at":"2026-07-05T12:10:56.461033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16365","created_at":"2026-07-05T12:10:56.461033+00:00"},{"alias_kind":"pith_short_12","alias_value":"ML4WTEX5SIQ2","created_at":"2026-07-05T12:10:56.461033+00:00"},{"alias_kind":"pith_short_16","alias_value":"ML4WTEX5SIQ2MP6C","created_at":"2026-07-05T12:10:56.461033+00:00"},{"alias_kind":"pith_short_8","alias_value":"ML4WTEX5","created_at":"2026-07-05T12:10:56.461033+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00535","citing_title":"DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2507.01925","citing_title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","ref_index":262,"is_internal_anchor":false},{"citing_arxiv_id":"2509.02544","citing_title":"UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11223","citing_title":"Do Vision-Language-Models show human-like logical problem-solving capability in point and click puzzle games?","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11223","citing_title":"Do Vision-Language-Models show human-like logical problem-solving capability in point and click puzzle games?","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27578","citing_title":"World2Minecraft: Occupancy-Driven Simulated Scenes Construction","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07429","citing_title":"GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ML4WTEX5SIQ2MP6CZTK5ROTTU4","json":"https://pith.science/pith/ML4WTEX5SIQ2MP6CZTK5ROTTU4.json","graph_json":"https://pith.science/api/pith-number/ML4WTEX5SIQ2MP6CZTK5ROTTU4/graph.json","events_json":"https://pith.science/api/pith-number/ML4WTEX5SIQ2MP6CZTK5ROTTU4/events.json","paper":"https://pith.science/paper/ML4WTEX5"},"agent_actions":{"view_html":"https://pith.science/pith/ML4WTEX5SIQ2MP6CZTK5ROTTU4","download_json":"https://pith.science/pith/ML4WTEX5SIQ2MP6CZTK5ROTTU4.json","view_paper":"https://pith.science/paper/ML4WTEX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16365&json=true","fetch_graph":"https://pith.science/api/pith-number/ML4WTEX5SIQ2MP6CZTK5ROTTU4/graph.json","fetch_events":"https://pith.science/api/pith-number/ML4WTEX5SIQ2MP6CZTK5ROTTU4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ML4WTEX5SIQ2MP6CZTK5ROTTU4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ML4WTEX5SIQ2MP6CZTK5ROTTU4/action/storage_attestation","attest_author":"https://pith.science/pith/ML4WTEX5SIQ2MP6CZTK5ROTTU4/action/author_attestation","sign_citation":"https://pith.science/pith/ML4WTEX5SIQ2MP6CZTK5ROTTU4/action/citation_signature","submit_replication":"https://pith.science/pith/ML4WTEX5SIQ2MP6CZTK5ROTTU4/action/replication_record"}},"created_at":"2026-07-05T12:10:56.461033+00:00","updated_at":"2026-07-05T12:10:56.461033+00:00"}