{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ML4WTEX5SIQ2MP6CZTK5ROTTU4","short_pith_number":"pith:ML4WTEX5","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"},"canonical_sha256":"62f96992fd9221a63fc2ccd5d8ba73a7061186b55956ee86b954ac0e2f8f98dc","source":{"kind":"arxiv","id":"2503.16365","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ML4WTEX5SIQ2MP6CZTK5ROTTU4","target":"record","payload":{"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"},"canonical_sha256":"62f96992fd9221a63fc2ccd5d8ba73a7061186b55956ee86b954ac0e2f8f98dc","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"},"source_kind":"arxiv","source_id":"2503.16365","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:10:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jmDD/cUTP/YmF8oEslVzhHQpsYg9fOv23WTmXaasQThAn/AT0ZN90nfmshRxTwmTuMzEtAraZWYemMEuZW5qDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:06:36.596595Z"},"content_sha256":"83450e283d8d522c0695c0d3267aac384336243bc0f371f3b4b85d6f465d22b7","schema_version":"1.0","event_id":"sha256:83450e283d8d522c0695c0d3267aac384336243bc0f371f3b4b85d6f465d22b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ML4WTEX5SIQ2MP6CZTK5ROTTU4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:10:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3arFC7TDYtdW23giNu8aHchLzhgEgShnyWGd9c8Z4nqiLz1fhm8JTyTsvujaSWBobnDUghpwCiYZUkiHQMssDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:06:36.597100Z"},"content_sha256":"61b4b11241420f6a9878fdf1deb3267ca2782e39c2d5b1fb218e0bafbb36cf7a","schema_version":"1.0","event_id":"sha256:61b4b11241420f6a9878fdf1deb3267ca2782e39c2d5b1fb218e0bafbb36cf7a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ML4WTEX5SIQ2MP6CZTK5ROTTU4/bundle.json","state_url":"https://pith.science/pith/ML4WTEX5SIQ2MP6CZTK5ROTTU4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ML4WTEX5SIQ2MP6CZTK5ROTTU4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T12:06:36Z","links":{"resolver":"https://pith.science/pith/ML4WTEX5SIQ2MP6CZTK5ROTTU4","bundle":"https://pith.science/pith/ML4WTEX5SIQ2MP6CZTK5ROTTU4/bundle.json","state":"https://pith.science/pith/ML4WTEX5SIQ2MP6CZTK5ROTTU4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ML4WTEX5SIQ2MP6CZTK5ROTTU4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CYgilyNcWl2u9TtZ0h4Jje018KKCEH5GgVXv9uFg13iZAyVKRpTywHz2bG/G16w1uUCpanotC3FFnGuYwNIPAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T12:06:36.600523Z","bundle_sha256":"494d1efe6e23cb5410269c5f30aeecd1c25af3cbe03529710931a39946982ed2"}}