{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6XRESUBB3NVN63SRSUFV23EWKD","short_pith_number":"pith:6XRESUBB","canonical_record":{"source":{"id":"2505.17016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T17:59:45Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"bb0f81aeebf5a926c0bafb8ef6603fa0cf155093d27ae3e9a03ace1ec0aecb01","abstract_canon_sha256":"1f8bf01acbd4d6da9ef27c5ed60d6e95d453d99659996ccb88ed723451b13ae0"},"schema_version":"1.0"},"canonical_sha256":"f5e2495021db6adf6e51950b5d6c9650d3fd08dd8944f742fdc9f119e4ec2497","source":{"kind":"arxiv","id":"2505.17016","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17016","created_at":"2026-05-21T14:18:16Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17016v1","created_at":"2026-05-21T14:18:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17016","created_at":"2026-05-21T14:18:16Z"},{"alias_kind":"pith_short_12","alias_value":"6XRESUBB3NVN","created_at":"2026-05-21T14:18:16Z"},{"alias_kind":"pith_short_16","alias_value":"6XRESUBB3NVN63SR","created_at":"2026-05-21T14:18:16Z"},{"alias_kind":"pith_short_8","alias_value":"6XRESUBB","created_at":"2026-05-21T14:18:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6XRESUBB3NVN63SRSUFV23EWKD","target":"record","payload":{"canonical_record":{"source":{"id":"2505.17016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T17:59:45Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"bb0f81aeebf5a926c0bafb8ef6603fa0cf155093d27ae3e9a03ace1ec0aecb01","abstract_canon_sha256":"1f8bf01acbd4d6da9ef27c5ed60d6e95d453d99659996ccb88ed723451b13ae0"},"schema_version":"1.0"},"canonical_sha256":"f5e2495021db6adf6e51950b5d6c9650d3fd08dd8944f742fdc9f119e4ec2497","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T14:18:16.289959Z","signature_b64":"i8JE9eLR+QSEbyFOQTrYePDXXQNhsq8Gnn2mXMhLjIWk3WflR8exkSzSXHhuJEB9W5SWiyviTQ2bz87LlbcwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5e2495021db6adf6e51950b5d6c9650d3fd08dd8944f742fdc9f119e4ec2497","last_reissued_at":"2026-05-21T14:18:16.288196Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T14:18:16.288196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.17016","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T14:18:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W3mHYSEnOXOY8b69nzxKx1k5LGKuiwueL7TsqJoSWzd4vnClVW6Ng+VPbqrJ885ipglis+8g5lcYIMvtzCI4Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T15:26:13.508272Z"},"content_sha256":"231eeb0b7bf65b35aaeec5e6c6f25991f8914c72711ee6aa114d7cccabbb6a58","schema_version":"1.0","event_id":"sha256:231eeb0b7bf65b35aaeec5e6c6f25991f8914c72711ee6aa114d7cccabbb6a58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6XRESUBB3NVN63SRSUFV23EWKD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Interactive Post-Training for Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Kairan Dou, Philipp Kr\\\"ahenb\\\"uhl, Shuhan Tan, Yue Zhao","submitted_at":"2025-05-22T17:59:45Z","abstract_excerpt":"We introduce RIPT-VLA, a simple and scalable reinforcement-learning-based interactive post-training paradigm that fine-tunes pretrained Vision-Language-Action (VLA) models using only sparse binary success rewards. Existing VLA training pipelines rely heavily on offline expert demonstration data and supervised imitation, limiting their ability to adapt to new tasks and environments under low-data regimes. RIPT-VLA addresses this by enabling interactive post-training with a stable policy optimization algorithm based on dynamic rollout sampling and leave-one-out advantage estimation.\n  RIPT-VLA h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17016","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/2505.17016/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":"2026-05-21T14:18:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NTvyVnxZTOZzbPLOFLjkJEYM2z7nGet0DReBQ9GP4wdxqOFDIchOLzzQtEK5hhmNotXLLd7FSaSrtUXJApYmCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T15:26:13.508984Z"},"content_sha256":"5887bb07fef646d3048a2fd15286ea8d88805dc5d868d040d8d5b60cbd228cbf","schema_version":"1.0","event_id":"sha256:5887bb07fef646d3048a2fd15286ea8d88805dc5d868d040d8d5b60cbd228cbf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6XRESUBB3NVN63SRSUFV23EWKD/bundle.json","state_url":"https://pith.science/pith/6XRESUBB3NVN63SRSUFV23EWKD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6XRESUBB3NVN63SRSUFV23EWKD/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":"2026-06-02T15:26:13Z","links":{"resolver":"https://pith.science/pith/6XRESUBB3NVN63SRSUFV23EWKD","bundle":"https://pith.science/pith/6XRESUBB3NVN63SRSUFV23EWKD/bundle.json","state":"https://pith.science/pith/6XRESUBB3NVN63SRSUFV23EWKD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6XRESUBB3NVN63SRSUFV23EWKD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6XRESUBB3NVN63SRSUFV23EWKD","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":"1f8bf01acbd4d6da9ef27c5ed60d6e95d453d99659996ccb88ed723451b13ae0","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T17:59:45Z","title_canon_sha256":"bb0f81aeebf5a926c0bafb8ef6603fa0cf155093d27ae3e9a03ace1ec0aecb01"},"schema_version":"1.0","source":{"id":"2505.17016","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17016","created_at":"2026-05-21T14:18:16Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17016v1","created_at":"2026-05-21T14:18:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17016","created_at":"2026-05-21T14:18:16Z"},{"alias_kind":"pith_short_12","alias_value":"6XRESUBB3NVN","created_at":"2026-05-21T14:18:16Z"},{"alias_kind":"pith_short_16","alias_value":"6XRESUBB3NVN63SR","created_at":"2026-05-21T14:18:16Z"},{"alias_kind":"pith_short_8","alias_value":"6XRESUBB","created_at":"2026-05-21T14:18:16Z"}],"graph_snapshots":[{"event_id":"sha256:5887bb07fef646d3048a2fd15286ea8d88805dc5d868d040d8d5b60cbd228cbf","target":"graph","created_at":"2026-05-21T14:18:16Z","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/2505.17016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce RIPT-VLA, a simple and scalable reinforcement-learning-based interactive post-training paradigm that fine-tunes pretrained Vision-Language-Action (VLA) models using only sparse binary success rewards. Existing VLA training pipelines rely heavily on offline expert demonstration data and supervised imitation, limiting their ability to adapt to new tasks and environments under low-data regimes. RIPT-VLA addresses this by enabling interactive post-training with a stable policy optimization algorithm based on dynamic rollout sampling and leave-one-out advantage estimation.\n  RIPT-VLA h","authors_text":"Kairan Dou, Philipp Kr\\\"ahenb\\\"uhl, Shuhan Tan, Yue Zhao","cross_cats":["cs.AI","cs.CV","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T17:59:45Z","title":"Interactive Post-Training for Vision-Language-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17016","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":"sha256:231eeb0b7bf65b35aaeec5e6c6f25991f8914c72711ee6aa114d7cccabbb6a58","target":"record","created_at":"2026-05-21T14:18:16Z","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":"1f8bf01acbd4d6da9ef27c5ed60d6e95d453d99659996ccb88ed723451b13ae0","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T17:59:45Z","title_canon_sha256":"bb0f81aeebf5a926c0bafb8ef6603fa0cf155093d27ae3e9a03ace1ec0aecb01"},"schema_version":"1.0","source":{"id":"2505.17016","kind":"arxiv","version":1}},"canonical_sha256":"f5e2495021db6adf6e51950b5d6c9650d3fd08dd8944f742fdc9f119e4ec2497","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5e2495021db6adf6e51950b5d6c9650d3fd08dd8944f742fdc9f119e4ec2497","first_computed_at":"2026-05-21T14:18:16.288196Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T14:18:16.288196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i8JE9eLR+QSEbyFOQTrYePDXXQNhsq8Gnn2mXMhLjIWk3WflR8exkSzSXHhuJEB9W5SWiyviTQ2bz87LlbcwAA==","signature_status":"signed_v1","signed_at":"2026-05-21T14:18:16.289959Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17016","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:231eeb0b7bf65b35aaeec5e6c6f25991f8914c72711ee6aa114d7cccabbb6a58","sha256:5887bb07fef646d3048a2fd15286ea8d88805dc5d868d040d8d5b60cbd228cbf"],"state_sha256":"402112a0438571164a7126b4faee0a6448c03cdd987d92b4ac25d63c2401312e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cpFeymmALd4WkqqhDCBb1PscorP2QUh2FJJLp4MscsPDpveGGoB4LzqWbP9dGBrXfexMXC9RJTb+PgX34DIIAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T15:26:13.512381Z","bundle_sha256":"d0038536d86bb305a2f39ea0868eb2b85215b7b8846aae93bc2b686d36ed6e13"}}