{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SF55K56K4OHQSKXWED3FVGDMXM","short_pith_number":"pith:SF55K56K","canonical_record":{"source":{"id":"2605.16154","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T16:33:59Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"664582dafb2bb99f24dca92613a7ab8cc1a97fddf2ae6194f98d821d1021b944","abstract_canon_sha256":"f234a20cc377ead2bcfd6d6544e73879b9a5f7b1f7cec32f2b739fd94270483f"},"schema_version":"1.0"},"canonical_sha256":"917bd577cae38f092af620f65a986cbb2219ab069752aff8e35d4deadf27dc7d","source":{"kind":"arxiv","id":"2605.16154","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16154","created_at":"2026-05-20T00:01:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16154v1","created_at":"2026-05-20T00:01:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16154","created_at":"2026-05-20T00:01:55Z"},{"alias_kind":"pith_short_12","alias_value":"SF55K56K4OHQ","created_at":"2026-05-20T00:01:55Z"},{"alias_kind":"pith_short_16","alias_value":"SF55K56K4OHQSKXW","created_at":"2026-05-20T00:01:55Z"},{"alias_kind":"pith_short_8","alias_value":"SF55K56K","created_at":"2026-05-20T00:01:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SF55K56K4OHQSKXWED3FVGDMXM","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16154","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T16:33:59Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"664582dafb2bb99f24dca92613a7ab8cc1a97fddf2ae6194f98d821d1021b944","abstract_canon_sha256":"f234a20cc377ead2bcfd6d6544e73879b9a5f7b1f7cec32f2b739fd94270483f"},"schema_version":"1.0"},"canonical_sha256":"917bd577cae38f092af620f65a986cbb2219ab069752aff8e35d4deadf27dc7d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:55.311866Z","signature_b64":"ZogY617mHY0pl8IqKN8w3uC5zx0IkjkRDq8v2CPpMALb+tvKQmt0FAUWw7dp8jHYBcBvoILSMOlJvHAFX57fCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"917bd577cae38f092af620f65a986cbb2219ab069752aff8e35d4deadf27dc7d","last_reissued_at":"2026-05-20T00:01:55.310797Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:55.310797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16154","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":"2026-05-20T00:01:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qSPdpZ35VMWNBy64CYu8iGLeubM9gFP+liQQiQPJu0pCCbQUlRMyY46ZaV4H8qSa0C0/1+7B7iX7+z8rtV8NBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T15:28:20.904459Z"},"content_sha256":"b5e993a40dfa84e53fcd93d0d3d45a240dce4a648ef303327dd3053738003a4c","schema_version":"1.0","event_id":"sha256:b5e993a40dfa84e53fcd93d0d3d45a240dce4a648ef303327dd3053738003a4c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SF55K56K4OHQSKXWED3FVGDMXM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learn Where Outcomes Diverge: Efficient VLA RL via Probabilistic Chunk Masking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Nikshep Grampurohit, Pulkit Verma, Vaidehi Bagaria","submitted_at":"2026-05-15T16:33:59Z","abstract_excerpt":"Reinforcement learning (RL) allows vision-language-action (VLA) policies to generalize beyond their training distribution by optimizing directly for task success, but post-training is computationally expensive. A natural response has been to speed rollout collection through faster simulators and world models. In GRPO-based VLA RL, we find that the dominant cost lies elsewhere: gradient computation accounts for approximately 78% of wall-clock time per step in our runs, while rollout collection accounts for only 21%. Gradient cost dominates because much of this computation is spent on phases tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16154","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/2605.16154/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"cited_work_retraction","ran_at":"2026-05-19T18:22:02.507774Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:31.040869Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.442418Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"0870b263bfddb3599c0d92368e067d8ad8d3a764319d73445a6cfc5d40bfde6a"},"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":"2026-05-20T00:01:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0slInZDDxAG8sLt35Y/0H0VtB5n+wo072uSksyDMu68ItW1Og6fRk0ailWLtT4kAS1XMOV7BQgNORnmNOT8FDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T15:28:20.904959Z"},"content_sha256":"ee52844b318c5f57a0fc1b872186e8fb38e8d0a299e21518b97fc290d008dbf3","schema_version":"1.0","event_id":"sha256:ee52844b318c5f57a0fc1b872186e8fb38e8d0a299e21518b97fc290d008dbf3"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:SF55K56K4OHQSKXWED3FVGDMXM","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.48550/arxiv.2305.14314.URLhttps://arxiv.org/abs/2305.14314v1.Yanjiang) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"doi: 10.48550/arxiv.2305. 14314. URLhttps://arxiv.org/abs/2305.14314v1. Yanjiang Guo, Jianke Zhang, Xiaoyu Chen, Xiang Ji, Yen-Jen Wang, Yucheng Hu, and Jianyu Chen. Improving Vision-Language-Action Model with Online Reinforcement Learning.","arxiv_id":"2605.16154","detector":"doi_compliance","evidence":{"ref_index":6,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"doi: 10.48550/arxiv.2305. 14314. URLhttps://arxiv.org/abs/2305.14314v1. Yanjiang Guo, Jianke Zhang, Xiaoyu Chen, Xiang Ji, Yen-Jen Wang, Yucheng Hu, and Jianyu Chen. Improving Vision-Language-Action Model with Online Reinforcement Learning.","reconstructed_doi":"10.48550/arxiv.2305.14314.URLhttps://arxiv.org/abs/2305.14314v1.Yanjiang"},"severity":"advisory","ref_index":6,"audited_at":"2026-05-20T21:14:47.870665Z","event_type":"pith.integrity.v1","detected_doi":"10.48550/arxiv.2305.14314.URLhttps://arxiv.org/abs/2305.14314v1.Yanjiang","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"5060393a5b6f9ffcf12040ca3d3030b1664ce49758c62d463ab1dea7ca97437a","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":5456,"payload_sha256":"89f1a8fc7e2b54e520d5d97ca849aaf0abdb0cb224e978e2c34110e716bd95a4","signature_b64":"mdrdZOrLmFCZ0mT5mXhSe/WeSLyH6CClU0yILNhDhgjo4iMV63dIoeglb+J8wMq5zkKrK51JMp/yYqi4DPsYDQ==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T21:18:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hxJELYM+2emrA6u9YkNqMUW/x3s8Z5ECKL8FGjjrIyeXBjf54cE65iHTI8/OAYGGgNw8HiWFMmDEAa9CbL1XAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T15:28:20.905947Z"},"content_sha256":"95c66c993afc38cd03a88f26973fcfb73e72008109d1597fa1831384e3e647f0","schema_version":"1.0","event_id":"sha256:95c66c993afc38cd03a88f26973fcfb73e72008109d1597fa1831384e3e647f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SF55K56K4OHQSKXWED3FVGDMXM/bundle.json","state_url":"https://pith.science/pith/SF55K56K4OHQSKXWED3FVGDMXM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SF55K56K4OHQSKXWED3FVGDMXM/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":"2026-05-21T15:28:20Z","links":{"resolver":"https://pith.science/pith/SF55K56K4OHQSKXWED3FVGDMXM","bundle":"https://pith.science/pith/SF55K56K4OHQSKXWED3FVGDMXM/bundle.json","state":"https://pith.science/pith/SF55K56K4OHQSKXWED3FVGDMXM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SF55K56K4OHQSKXWED3FVGDMXM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SF55K56K4OHQSKXWED3FVGDMXM","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f234a20cc377ead2bcfd6d6544e73879b9a5f7b1f7cec32f2b739fd94270483f","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T16:33:59Z","title_canon_sha256":"664582dafb2bb99f24dca92613a7ab8cc1a97fddf2ae6194f98d821d1021b944"},"schema_version":"1.0","source":{"id":"2605.16154","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16154","created_at":"2026-05-20T00:01:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16154v1","created_at":"2026-05-20T00:01:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16154","created_at":"2026-05-20T00:01:55Z"},{"alias_kind":"pith_short_12","alias_value":"SF55K56K4OHQ","created_at":"2026-05-20T00:01:55Z"},{"alias_kind":"pith_short_16","alias_value":"SF55K56K4OHQSKXW","created_at":"2026-05-20T00:01:55Z"},{"alias_kind":"pith_short_8","alias_value":"SF55K56K","created_at":"2026-05-20T00:01:55Z"}],"graph_snapshots":[{"event_id":"sha256:ee52844b318c5f57a0fc1b872186e8fb38e8d0a299e21518b97fc290d008dbf3","target":"graph","created_at":"2026-05-20T00:01:55Z","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":[{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T18:22:02.507774Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:31.040869Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.442418Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.16154/integrity.json","findings":[],"snapshot_sha256":"0870b263bfddb3599c0d92368e067d8ad8d3a764319d73445a6cfc5d40bfde6a","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) allows vision-language-action (VLA) policies to generalize beyond their training distribution by optimizing directly for task success, but post-training is computationally expensive. A natural response has been to speed rollout collection through faster simulators and world models. In GRPO-based VLA RL, we find that the dominant cost lies elsewhere: gradient computation accounts for approximately 78% of wall-clock time per step in our runs, while rollout collection accounts for only 21%. Gradient cost dominates because much of this computation is spent on phases tha","authors_text":"Nikshep Grampurohit, Pulkit Verma, Vaidehi Bagaria","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T16:33:59Z","title":"Learn Where Outcomes Diverge: Efficient VLA RL via Probabilistic Chunk Masking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16154","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:b5e993a40dfa84e53fcd93d0d3d45a240dce4a648ef303327dd3053738003a4c","target":"record","created_at":"2026-05-20T00:01:55Z","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":"f234a20cc377ead2bcfd6d6544e73879b9a5f7b1f7cec32f2b739fd94270483f","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T16:33:59Z","title_canon_sha256":"664582dafb2bb99f24dca92613a7ab8cc1a97fddf2ae6194f98d821d1021b944"},"schema_version":"1.0","source":{"id":"2605.16154","kind":"arxiv","version":1}},"canonical_sha256":"917bd577cae38f092af620f65a986cbb2219ab069752aff8e35d4deadf27dc7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"917bd577cae38f092af620f65a986cbb2219ab069752aff8e35d4deadf27dc7d","first_computed_at":"2026-05-20T00:01:55.310797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:55.310797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZogY617mHY0pl8IqKN8w3uC5zx0IkjkRDq8v2CPpMALb+tvKQmt0FAUWw7dp8jHYBcBvoILSMOlJvHAFX57fCA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:55.311866Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16154","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5e993a40dfa84e53fcd93d0d3d45a240dce4a648ef303327dd3053738003a4c","sha256:ee52844b318c5f57a0fc1b872186e8fb38e8d0a299e21518b97fc290d008dbf3","sha256:95c66c993afc38cd03a88f26973fcfb73e72008109d1597fa1831384e3e647f0"],"state_sha256":"c7edeeb8d75df81411db614fed455e5dc9c79a28772c8dad4a2b14684c40ebac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tEQfrml6vDUk77o0rW5JBu34VQavuiP8tLg9J2VQjD68h2qWppo2RFed2mSe4xa6sZlwDwA9WEh8WLkOCH+TBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T15:28:20.908348Z","bundle_sha256":"bee1344517fdd8ac3d98b917e7864b13600ed8d49ebf32549faaa589ed1842a9"}}