{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GADTS5BFZ4POH76HPPRHYUE3MY","short_pith_number":"pith:GADTS5BF","canonical_record":{"source":{"id":"2607.26991","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-29T14:49:56Z","cross_cats_sorted":[],"title_canon_sha256":"81276eed19d6337e1de59b7ee0e356d17f5c2f37c928944161df2bdd55996c31","abstract_canon_sha256":"8294be871be280cb9a4797de318436a6c20b0d76f8bcf65742f11878f849dd4e"},"schema_version":"1.0"},"canonical_sha256":"3007397425cf1ee3ffc77be27c509b6609a5458652ea7664ccd66fea1d35c124","source":{"kind":"arxiv","id":"2607.26991","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26991","created_at":"2026-07-30T01:23:16Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26991v1","created_at":"2026-07-30T01:23:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26991","created_at":"2026-07-30T01:23:16Z"},{"alias_kind":"pith_short_12","alias_value":"GADTS5BFZ4PO","created_at":"2026-07-30T01:23:16Z"},{"alias_kind":"pith_short_16","alias_value":"GADTS5BFZ4POH76H","created_at":"2026-07-30T01:23:16Z"},{"alias_kind":"pith_short_8","alias_value":"GADTS5BF","created_at":"2026-07-30T01:23:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GADTS5BFZ4POH76HPPRHYUE3MY","target":"record","payload":{"canonical_record":{"source":{"id":"2607.26991","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-29T14:49:56Z","cross_cats_sorted":[],"title_canon_sha256":"81276eed19d6337e1de59b7ee0e356d17f5c2f37c928944161df2bdd55996c31","abstract_canon_sha256":"8294be871be280cb9a4797de318436a6c20b0d76f8bcf65742f11878f849dd4e"},"schema_version":"1.0"},"canonical_sha256":"3007397425cf1ee3ffc77be27c509b6609a5458652ea7664ccd66fea1d35c124","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3007397425cf1ee3ffc77be27c509b6609a5458652ea7664ccd66fea1d35c124","last_reissued_at":"2026-07-30T01:23:16.647750Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:23:16.647750Z"},"source_kind":"arxiv","source_id":"2607.26991","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":"2026-07-30T01:23:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mZCzuYCVG3Vb5mcRq1Y7LmXavC+HI2p75+ZU5NfMtzZn2TPA/e5rY14rx7hSwQBS1gQ+6VoOtxPnmSuC3TrxBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:08:54.083903Z"},"content_sha256":"56e195677569e21a52fe7d869e57f54498774e8c822e302a59b4e68c97ce29a6","schema_version":"1.0","event_id":"sha256:56e195677569e21a52fe7d869e57f54498774e8c822e302a59b4e68c97ce29a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GADTS5BFZ4POH76HPPRHYUE3MY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Derek Ming Siang Tan, Guillaume Sartoretti, Qiao Gu, Shailesh Shailesh, Srikrishna Iyer, William Wei Jie Teo, Yuanliang Ju","submitted_at":"2026-07-29T14:49:56Z","abstract_excerpt":"Despite the impressive visuomotor capabilities enabled by Vision-Language-Action (VLA) models, their performance often degrades on challenging and out-of-domain tasks. Recent test-time steering and scaling methods improve performance without extensive data collection and retraining, but action samples often remain concentrated around similar behaviors and therefore inherit correlated failure modes. Moreover, existing methods apply the same intervention strategy at every timestep, regardless of whether the base policy is already likely to succeed. To address these limitations, we introduce $RL^"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26991","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/2607.26991/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":"2026-07-30T01:23:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v1BR4tBgJe/KB1rc0OwdfHP5jtF7ItJ7hAsvTO9lK9adZX32gEQv28eIrL8mE3QgAgC09NMXpzcmX1aPWCnTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:08:54.084505Z"},"content_sha256":"2d443927ab3cbc692b85b012036423c70683db5fde07f773eef07f9d22132f40","schema_version":"1.0","event_id":"sha256:2d443927ab3cbc692b85b012036423c70683db5fde07f773eef07f9d22132f40"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GADTS5BFZ4POH76HPPRHYUE3MY/bundle.json","state_url":"https://pith.science/pith/GADTS5BFZ4POH76HPPRHYUE3MY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GADTS5BFZ4POH76HPPRHYUE3MY/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":"2026-08-05T06:08:54Z","links":{"resolver":"https://pith.science/pith/GADTS5BFZ4POH76HPPRHYUE3MY","bundle":"https://pith.science/pith/GADTS5BFZ4POH76HPPRHYUE3MY/bundle.json","state":"https://pith.science/pith/GADTS5BFZ4POH76HPPRHYUE3MY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GADTS5BFZ4POH76HPPRHYUE3MY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GADTS5BFZ4POH76HPPRHYUE3MY","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":"8294be871be280cb9a4797de318436a6c20b0d76f8bcf65742f11878f849dd4e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-29T14:49:56Z","title_canon_sha256":"81276eed19d6337e1de59b7ee0e356d17f5c2f37c928944161df2bdd55996c31"},"schema_version":"1.0","source":{"id":"2607.26991","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26991","created_at":"2026-07-30T01:23:16Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26991v1","created_at":"2026-07-30T01:23:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26991","created_at":"2026-07-30T01:23:16Z"},{"alias_kind":"pith_short_12","alias_value":"GADTS5BFZ4PO","created_at":"2026-07-30T01:23:16Z"},{"alias_kind":"pith_short_16","alias_value":"GADTS5BFZ4POH76H","created_at":"2026-07-30T01:23:16Z"},{"alias_kind":"pith_short_8","alias_value":"GADTS5BF","created_at":"2026-07-30T01:23:16Z"}],"graph_snapshots":[{"event_id":"sha256:2d443927ab3cbc692b85b012036423c70683db5fde07f773eef07f9d22132f40","target":"graph","created_at":"2026-07-30T01:23:16Z","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/2607.26991/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the impressive visuomotor capabilities enabled by Vision-Language-Action (VLA) models, their performance often degrades on challenging and out-of-domain tasks. Recent test-time steering and scaling methods improve performance without extensive data collection and retraining, but action samples often remain concentrated around similar behaviors and therefore inherit correlated failure modes. Moreover, existing methods apply the same intervention strategy at every timestep, regardless of whether the base policy is already likely to succeed. To address these limitations, we introduce $RL^","authors_text":"Derek Ming Siang Tan, Guillaume Sartoretti, Qiao Gu, Shailesh Shailesh, Srikrishna Iyer, William Wei Jie Teo, Yuanliang Ju","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-29T14:49:56Z","title":"RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26991","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":"sha256:56e195677569e21a52fe7d869e57f54498774e8c822e302a59b4e68c97ce29a6","target":"record","created_at":"2026-07-30T01:23:16Z","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":"8294be871be280cb9a4797de318436a6c20b0d76f8bcf65742f11878f849dd4e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-29T14:49:56Z","title_canon_sha256":"81276eed19d6337e1de59b7ee0e356d17f5c2f37c928944161df2bdd55996c31"},"schema_version":"1.0","source":{"id":"2607.26991","kind":"arxiv","version":1}},"canonical_sha256":"3007397425cf1ee3ffc77be27c509b6609a5458652ea7664ccd66fea1d35c124","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3007397425cf1ee3ffc77be27c509b6609a5458652ea7664ccd66fea1d35c124","first_computed_at":"2026-07-30T01:23:16.647750Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:23:16.647750Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26991","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56e195677569e21a52fe7d869e57f54498774e8c822e302a59b4e68c97ce29a6","sha256:2d443927ab3cbc692b85b012036423c70683db5fde07f773eef07f9d22132f40"],"state_sha256":"62fe875e9d6852741259b4d42ad99e068fe8bbbbcfd56785223943ece6847494"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l8jWB8/MGAifZ9oJrT37i2M/hjLsyGwXMPc/GP3jj2vwAg8Yl+nZmQLjqvlawmPUbm49/CqtA0EC4n01vFqpCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:08:54.089554Z","bundle_sha256":"be2daae6a0e10f5277de179e343f0fb4ca854d138cdf8bfdc1641dfb288ea315"}}