{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BMF3H23UNIWTLF34ZK2DJHYQHZ","short_pith_number":"pith:BMF3H23U","canonical_record":{"source":{"id":"2606.29892","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-29T07:31:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"856db6e41dca6ebbdc7b07a060ee8c21eb61937978837b7b1efe6ca2fd2d2f0d","abstract_canon_sha256":"a8400189d7b693e6b1194a1e66a574910df4a401baa3c6a45e61b0caeba2dc7f"},"schema_version":"1.0"},"canonical_sha256":"0b0bb3eb746a2d35977ccab4349f103e6a7112da3332d8a1e72d6ed32d106596","source":{"kind":"arxiv","id":"2606.29892","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29892","created_at":"2026-06-30T02:17:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29892v1","created_at":"2026-06-30T02:17:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29892","created_at":"2026-06-30T02:17:39Z"},{"alias_kind":"pith_short_12","alias_value":"BMF3H23UNIWT","created_at":"2026-06-30T02:17:39Z"},{"alias_kind":"pith_short_16","alias_value":"BMF3H23UNIWTLF34","created_at":"2026-06-30T02:17:39Z"},{"alias_kind":"pith_short_8","alias_value":"BMF3H23U","created_at":"2026-06-30T02:17:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BMF3H23UNIWTLF34ZK2DJHYQHZ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.29892","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-29T07:31:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"856db6e41dca6ebbdc7b07a060ee8c21eb61937978837b7b1efe6ca2fd2d2f0d","abstract_canon_sha256":"a8400189d7b693e6b1194a1e66a574910df4a401baa3c6a45e61b0caeba2dc7f"},"schema_version":"1.0"},"canonical_sha256":"0b0bb3eb746a2d35977ccab4349f103e6a7112da3332d8a1e72d6ed32d106596","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:39.776267Z","signature_b64":"pQzrg5sNz6x53svtnnIxpwRW5uSYKo9dGGiThZYiVIyGi7TWNdg0PLEZzqXsK3qAHTDPm/tyM9e1uwoW3quPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b0bb3eb746a2d35977ccab4349f103e6a7112da3332d8a1e72d6ed32d106596","last_reissued_at":"2026-06-30T02:17:39.775651Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:39.775651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.29892","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":"2026-06-30T02:17:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y8EtcAtxjm1ECPJPzmxjM1LxQLITq5gc/OjtkaDUEkKRAS93686OG5KE6m5TyCYWReX6cNZuT2cEABCNWIaFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T18:18:39.984614Z"},"content_sha256":"e461544f84a1f035144a1d1811b0c449670116648c2213793923ed03793187c4","schema_version":"1.0","event_id":"sha256:e461544f84a1f035144a1d1811b0c449670116648c2213793923ed03793187c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BMF3H23UNIWTLF34ZK2DJHYQHZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jiakang Yuan, Jiaxin Wang, Siyao Chen, Tao Chen","submitted_at":"2026-06-29T07:31:41Z","abstract_excerpt":"Reinforcement learning (RL) has become indispensable for pushing Vision-Language-Action Models (VLAs) beyond static imitation learning. However, existing RL methods typically require external environmental feedback, relying on predefined success signals to guide policy updates. In this work, we show that VLA models possess useful internal evaluative capabilities: in discrete-action VLAs, trajectories with higher generation confidence are significantly more likely to succeed. Based on this observation, we introduce T^2VLA (Test-time VLA), an architecture-agnostic test-time RL framework that ena"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29892","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/2606.29892/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":"2026-06-30T02:17:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CopfWv9viKSqGf/ROB7Dt4NAs33d2WhsD82jxdABdMfOkTjDchDgFUqmUM1YZT961EnCKZ9rYMtF3KKpzl8sBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T18:18:39.985000Z"},"content_sha256":"07a4f1fdd6573582cc8f90484e987735fb926bb3aac6ad239ca63371ea62be09","schema_version":"1.0","event_id":"sha256:07a4f1fdd6573582cc8f90484e987735fb926bb3aac6ad239ca63371ea62be09"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BMF3H23UNIWTLF34ZK2DJHYQHZ/bundle.json","state_url":"https://pith.science/pith/BMF3H23UNIWTLF34ZK2DJHYQHZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BMF3H23UNIWTLF34ZK2DJHYQHZ/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":"2026-06-30T18:18:39Z","links":{"resolver":"https://pith.science/pith/BMF3H23UNIWTLF34ZK2DJHYQHZ","bundle":"https://pith.science/pith/BMF3H23UNIWTLF34ZK2DJHYQHZ/bundle.json","state":"https://pith.science/pith/BMF3H23UNIWTLF34ZK2DJHYQHZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BMF3H23UNIWTLF34ZK2DJHYQHZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BMF3H23UNIWTLF34ZK2DJHYQHZ","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":"a8400189d7b693e6b1194a1e66a574910df4a401baa3c6a45e61b0caeba2dc7f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-29T07:31:41Z","title_canon_sha256":"856db6e41dca6ebbdc7b07a060ee8c21eb61937978837b7b1efe6ca2fd2d2f0d"},"schema_version":"1.0","source":{"id":"2606.29892","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29892","created_at":"2026-06-30T02:17:39Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29892v1","created_at":"2026-06-30T02:17:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29892","created_at":"2026-06-30T02:17:39Z"},{"alias_kind":"pith_short_12","alias_value":"BMF3H23UNIWT","created_at":"2026-06-30T02:17:39Z"},{"alias_kind":"pith_short_16","alias_value":"BMF3H23UNIWTLF34","created_at":"2026-06-30T02:17:39Z"},{"alias_kind":"pith_short_8","alias_value":"BMF3H23U","created_at":"2026-06-30T02:17:39Z"}],"graph_snapshots":[{"event_id":"sha256:07a4f1fdd6573582cc8f90484e987735fb926bb3aac6ad239ca63371ea62be09","target":"graph","created_at":"2026-06-30T02:17:39Z","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/2606.29892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has become indispensable for pushing Vision-Language-Action Models (VLAs) beyond static imitation learning. However, existing RL methods typically require external environmental feedback, relying on predefined success signals to guide policy updates. In this work, we show that VLA models possess useful internal evaluative capabilities: in discrete-action VLAs, trajectories with higher generation confidence are significantly more likely to succeed. Based on this observation, we introduce T^2VLA (Test-time VLA), an architecture-agnostic test-time RL framework that ena","authors_text":"Jiakang Yuan, Jiaxin Wang, Siyao Chen, Tao Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-29T07:31:41Z","title":"Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29892","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:e461544f84a1f035144a1d1811b0c449670116648c2213793923ed03793187c4","target":"record","created_at":"2026-06-30T02:17:39Z","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":"a8400189d7b693e6b1194a1e66a574910df4a401baa3c6a45e61b0caeba2dc7f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-29T07:31:41Z","title_canon_sha256":"856db6e41dca6ebbdc7b07a060ee8c21eb61937978837b7b1efe6ca2fd2d2f0d"},"schema_version":"1.0","source":{"id":"2606.29892","kind":"arxiv","version":1}},"canonical_sha256":"0b0bb3eb746a2d35977ccab4349f103e6a7112da3332d8a1e72d6ed32d106596","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b0bb3eb746a2d35977ccab4349f103e6a7112da3332d8a1e72d6ed32d106596","first_computed_at":"2026-06-30T02:17:39.775651Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:39.775651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pQzrg5sNz6x53svtnnIxpwRW5uSYKo9dGGiThZYiVIyGi7TWNdg0PLEZzqXsK3qAHTDPm/tyM9e1uwoW3quPBw==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:39.776267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29892","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e461544f84a1f035144a1d1811b0c449670116648c2213793923ed03793187c4","sha256:07a4f1fdd6573582cc8f90484e987735fb926bb3aac6ad239ca63371ea62be09"],"state_sha256":"06b9b05f9d518c6f860d4694ba1173c738cccb8e102769cedf14b0a8ea250cd6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+LTwSLf7Oo0+4d2m+vDAHvaXYlCXLZPONtT1sGKPeyspPWUChUcpSz/znP3uI/rGT8ZW3iMf4kiOtoj7qXcJDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T18:18:39.987216Z","bundle_sha256":"049e019233db97ca8f62cb19133f108a07a47fffa5af60268d347e6d11fc4515"}}