{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:R5L2OLF66D7KACR5W2Q4TSGE76","short_pith_number":"pith:R5L2OLF6","canonical_record":{"source":{"id":"2606.17924","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-16T13:38:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a16628deaadecd2ab562e8bebf8d8dc687c731d5870aa4d6fd1af1f830926771","abstract_canon_sha256":"a60e306c0badbbb766bfad2139168f1964064c23249517dd916f111d9a97f1f6"},"schema_version":"1.0"},"canonical_sha256":"8f57a72cbef0fea00a3db6a1c9c8c4ffbb1b2d5e7a981ea531c8474bf632ae75","source":{"kind":"arxiv","id":"2606.17924","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17924","created_at":"2026-06-19T16:10:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17924v1","created_at":"2026-06-19T16:10:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17924","created_at":"2026-06-19T16:10:43Z"},{"alias_kind":"pith_short_12","alias_value":"R5L2OLF66D7K","created_at":"2026-06-19T16:10:43Z"},{"alias_kind":"pith_short_16","alias_value":"R5L2OLF66D7KACR5","created_at":"2026-06-19T16:10:43Z"},{"alias_kind":"pith_short_8","alias_value":"R5L2OLF6","created_at":"2026-06-19T16:10:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:R5L2OLF66D7KACR5W2Q4TSGE76","target":"record","payload":{"canonical_record":{"source":{"id":"2606.17924","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-16T13:38:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a16628deaadecd2ab562e8bebf8d8dc687c731d5870aa4d6fd1af1f830926771","abstract_canon_sha256":"a60e306c0badbbb766bfad2139168f1964064c23249517dd916f111d9a97f1f6"},"schema_version":"1.0"},"canonical_sha256":"8f57a72cbef0fea00a3db6a1c9c8c4ffbb1b2d5e7a981ea531c8474bf632ae75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:43.690838Z","signature_b64":"/jZU50PeTuKkShmJWi3gtYTec/7K3/BOJVBHLLXrpzBPWMIQegEjPM3tWEtgVF87h6GcuFLqKJkNbwTzMkoiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f57a72cbef0fea00a3db6a1c9c8c4ffbb1b2d5e7a981ea531c8474bf632ae75","last_reissued_at":"2026-06-19T16:10:43.690482Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:43.690482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.17924","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":"2026-06-19T16:10:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1SOqYv2grjEh44FuZH+QIJxu2SpQuwDntR3YwfAeDCTPTZlE3EZEtnxHu7X4RlpP0y2Kj8w3Ldz7kdVLAs3WDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T21:15:55.717395Z"},"content_sha256":"fdaf6e84902fc48ceae209c0f5ce626821ec9baf514ee3c556969a6d955d235a","schema_version":"1.0","event_id":"sha256:fdaf6e84902fc48ceae209c0f5ce626821ec9baf514ee3c556969a6d955d235a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:R5L2OLF66D7KACR5W2Q4TSGE76","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Bochen Yang, Lianlei Shan","submitted_at":"2026-06-16T13:38:03Z","abstract_excerpt":"Current Vision-Language-Action (VLA) models face a trade-off between efficient action generation and explicit deliberation. Directly decoding actions from vision-language backbone representations enables low-latency control, whereas explicit reasoning through textual chains, pixel-level subgoals, or action search can improve planning but incurs substantial latency and computational cost. We propose PearlVLA, a VLA framework that moves deliberation into the latent space of a vision-language model (VLM). PearlVLA separates VLM meta-query representations into a fixed visual grounding branch and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17924","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/2606.17924/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":"2026-06-19T16:10:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KocGKohfmW4fURWJB7GnH2wor8j+ikefrQ9zUU90y6Pbq4Lm9Kl74ws4YnTzDFeCOOjiPFbIvCb1S0cDIbnSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T21:15:55.717762Z"},"content_sha256":"6f7b485774cf56b1ba7713083f7c8b3a31b79caaeab4bf42b4677600fba32402","schema_version":"1.0","event_id":"sha256:6f7b485774cf56b1ba7713083f7c8b3a31b79caaeab4bf42b4677600fba32402"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R5L2OLF66D7KACR5W2Q4TSGE76/bundle.json","state_url":"https://pith.science/pith/R5L2OLF66D7KACR5W2Q4TSGE76/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R5L2OLF66D7KACR5W2Q4TSGE76/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":"2026-06-27T21:15:55Z","links":{"resolver":"https://pith.science/pith/R5L2OLF66D7KACR5W2Q4TSGE76","bundle":"https://pith.science/pith/R5L2OLF66D7KACR5W2Q4TSGE76/bundle.json","state":"https://pith.science/pith/R5L2OLF66D7KACR5W2Q4TSGE76/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R5L2OLF66D7KACR5W2Q4TSGE76/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:R5L2OLF66D7KACR5W2Q4TSGE76","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":"a60e306c0badbbb766bfad2139168f1964064c23249517dd916f111d9a97f1f6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-16T13:38:03Z","title_canon_sha256":"a16628deaadecd2ab562e8bebf8d8dc687c731d5870aa4d6fd1af1f830926771"},"schema_version":"1.0","source":{"id":"2606.17924","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17924","created_at":"2026-06-19T16:10:43Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17924v1","created_at":"2026-06-19T16:10:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17924","created_at":"2026-06-19T16:10:43Z"},{"alias_kind":"pith_short_12","alias_value":"R5L2OLF66D7K","created_at":"2026-06-19T16:10:43Z"},{"alias_kind":"pith_short_16","alias_value":"R5L2OLF66D7KACR5","created_at":"2026-06-19T16:10:43Z"},{"alias_kind":"pith_short_8","alias_value":"R5L2OLF6","created_at":"2026-06-19T16:10:43Z"}],"graph_snapshots":[{"event_id":"sha256:6f7b485774cf56b1ba7713083f7c8b3a31b79caaeab4bf42b4677600fba32402","target":"graph","created_at":"2026-06-19T16:10:43Z","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/2606.17924/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current Vision-Language-Action (VLA) models face a trade-off between efficient action generation and explicit deliberation. Directly decoding actions from vision-language backbone representations enables low-latency control, whereas explicit reasoning through textual chains, pixel-level subgoals, or action search can improve planning but incurs substantial latency and computational cost. We propose PearlVLA, a VLA framework that moves deliberation into the latent space of a vision-language model (VLM). PearlVLA separates VLM meta-query representations into a fixed visual grounding branch and a","authors_text":"Bochen Yang, Lianlei Shan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-16T13:38:03Z","title":"PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17924","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:fdaf6e84902fc48ceae209c0f5ce626821ec9baf514ee3c556969a6d955d235a","target":"record","created_at":"2026-06-19T16:10:43Z","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":"a60e306c0badbbb766bfad2139168f1964064c23249517dd916f111d9a97f1f6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-16T13:38:03Z","title_canon_sha256":"a16628deaadecd2ab562e8bebf8d8dc687c731d5870aa4d6fd1af1f830926771"},"schema_version":"1.0","source":{"id":"2606.17924","kind":"arxiv","version":1}},"canonical_sha256":"8f57a72cbef0fea00a3db6a1c9c8c4ffbb1b2d5e7a981ea531c8474bf632ae75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f57a72cbef0fea00a3db6a1c9c8c4ffbb1b2d5e7a981ea531c8474bf632ae75","first_computed_at":"2026-06-19T16:10:43.690482Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:43.690482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/jZU50PeTuKkShmJWi3gtYTec/7K3/BOJVBHLLXrpzBPWMIQegEjPM3tWEtgVF87h6GcuFLqKJkNbwTzMkoiAQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:43.690838Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.17924","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fdaf6e84902fc48ceae209c0f5ce626821ec9baf514ee3c556969a6d955d235a","sha256:6f7b485774cf56b1ba7713083f7c8b3a31b79caaeab4bf42b4677600fba32402"],"state_sha256":"30260e5b60ba4fa678aaffe1ec062a0c4f7e7fd01fe0167b6ccf003b65532b5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oaEFGsAMipbDTvwXc/6uk6Kj8mpGLrWyv+O+97fKLVOLFuRPI3ViAJwNyOmfmKftjfTd0laRGT/tBCnvY7mlAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T21:15:55.719725Z","bundle_sha256":"7c1fb4c8f2aab43a0c6c72f8b1b5a52ec80fa530e2c1247934bca7e315b4fde0"}}