{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3X2GFYZFIOCQFLRLEZOPTB63Z2","short_pith_number":"pith:3X2GFYZF","canonical_record":{"source":{"id":"2602.19710","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-23T11:00:08Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"d1887ac83aa98df5c4eaa00d1662463d763ef0961ec56be17418f321fccc996c","abstract_canon_sha256":"b05b69419d03c5502be8c65cac55b1b016b5266b0b899cc5ce50fe7708dd6296"},"schema_version":"1.0"},"canonical_sha256":"ddf462e325438502ae2b265cf987dbce9da62cd435a94113889a64e00a328820","source":{"kind":"arxiv","id":"2602.19710","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.19710","created_at":"2026-05-20T00:03:06Z"},{"alias_kind":"arxiv_version","alias_value":"2602.19710v2","created_at":"2026-05-20T00:03:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.19710","created_at":"2026-05-20T00:03:06Z"},{"alias_kind":"pith_short_12","alias_value":"3X2GFYZFIOCQ","created_at":"2026-05-20T00:03:06Z"},{"alias_kind":"pith_short_16","alias_value":"3X2GFYZFIOCQFLRL","created_at":"2026-05-20T00:03:06Z"},{"alias_kind":"pith_short_8","alias_value":"3X2GFYZF","created_at":"2026-05-20T00:03:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3X2GFYZFIOCQFLRLEZOPTB63Z2","target":"record","payload":{"canonical_record":{"source":{"id":"2602.19710","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-23T11:00:08Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"d1887ac83aa98df5c4eaa00d1662463d763ef0961ec56be17418f321fccc996c","abstract_canon_sha256":"b05b69419d03c5502be8c65cac55b1b016b5266b0b899cc5ce50fe7708dd6296"},"schema_version":"1.0"},"canonical_sha256":"ddf462e325438502ae2b265cf987dbce9da62cd435a94113889a64e00a328820","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:06.385674Z","signature_b64":"rz3DDhOlR8UHr8NhytPX8vRzr1yssylPfLcCNui1mBxrTj1neG6hhb5h+TwcgMjydcSKpENurYJMPuRixATDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddf462e325438502ae2b265cf987dbce9da62cd435a94113889a64e00a328820","last_reissued_at":"2026-05-20T00:03:06.384872Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:06.384872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.19710","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tl7rskCAVi3BH7t8AHQl5pGMO7K7iWD78o6iuCplviBynexsxIhmTQCQxQtF5W61s4+Fggr+TEA5J0xLxSdxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T08:31:32.116964Z"},"content_sha256":"4d290148d07e605f0b8fd44014b3e665be166956a2e11cf79ab7f3884ed327e4","schema_version":"1.0","event_id":"sha256:4d290148d07e605f0b8fd44014b3e665be166956a2e11cf79ab7f3884ed327e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3X2GFYZFIOCQFLRLEZOPTB63Z2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Universal Pose Pretraining for Generalizable Vision-Language-Action Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Haitao Lin, Hanyang Yu, He Zhang, Jingshun Huang, Ping Tan, Xiangyang Xue, Yanwei Fu, Yonggen Ling","submitted_at":"2026-02-23T11:00:08Z","abstract_excerpt":"Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-specific action supervision. Since these models typically rely on VLM backbones optimized for Visual Question Answering (VQA), they excel at semantic identification but often overlook subtle 3D state variations that dictate distinct action patterns. To resolve these misalignments, we propose Pose-VLA, a decoupled paradigm that separates VLA training into a pre-training phase for extracting universal 3D spatial priors in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.19710","kind":"arxiv","version":2},"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/2602.19710/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":"2026-05-20T00:03:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SFMxNoL0UoCtUXME+vAKHnKqkhSsGBqVpnQM8Aenda841uI4G741ngMT+t//Pt9kYfTHx0w+ec+ClDKENFUFCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T08:31:32.117706Z"},"content_sha256":"d67b112823949b2fd79756ca8c1d494f91d87c3c449bbb988906d071f9bc017b","schema_version":"1.0","event_id":"sha256:d67b112823949b2fd79756ca8c1d494f91d87c3c449bbb988906d071f9bc017b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3X2GFYZFIOCQFLRLEZOPTB63Z2/bundle.json","state_url":"https://pith.science/pith/3X2GFYZFIOCQFLRLEZOPTB63Z2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3X2GFYZFIOCQFLRLEZOPTB63Z2/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":"2026-05-24T08:31:32Z","links":{"resolver":"https://pith.science/pith/3X2GFYZFIOCQFLRLEZOPTB63Z2","bundle":"https://pith.science/pith/3X2GFYZFIOCQFLRLEZOPTB63Z2/bundle.json","state":"https://pith.science/pith/3X2GFYZFIOCQFLRLEZOPTB63Z2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3X2GFYZFIOCQFLRLEZOPTB63Z2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3X2GFYZFIOCQFLRLEZOPTB63Z2","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":"b05b69419d03c5502be8c65cac55b1b016b5266b0b899cc5ce50fe7708dd6296","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-23T11:00:08Z","title_canon_sha256":"d1887ac83aa98df5c4eaa00d1662463d763ef0961ec56be17418f321fccc996c"},"schema_version":"1.0","source":{"id":"2602.19710","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.19710","created_at":"2026-05-20T00:03:06Z"},{"alias_kind":"arxiv_version","alias_value":"2602.19710v2","created_at":"2026-05-20T00:03:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.19710","created_at":"2026-05-20T00:03:06Z"},{"alias_kind":"pith_short_12","alias_value":"3X2GFYZFIOCQ","created_at":"2026-05-20T00:03:06Z"},{"alias_kind":"pith_short_16","alias_value":"3X2GFYZFIOCQFLRL","created_at":"2026-05-20T00:03:06Z"},{"alias_kind":"pith_short_8","alias_value":"3X2GFYZF","created_at":"2026-05-20T00:03:06Z"}],"graph_snapshots":[{"event_id":"sha256:d67b112823949b2fd79756ca8c1d494f91d87c3c449bbb988906d071f9bc017b","target":"graph","created_at":"2026-05-20T00:03:06Z","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/2602.19710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-specific action supervision. Since these models typically rely on VLM backbones optimized for Visual Question Answering (VQA), they excel at semantic identification but often overlook subtle 3D state variations that dictate distinct action patterns. To resolve these misalignments, we propose Pose-VLA, a decoupled paradigm that separates VLA training into a pre-training phase for extracting universal 3D spatial priors in ","authors_text":"Haitao Lin, Hanyang Yu, He Zhang, Jingshun Huang, Ping Tan, Xiangyang Xue, Yanwei Fu, Yonggen Ling","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-23T11:00:08Z","title":"Universal Pose Pretraining for Generalizable Vision-Language-Action Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.19710","kind":"arxiv","version":2},"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":"sha256:4d290148d07e605f0b8fd44014b3e665be166956a2e11cf79ab7f3884ed327e4","target":"record","created_at":"2026-05-20T00:03:06Z","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":"b05b69419d03c5502be8c65cac55b1b016b5266b0b899cc5ce50fe7708dd6296","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-23T11:00:08Z","title_canon_sha256":"d1887ac83aa98df5c4eaa00d1662463d763ef0961ec56be17418f321fccc996c"},"schema_version":"1.0","source":{"id":"2602.19710","kind":"arxiv","version":2}},"canonical_sha256":"ddf462e325438502ae2b265cf987dbce9da62cd435a94113889a64e00a328820","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddf462e325438502ae2b265cf987dbce9da62cd435a94113889a64e00a328820","first_computed_at":"2026-05-20T00:03:06.384872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:06.384872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rz3DDhOlR8UHr8NhytPX8vRzr1yssylPfLcCNui1mBxrTj1neG6hhb5h+TwcgMjydcSKpENurYJMPuRixATDBg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:06.385674Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.19710","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d290148d07e605f0b8fd44014b3e665be166956a2e11cf79ab7f3884ed327e4","sha256:d67b112823949b2fd79756ca8c1d494f91d87c3c449bbb988906d071f9bc017b"],"state_sha256":"4df052b4bfbe5fff09090000f1fc218b2adf7f4b7298f579010adda752fddd72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TuveN7km1O9tKEr3iGKnDcFxRpbX1kh7sO0KCR0ziMtQGTmCSuz/C+sNGZk0+Orig5xJQHtL1h92eWD42ztkAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T08:31:32.121466Z","bundle_sha256":"877ebe5cafa5cf4268ddbaaf2179e96e4221997812ef1caf7e5d47f2124d9918"}}