{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZARD27V76RNBZ5IFD7F5FHBUYV","short_pith_number":"pith:ZARD27V7","canonical_record":{"source":{"id":"2602.03668","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-03T15:51:25Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"dadabbac91cc2e0b0c79aceb634cafd2e709dfa00da201181bf898701319c8a7","abstract_canon_sha256":"45e4aaeaa709cd485cc2eb7893f6e4469d4d6f62a8ed77de72c0efa5046b2dd0"},"schema_version":"1.0"},"canonical_sha256":"c8223d7ebff45a1cf5051fcbd29c34c55f934fd57294adb660f11ef5352b8c3b","source":{"kind":"arxiv","id":"2602.03668","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.03668","created_at":"2026-05-28T01:04:36Z"},{"alias_kind":"arxiv_version","alias_value":"2602.03668v3","created_at":"2026-05-28T01:04:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03668","created_at":"2026-05-28T01:04:36Z"},{"alias_kind":"pith_short_12","alias_value":"ZARD27V76RNB","created_at":"2026-05-28T01:04:36Z"},{"alias_kind":"pith_short_16","alias_value":"ZARD27V76RNBZ5IF","created_at":"2026-05-28T01:04:36Z"},{"alias_kind":"pith_short_8","alias_value":"ZARD27V7","created_at":"2026-05-28T01:04:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZARD27V76RNBZ5IFD7F5FHBUYV","target":"record","payload":{"canonical_record":{"source":{"id":"2602.03668","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-03T15:51:25Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"dadabbac91cc2e0b0c79aceb634cafd2e709dfa00da201181bf898701319c8a7","abstract_canon_sha256":"45e4aaeaa709cd485cc2eb7893f6e4469d4d6f62a8ed77de72c0efa5046b2dd0"},"schema_version":"1.0"},"canonical_sha256":"c8223d7ebff45a1cf5051fcbd29c34c55f934fd57294adb660f11ef5352b8c3b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:36.264470Z","signature_b64":"sdJ9AvZXezzT778XkE01+YVKGCmeGsVjnXMM2TbwF2z4wp6ogSZ1c4S1k4ZnyeRzlbQ+4Vr3VY1ae37vZ42dBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8223d7ebff45a1cf5051fcbd29c34c55f934fd57294adb660f11ef5352b8c3b","last_reissued_at":"2026-05-28T01:04:36.264068Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:36.264068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.03668","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:04:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UoynSE5xD8+N4p+0b/ZcwTboj8emBRV5iFgNX/oXMUBdKXdsjkk0Aq3usSQWsJIXi8w2EJxWIR7uzXiN9d/qCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T12:15:50.957179Z"},"content_sha256":"ef163024d5a3daaf1265bb1e137c59221c682889e7b308520f66389878a6b367","schema_version":"1.0","event_id":"sha256:ef163024d5a3daaf1265bb1e137c59221c682889e7b308520f66389878a6b367"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZARD27V76RNBZ5IFD7F5FHBUYV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Cross-viewpoint reconstruction trains latent actions to capture underlying robot actions rather than camera-specific details.","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Dohyeok Lee, Jin Woo Koo, Jung Min Lee, Jungwoo Lee, Li Zhao, Sangwoo Hong, Seokhun Ju, Taehyun Cho","submitted_at":"2026-02-03T15:51:25Z","abstract_excerpt":"Latent actions learned from diverse human videos serve as pseudo-labels for vision-language-action (VLA) pretraining, but provide effective supervision only if they remain informative about the underlying ground-truth actions. For effective supervision, latent actions should contain information about the underlying actions even though they are inaccessible. We propose Multi-ViewPoint Latent Action Moel (MVP-LAM), which learns latent actions that are highly informative about ground-truth actions from multi-view videos. MVP-LAM trains latent actions with a cross-viewpoint reconstruction objectiv"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MVP-LAM produces more action-centric latent actions, achieving higher mutual information with ground-truth actions and improved action prediction, including under out-of-distribution evaluation. Finally, pretraining VLAs with MVP-LAM latent actions improves downstream manipulation performance on various benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That forcing a latent action from one viewpoint to explain the future in another viewpoint will make the latent action contain information about the underlying ground-truth actions rather than viewpoint-specific cues.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MVP-LAM learns action-centric latent actions from multi-view videos via cross-viewpoint reconstruction, yielding higher mutual information with ground-truth actions and improved downstream VLA manipulation performance.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Cross-viewpoint reconstruction trains latent actions to capture underlying robot actions rather than camera-specific details.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e9f85e4e3c684adf15bd89c51595407fc5614ba562c36a381fa0d59d78391f3d"},"source":{"id":"2602.03668","kind":"arxiv","version":3},"verdict":{"id":"4791e08e-34dd-42c2-a1ad-5cfcd5a82804","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T07:47:36.715161Z","strongest_claim":"MVP-LAM produces more action-centric latent actions, achieving higher mutual information with ground-truth actions and improved action prediction, including under out-of-distribution evaluation. Finally, pretraining VLAs with MVP-LAM latent actions improves downstream manipulation performance on various benchmarks.","one_line_summary":"MVP-LAM learns action-centric latent actions from multi-view videos via cross-viewpoint reconstruction, yielding higher mutual information with ground-truth actions and improved downstream VLA manipulation performance.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That forcing a latent action from one viewpoint to explain the future in another viewpoint will make the latent action contain information about the underlying ground-truth actions rather than viewpoint-specific cues.","pith_extraction_headline":"Cross-viewpoint reconstruction trains latent actions to capture underlying robot actions rather than camera-specific details."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.03668/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":2,"snapshot_sha256":"73afbef700494a2e36d6b5812d9ab7e286420d4f39f91637ba681de9fddad6f1"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"4791e08e-34dd-42c2-a1ad-5cfcd5a82804"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-28T01:04:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AQpv2nnm+SnX0VVc86RG16zXCYkyTzQofS8MrD8XiPfWC5nWwKVjFGM+9UcR+vUxcaiMJ7wLRN/PlDLdlTzxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T12:15:50.957659Z"},"content_sha256":"e80fd6fc70154a0822efa42be2d8e1f0a7c7f42245f8c703d03104f46eb570ad","schema_version":"1.0","event_id":"sha256:e80fd6fc70154a0822efa42be2d8e1f0a7c7f42245f8c703d03104f46eb570ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZARD27V76RNBZ5IFD7F5FHBUYV/bundle.json","state_url":"https://pith.science/pith/ZARD27V76RNBZ5IFD7F5FHBUYV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZARD27V76RNBZ5IFD7F5FHBUYV/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":"2026-06-20T12:15:50Z","links":{"resolver":"https://pith.science/pith/ZARD27V76RNBZ5IFD7F5FHBUYV","bundle":"https://pith.science/pith/ZARD27V76RNBZ5IFD7F5FHBUYV/bundle.json","state":"https://pith.science/pith/ZARD27V76RNBZ5IFD7F5FHBUYV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZARD27V76RNBZ5IFD7F5FHBUYV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZARD27V76RNBZ5IFD7F5FHBUYV","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":"45e4aaeaa709cd485cc2eb7893f6e4469d4d6f62a8ed77de72c0efa5046b2dd0","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-03T15:51:25Z","title_canon_sha256":"dadabbac91cc2e0b0c79aceb634cafd2e709dfa00da201181bf898701319c8a7"},"schema_version":"1.0","source":{"id":"2602.03668","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.03668","created_at":"2026-05-28T01:04:36Z"},{"alias_kind":"arxiv_version","alias_value":"2602.03668v3","created_at":"2026-05-28T01:04:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03668","created_at":"2026-05-28T01:04:36Z"},{"alias_kind":"pith_short_12","alias_value":"ZARD27V76RNB","created_at":"2026-05-28T01:04:36Z"},{"alias_kind":"pith_short_16","alias_value":"ZARD27V76RNBZ5IF","created_at":"2026-05-28T01:04:36Z"},{"alias_kind":"pith_short_8","alias_value":"ZARD27V7","created_at":"2026-05-28T01:04:36Z"}],"graph_snapshots":[{"event_id":"sha256:e80fd6fc70154a0822efa42be2d8e1f0a7c7f42245f8c703d03104f46eb570ad","target":"graph","created_at":"2026-05-28T01:04:36Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"MVP-LAM produces more action-centric latent actions, achieving higher mutual information with ground-truth actions and improved action prediction, including under out-of-distribution evaluation. Finally, pretraining VLAs with MVP-LAM latent actions improves downstream manipulation performance on various benchmarks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That forcing a latent action from one viewpoint to explain the future in another viewpoint will make the latent action contain information about the underlying ground-truth actions rather than viewpoint-specific cues."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MVP-LAM learns action-centric latent actions from multi-view videos via cross-viewpoint reconstruction, yielding higher mutual information with ground-truth actions and improved downstream VLA manipulation performance."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Cross-viewpoint reconstruction trains latent actions to capture underlying robot actions rather than camera-specific details."}],"snapshot_sha256":"e9f85e4e3c684adf15bd89c51595407fc5614ba562c36a381fa0d59d78391f3d"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"73afbef700494a2e36d6b5812d9ab7e286420d4f39f91637ba681de9fddad6f1"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.03668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Latent actions learned from diverse human videos serve as pseudo-labels for vision-language-action (VLA) pretraining, but provide effective supervision only if they remain informative about the underlying ground-truth actions. For effective supervision, latent actions should contain information about the underlying actions even though they are inaccessible. We propose Multi-ViewPoint Latent Action Moel (MVP-LAM), which learns latent actions that are highly informative about ground-truth actions from multi-view videos. MVP-LAM trains latent actions with a cross-viewpoint reconstruction objectiv","authors_text":"Dohyeok Lee, Jin Woo Koo, Jung Min Lee, Jungwoo Lee, Li Zhao, Sangwoo Hong, Seokhun Ju, Taehyun Cho","cross_cats":["cs.CV"],"headline":"Cross-viewpoint reconstruction trains latent actions to capture underlying robot actions rather than camera-specific details.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-03T15:51:25Z","title":"MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.03668","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T07:47:36.715161Z","id":"4791e08e-34dd-42c2-a1ad-5cfcd5a82804","model_set":{"reader":"grok-4.3"},"one_line_summary":"MVP-LAM learns action-centric latent actions from multi-view videos via cross-viewpoint reconstruction, yielding higher mutual information with ground-truth actions and improved downstream VLA manipulation performance.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Cross-viewpoint reconstruction trains latent actions to capture underlying robot actions rather than camera-specific details.","strongest_claim":"MVP-LAM produces more action-centric latent actions, achieving higher mutual information with ground-truth actions and improved action prediction, including under out-of-distribution evaluation. Finally, pretraining VLAs with MVP-LAM latent actions improves downstream manipulation performance on various benchmarks.","weakest_assumption":"That forcing a latent action from one viewpoint to explain the future in another viewpoint will make the latent action contain information about the underlying ground-truth actions rather than viewpoint-specific cues."}},"verdict_id":"4791e08e-34dd-42c2-a1ad-5cfcd5a82804"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ef163024d5a3daaf1265bb1e137c59221c682889e7b308520f66389878a6b367","target":"record","created_at":"2026-05-28T01:04:36Z","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":"45e4aaeaa709cd485cc2eb7893f6e4469d4d6f62a8ed77de72c0efa5046b2dd0","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-03T15:51:25Z","title_canon_sha256":"dadabbac91cc2e0b0c79aceb634cafd2e709dfa00da201181bf898701319c8a7"},"schema_version":"1.0","source":{"id":"2602.03668","kind":"arxiv","version":3}},"canonical_sha256":"c8223d7ebff45a1cf5051fcbd29c34c55f934fd57294adb660f11ef5352b8c3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8223d7ebff45a1cf5051fcbd29c34c55f934fd57294adb660f11ef5352b8c3b","first_computed_at":"2026-05-28T01:04:36.264068Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:36.264068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sdJ9AvZXezzT778XkE01+YVKGCmeGsVjnXMM2TbwF2z4wp6ogSZ1c4S1k4ZnyeRzlbQ+4Vr3VY1ae37vZ42dBg==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:36.264470Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.03668","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef163024d5a3daaf1265bb1e137c59221c682889e7b308520f66389878a6b367","sha256:e80fd6fc70154a0822efa42be2d8e1f0a7c7f42245f8c703d03104f46eb570ad"],"state_sha256":"efac780c1f739e3337e9a03a2f655f315c392644a70eacf189c923058e8d0f5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1z/MRhg3b2vlBSDZQsTQEgac77rondixQ32LtKX7z1j015rxd2Fn1L1L3HB0mYKJ7mmdm5i0hn0pMvpauVIICw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T12:15:50.959795Z","bundle_sha256":"1a35c980a9c008d08cfa9a7010bd810ff0038750cb11a89dbfb82de7e7b0ce6d"}}