{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WINV7XAN64EBIEUVFIYMBFQLZO","short_pith_number":"pith:WINV7XAN","canonical_record":{"source":{"id":"2502.01784","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-03T19:55:57Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"be9822716d19b2f85b7f6674f6be1cc8ca93384dec5d23a379b0584d1b8ff494","abstract_canon_sha256":"cb8c2438c7b263be00137e0c65e716fdad71f4bb6ecef7864d7270d1e32d32e6"},"schema_version":"1.0"},"canonical_sha256":"b21b5fdc0df7081412952a30c0960bcb91704a02407e45f65a63633881997f11","source":{"kind":"arxiv","id":"2502.01784","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01784","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01784v1","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01784","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"WINV7XAN64EB","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"WINV7XAN64EBIEUV","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"WINV7XAN","created_at":"2026-07-05T10:09:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WINV7XAN64EBIEUVFIYMBFQLZO","target":"record","payload":{"canonical_record":{"source":{"id":"2502.01784","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-03T19:55:57Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"be9822716d19b2f85b7f6674f6be1cc8ca93384dec5d23a379b0584d1b8ff494","abstract_canon_sha256":"cb8c2438c7b263be00137e0c65e716fdad71f4bb6ecef7864d7270d1e32d32e6"},"schema_version":"1.0"},"canonical_sha256":"b21b5fdc0df7081412952a30c0960bcb91704a02407e45f65a63633881997f11","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:18.994541Z","signature_b64":"0IdRUTnwNZNk+yA6Cy+e/YXnibJFI6i+qhxsIZoFTLGAZeWddleCWsCxJGtJ42dPq94g5nGpb5WrxodmMLIAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b21b5fdc0df7081412952a30c0960bcb91704a02407e45f65a63633881997f11","last_reissued_at":"2026-07-05T10:09:18.994021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:18.994021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.01784","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":"2026-07-05T10:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FiKrzFVstQ6MNs0tqRlEZ3gxAfgRg5VM8ljDRQf/BWDXBqBG+HfkgYisUVJdtZ90X76rPyPqfbkkaq8z+xDjCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:49:54.945683Z"},"content_sha256":"a1bf88fddb004d2808a6daab9bd279aa26722cf1e9b5b69da39be48ddcdec466","schema_version":"1.0","event_id":"sha256:a1bf88fddb004d2808a6daab9bd279aa26722cf1e9b5b69da39be48ddcdec466"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WINV7XAN64EBIEUVFIYMBFQLZO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VILP: Imitation Learning with Latent Video Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Qiang Qiu, Yu She, Zhengtong Xu","submitted_at":"2025-02-03T19:55:57Z","abstract_excerpt":"In the era of generative AI, integrating video generation models into robotics opens new possibilities for the general-purpose robot agent. This paper introduces imitation learning with latent video planning (VILP). We propose a latent video diffusion model to generate predictive robot videos that adhere to temporal consistency to a good degree. Our method is able to generate highly time-aligned videos from multiple views, which is crucial for robot policy learning. Our video generation model is highly time-efficient. For example, it can generate videos from two distinct perspectives, each con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01784","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/2502.01784/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":"2026-07-05T10:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lX1fvDGH/9/3GOggp/houMxl3A/XJKgPB0UaYfgBgwGpZNCPTk6f6FvqSCh1lfm2x4h4dxh9RpI/EY6hNMh1Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:49:54.946173Z"},"content_sha256":"9b0b0ce004896b2573fba5dbc35a08ccfe0c5f057ab8cac824a7925b1e3fd300","schema_version":"1.0","event_id":"sha256:9b0b0ce004896b2573fba5dbc35a08ccfe0c5f057ab8cac824a7925b1e3fd300"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WINV7XAN64EBIEUVFIYMBFQLZO/bundle.json","state_url":"https://pith.science/pith/WINV7XAN64EBIEUVFIYMBFQLZO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WINV7XAN64EBIEUVFIYMBFQLZO/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":"2026-08-06T07:49:54Z","links":{"resolver":"https://pith.science/pith/WINV7XAN64EBIEUVFIYMBFQLZO","bundle":"https://pith.science/pith/WINV7XAN64EBIEUVFIYMBFQLZO/bundle.json","state":"https://pith.science/pith/WINV7XAN64EBIEUVFIYMBFQLZO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WINV7XAN64EBIEUVFIYMBFQLZO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WINV7XAN64EBIEUVFIYMBFQLZO","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":"cb8c2438c7b263be00137e0c65e716fdad71f4bb6ecef7864d7270d1e32d32e6","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-03T19:55:57Z","title_canon_sha256":"be9822716d19b2f85b7f6674f6be1cc8ca93384dec5d23a379b0584d1b8ff494"},"schema_version":"1.0","source":{"id":"2502.01784","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01784","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01784v1","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01784","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"WINV7XAN64EB","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"WINV7XAN64EBIEUV","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"WINV7XAN","created_at":"2026-07-05T10:09:18Z"}],"graph_snapshots":[{"event_id":"sha256:9b0b0ce004896b2573fba5dbc35a08ccfe0c5f057ab8cac824a7925b1e3fd300","target":"graph","created_at":"2026-07-05T10:09:18Z","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/2502.01784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the era of generative AI, integrating video generation models into robotics opens new possibilities for the general-purpose robot agent. This paper introduces imitation learning with latent video planning (VILP). We propose a latent video diffusion model to generate predictive robot videos that adhere to temporal consistency to a good degree. Our method is able to generate highly time-aligned videos from multiple views, which is crucial for robot policy learning. Our video generation model is highly time-efficient. For example, it can generate videos from two distinct perspectives, each con","authors_text":"Qiang Qiu, Yu She, Zhengtong Xu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-03T19:55:57Z","title":"VILP: Imitation Learning with Latent Video Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01784","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:a1bf88fddb004d2808a6daab9bd279aa26722cf1e9b5b69da39be48ddcdec466","target":"record","created_at":"2026-07-05T10:09:18Z","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":"cb8c2438c7b263be00137e0c65e716fdad71f4bb6ecef7864d7270d1e32d32e6","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-03T19:55:57Z","title_canon_sha256":"be9822716d19b2f85b7f6674f6be1cc8ca93384dec5d23a379b0584d1b8ff494"},"schema_version":"1.0","source":{"id":"2502.01784","kind":"arxiv","version":1}},"canonical_sha256":"b21b5fdc0df7081412952a30c0960bcb91704a02407e45f65a63633881997f11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b21b5fdc0df7081412952a30c0960bcb91704a02407e45f65a63633881997f11","first_computed_at":"2026-07-05T10:09:18.994021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:18.994021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0IdRUTnwNZNk+yA6Cy+e/YXnibJFI6i+qhxsIZoFTLGAZeWddleCWsCxJGtJ42dPq94g5nGpb5WrxodmMLIAAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:18.994541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01784","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1bf88fddb004d2808a6daab9bd279aa26722cf1e9b5b69da39be48ddcdec466","sha256:9b0b0ce004896b2573fba5dbc35a08ccfe0c5f057ab8cac824a7925b1e3fd300"],"state_sha256":"5d015e01e146b2772b2cb5eaa9c74eddb48e2290b1e2d8355621e6b3e489cf7c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OEz/sJrnMOI781eUPkoiZWhE3cgiKJdnddkOUZGA0OMeGNgoyYny8qWnWFcxI/ZEsvcEvNcXHpt8tTzBOqZkBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:49:54.949871Z","bundle_sha256":"63f48884ae80c1fd14e46ab1076ec961b21f44f1f8f1889e66c0558feb570a6e"}}