{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MFTHSW7OULOOGDAD4IWMVMUJ7K","short_pith_number":"pith:MFTHSW7O","schema_version":"1.0","canonical_sha256":"6166795beea2dce30c03e22ccab289fa8babd6d778f01ff66965b45ae2f105c1","source":{"kind":"arxiv","id":"2504.16925","version":1},"attestation_state":"computed","paper":{"title":"Latent Diffusion Planning for Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Amber Xie, Chelsea Finn, Dorsa Sadigh, Oleh Rybkin","submitted_at":"2025-04-23T17:53:34Z","abstract_excerpt":"Recent progress in imitation learning has been enabled by policy architectures that scale to complex visuomotor tasks, multimodal distributions, and large datasets. However, these methods often rely on learning from large amount of expert demonstrations. To address these shortcomings, we propose Latent Diffusion Planning (LDP), a modular approach consisting of a planner which can leverage action-free demonstrations, and an inverse dynamics model which can leverage suboptimal data, that both operate over a learned latent space. First, we learn a compact latent space through a variational autoen"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.16925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-04-23T17:53:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"15d9925e92a96e1c57e01e4d7a9ec87509512f17581875546b4d040d0083dc5e","abstract_canon_sha256":"368d0194ba09195539aa31da4bb8fb5ee27647cc54029f9aa96489ef17c3d1c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:06.559493Z","signature_b64":"YxTEZBl+ac4xcSz+UNbcP0zy6+w7gZUOusjSXTtqyFDJYwVfD2GRsPbGQaaY7kcwhv56FUXfpCoSgOI8GxkIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6166795beea2dce30c03e22ccab289fa8babd6d778f01ff66965b45ae2f105c1","last_reissued_at":"2026-07-05T10:53:06.559017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:06.559017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Diffusion Planning for Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Amber Xie, Chelsea Finn, Dorsa Sadigh, Oleh Rybkin","submitted_at":"2025-04-23T17:53:34Z","abstract_excerpt":"Recent progress in imitation learning has been enabled by policy architectures that scale to complex visuomotor tasks, multimodal distributions, and large datasets. However, these methods often rely on learning from large amount of expert demonstrations. To address these shortcomings, we propose Latent Diffusion Planning (LDP), a modular approach consisting of a planner which can leverage action-free demonstrations, and an inverse dynamics model which can leverage suboptimal data, that both operate over a learned latent space. First, we learn a compact latent space through a variational autoen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16925","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/2504.16925/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.16925","created_at":"2026-07-05T10:53:06.559075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16925v1","created_at":"2026-07-05T10:53:06.559075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16925","created_at":"2026-07-05T10:53:06.559075+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFTHSW7OULOO","created_at":"2026-07-05T10:53:06.559075+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFTHSW7OULOOGDAD","created_at":"2026-07-05T10:53:06.559075+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFTHSW7O","created_at":"2026-07-05T10:53:06.559075+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01166","citing_title":"Structured 4D Latent Predictive Model for Robot Planning","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08732","citing_title":"Latent Geometry Beyond Search: Amortizing Planning in World Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25620","citing_title":"Back to Parsimonious Latents: Learning Task-Centric World Models from Visual Foundations","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25829","citing_title":"OASIS: Observation-Action Space Alignment via SE(3) Trajectory Prediction for Robotic Manipulation","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2511.02776","citing_title":"XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":195,"is_internal_anchor":false},{"citing_arxiv_id":"2603.15759","citing_title":"Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08732","citing_title":"Latent Geometry Beyond Search: Amortizing Planning in World Models","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MFTHSW7OULOOGDAD4IWMVMUJ7K","json":"https://pith.science/pith/MFTHSW7OULOOGDAD4IWMVMUJ7K.json","graph_json":"https://pith.science/api/pith-number/MFTHSW7OULOOGDAD4IWMVMUJ7K/graph.json","events_json":"https://pith.science/api/pith-number/MFTHSW7OULOOGDAD4IWMVMUJ7K/events.json","paper":"https://pith.science/paper/MFTHSW7O"},"agent_actions":{"view_html":"https://pith.science/pith/MFTHSW7OULOOGDAD4IWMVMUJ7K","download_json":"https://pith.science/pith/MFTHSW7OULOOGDAD4IWMVMUJ7K.json","view_paper":"https://pith.science/paper/MFTHSW7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16925&json=true","fetch_graph":"https://pith.science/api/pith-number/MFTHSW7OULOOGDAD4IWMVMUJ7K/graph.json","fetch_events":"https://pith.science/api/pith-number/MFTHSW7OULOOGDAD4IWMVMUJ7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFTHSW7OULOOGDAD4IWMVMUJ7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFTHSW7OULOOGDAD4IWMVMUJ7K/action/storage_attestation","attest_author":"https://pith.science/pith/MFTHSW7OULOOGDAD4IWMVMUJ7K/action/author_attestation","sign_citation":"https://pith.science/pith/MFTHSW7OULOOGDAD4IWMVMUJ7K/action/citation_signature","submit_replication":"https://pith.science/pith/MFTHSW7OULOOGDAD4IWMVMUJ7K/action/replication_record"}},"created_at":"2026-07-05T10:53:06.559075+00:00","updated_at":"2026-07-05T10:53:06.559075+00:00"}