{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OMNQHEXE7EJCPBAGUWFORCCHFH","short_pith_number":"pith:OMNQHEXE","schema_version":"1.0","canonical_sha256":"731b0392e4f912278406a58ae8884729c197395fcad04896e287a029c914b1ec","source":{"kind":"arxiv","id":"2302.03086","version":2},"attestation_state":"computed","paper":{"title":"DITTO: Offline Imitation Learning with World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Branton DeMoss, Ingmar Posner, Jakob Foerster, Nick Hawes, Paul Duckworth","submitted_at":"2023-02-06T19:41:18Z","abstract_excerpt":"For imitation learning algorithms to scale to real-world challenges, they must handle high-dimensional observations, offline learning, and policy-induced covariate-shift. We propose DITTO, an offline imitation learning algorithm which addresses all three of these problems. DITTO optimizes a novel distance metric in the latent space of a learned world model: First, we train a world model on all available trajectory data, then, the imitation agent is unrolled from expert start states in the learned model, and penalized for its latent divergence from the expert dataset over multiple time steps. W"},"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":"2302.03086","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T19:41:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7a09b84cfc762d771aef8effd9c1eb13c1cc06b565a8e9db8d88c84dfa7ef28a","abstract_canon_sha256":"17dff7722ac8e0c1099b1382dff0f17a26e28ec375a0b1c421baef13c3d08a94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:20.619617Z","signature_b64":"HG/Aq2Fc7SyzdBgVcZqJvzHyU8b11PhN3z6PdgJojwtdx/kjjlNlLLpE0oIHiBwYcD25JPsrYx8XiZgE5dIFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"731b0392e4f912278406a58ae8884729c197395fcad04896e287a029c914b1ec","last_reissued_at":"2026-07-05T10:36:20.619114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:20.619114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DITTO: Offline Imitation Learning with World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Branton DeMoss, Ingmar Posner, Jakob Foerster, Nick Hawes, Paul Duckworth","submitted_at":"2023-02-06T19:41:18Z","abstract_excerpt":"For imitation learning algorithms to scale to real-world challenges, they must handle high-dimensional observations, offline learning, and policy-induced covariate-shift. We propose DITTO, an offline imitation learning algorithm which addresses all three of these problems. DITTO optimizes a novel distance metric in the latent space of a learned world model: First, we train a world model on all available trajectory data, then, the imitation agent is unrolled from expert start states in the learned model, and penalized for its latent divergence from the expert dataset over multiple time steps. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03086","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/2302.03086/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":"2302.03086","created_at":"2026-07-05T10:36:20.619171+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.03086v2","created_at":"2026-07-05T10:36:20.619171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03086","created_at":"2026-07-05T10:36:20.619171+00:00"},{"alias_kind":"pith_short_12","alias_value":"OMNQHEXE7EJC","created_at":"2026-07-05T10:36:20.619171+00:00"},{"alias_kind":"pith_short_16","alias_value":"OMNQHEXE7EJCPBAG","created_at":"2026-07-05T10:36:20.619171+00:00"},{"alias_kind":"pith_short_8","alias_value":"OMNQHEXE","created_at":"2026-07-05T10:36:20.619171+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OMNQHEXE7EJCPBAGUWFORCCHFH","json":"https://pith.science/pith/OMNQHEXE7EJCPBAGUWFORCCHFH.json","graph_json":"https://pith.science/api/pith-number/OMNQHEXE7EJCPBAGUWFORCCHFH/graph.json","events_json":"https://pith.science/api/pith-number/OMNQHEXE7EJCPBAGUWFORCCHFH/events.json","paper":"https://pith.science/paper/OMNQHEXE"},"agent_actions":{"view_html":"https://pith.science/pith/OMNQHEXE7EJCPBAGUWFORCCHFH","download_json":"https://pith.science/pith/OMNQHEXE7EJCPBAGUWFORCCHFH.json","view_paper":"https://pith.science/paper/OMNQHEXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.03086&json=true","fetch_graph":"https://pith.science/api/pith-number/OMNQHEXE7EJCPBAGUWFORCCHFH/graph.json","fetch_events":"https://pith.science/api/pith-number/OMNQHEXE7EJCPBAGUWFORCCHFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OMNQHEXE7EJCPBAGUWFORCCHFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OMNQHEXE7EJCPBAGUWFORCCHFH/action/storage_attestation","attest_author":"https://pith.science/pith/OMNQHEXE7EJCPBAGUWFORCCHFH/action/author_attestation","sign_citation":"https://pith.science/pith/OMNQHEXE7EJCPBAGUWFORCCHFH/action/citation_signature","submit_replication":"https://pith.science/pith/OMNQHEXE7EJCPBAGUWFORCCHFH/action/replication_record"}},"created_at":"2026-07-05T10:36:20.619171+00:00","updated_at":"2026-07-05T10:36:20.619171+00:00"}