{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XJ2J2FBEQAQCDL2I32JPVNWMVW","short_pith_number":"pith:XJ2J2FBE","schema_version":"1.0","canonical_sha256":"ba749d1424802021af48de92fab6ccadbe4b1b1dc3dad5cfd3bce4dae3c8947f","source":{"kind":"arxiv","id":"2202.13536","version":2},"attestation_state":"computed","paper":{"title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Geon-Hyeong Kim, Hongseok Yang, Jongmin Lee, Kee-Eung Kim, Youngsoo Jang","submitted_at":"2022-02-28T04:24:30Z","abstract_excerpt":"We consider the problem of learning from observation (LfO), in which the agent aims to mimic the expert's behavior from the state-only demonstrations by experts. We additionally assume that the agent cannot interact with the environment but has access to the action-labeled transition data collected by some agents with unknown qualities. This offline setting for LfO is appealing in many real-world scenarios where the ground-truth expert actions are inaccessible and the arbitrary environment interactions are costly or risky. In this paper, we present LobsDICE, an offline LfO algorithm that learn"},"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":"2202.13536","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-28T04:24:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed1097630a6c96ccfccd50c2544d80fdcdb5bca8150059fb091e46e173b280b7","abstract_canon_sha256":"b04e3defbf2a67f9096ed7a68fd3408d6d47d7c03f2934ee5936139f3f9a1c0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:39.488541Z","signature_b64":"ZHf1f8Ly/6kqmRfS7ZTclQKBxOuEbiqlxwiDZ4YbNe1M/KZNsFM5QxMEa7ShjTLKDOHdCmtysIFpaYFwAsEbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba749d1424802021af48de92fab6ccadbe4b1b1dc3dad5cfd3bce4dae3c8947f","last_reissued_at":"2026-07-05T05:07:39.488090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:39.488090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Geon-Hyeong Kim, Hongseok Yang, Jongmin Lee, Kee-Eung Kim, Youngsoo Jang","submitted_at":"2022-02-28T04:24:30Z","abstract_excerpt":"We consider the problem of learning from observation (LfO), in which the agent aims to mimic the expert's behavior from the state-only demonstrations by experts. We additionally assume that the agent cannot interact with the environment but has access to the action-labeled transition data collected by some agents with unknown qualities. This offline setting for LfO is appealing in many real-world scenarios where the ground-truth expert actions are inaccessible and the arbitrary environment interactions are costly or risky. In this paper, we present LobsDICE, an offline LfO algorithm that learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.13536","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/2202.13536/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":"2202.13536","created_at":"2026-07-05T05:07:39.488145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.13536v2","created_at":"2026-07-05T05:07:39.488145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.13536","created_at":"2026-07-05T05:07:39.488145+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJ2J2FBEQAQC","created_at":"2026-07-05T05:07:39.488145+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJ2J2FBEQAQCDL2I","created_at":"2026-07-05T05:07:39.488145+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJ2J2FBE","created_at":"2026-07-05T05:07:39.488145+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05375","citing_title":"Fitted Occupancy-Ratio Evaluation without Bellman Completeness","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJ2J2FBEQAQCDL2I32JPVNWMVW","json":"https://pith.science/pith/XJ2J2FBEQAQCDL2I32JPVNWMVW.json","graph_json":"https://pith.science/api/pith-number/XJ2J2FBEQAQCDL2I32JPVNWMVW/graph.json","events_json":"https://pith.science/api/pith-number/XJ2J2FBEQAQCDL2I32JPVNWMVW/events.json","paper":"https://pith.science/paper/XJ2J2FBE"},"agent_actions":{"view_html":"https://pith.science/pith/XJ2J2FBEQAQCDL2I32JPVNWMVW","download_json":"https://pith.science/pith/XJ2J2FBEQAQCDL2I32JPVNWMVW.json","view_paper":"https://pith.science/paper/XJ2J2FBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.13536&json=true","fetch_graph":"https://pith.science/api/pith-number/XJ2J2FBEQAQCDL2I32JPVNWMVW/graph.json","fetch_events":"https://pith.science/api/pith-number/XJ2J2FBEQAQCDL2I32JPVNWMVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJ2J2FBEQAQCDL2I32JPVNWMVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJ2J2FBEQAQCDL2I32JPVNWMVW/action/storage_attestation","attest_author":"https://pith.science/pith/XJ2J2FBEQAQCDL2I32JPVNWMVW/action/author_attestation","sign_citation":"https://pith.science/pith/XJ2J2FBEQAQCDL2I32JPVNWMVW/action/citation_signature","submit_replication":"https://pith.science/pith/XJ2J2FBEQAQCDL2I32JPVNWMVW/action/replication_record"}},"created_at":"2026-07-05T05:07:39.488145+00:00","updated_at":"2026-07-05T05:07:39.488145+00:00"}