{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WRTOGX56WF52MQBEBUGI62DPAQ","short_pith_number":"pith:WRTOGX56","schema_version":"1.0","canonical_sha256":"b466e35fbeb17ba640240d0c8f686f0410c2518cf42382eb079d441a4150e4d6","source":{"kind":"arxiv","id":"2403.11940","version":2},"attestation_state":"computed","paper":{"title":"Multistep Inverse Is Not All You Need","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Alexander Levine, Amy Zhang, Peter Stone","submitted_at":"2024-03-18T16:36:01Z","abstract_excerpt":"In real-world control settings, the observation space is often unnecessarily high-dimensional and subject to time-correlated noise. However, the controllable dynamics of the system are often far simpler than the dynamics of the raw observations. It is therefore desirable to learn an encoder to map the observation space to a simpler space of control-relevant variables. In this work, we consider the Ex-BMDP model, first proposed by Efroni et al. (2022), which formalizes control problems where observations can be factorized into an action-dependent latent state which evolves deterministically, an"},"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":"2403.11940","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-18T16:36:01Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"f3cf7d27758fa315df9fbba78c52d0c85a1a5af210bde4b5e226cf7496b4b15a","abstract_canon_sha256":"60c0a25d3c8d1c145eb73702d75c5cdf521958268be6caa911842071f4eb7b71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:09.167206Z","signature_b64":"yc4/lyRNOtUyiQ5Qin2hXQ5dkmcV1ih41h+boFp4TTXBcYb/k7099y8lDr/N5KoxrnPGAfe7UJfq0DWMy7J0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b466e35fbeb17ba640240d0c8f686f0410c2518cf42382eb079d441a4150e4d6","last_reissued_at":"2026-07-05T09:04:09.166744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:09.166744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multistep Inverse Is Not All You Need","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Alexander Levine, Amy Zhang, Peter Stone","submitted_at":"2024-03-18T16:36:01Z","abstract_excerpt":"In real-world control settings, the observation space is often unnecessarily high-dimensional and subject to time-correlated noise. However, the controllable dynamics of the system are often far simpler than the dynamics of the raw observations. It is therefore desirable to learn an encoder to map the observation space to a simpler space of control-relevant variables. In this work, we consider the Ex-BMDP model, first proposed by Efroni et al. (2022), which formalizes control problems where observations can be factorized into an action-dependent latent state which evolves deterministically, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11940","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/2403.11940/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":"2403.11940","created_at":"2026-07-05T09:04:09.166805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11940v2","created_at":"2026-07-05T09:04:09.166805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11940","created_at":"2026-07-05T09:04:09.166805+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRTOGX56WF52","created_at":"2026-07-05T09:04:09.166805+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRTOGX56WF52MQBE","created_at":"2026-07-05T09:04:09.166805+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRTOGX56","created_at":"2026-07-05T09:04:09.166805+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00379","citing_title":"Latent Action Learning Requires Supervision in the Presence of Distractors","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WRTOGX56WF52MQBEBUGI62DPAQ","json":"https://pith.science/pith/WRTOGX56WF52MQBEBUGI62DPAQ.json","graph_json":"https://pith.science/api/pith-number/WRTOGX56WF52MQBEBUGI62DPAQ/graph.json","events_json":"https://pith.science/api/pith-number/WRTOGX56WF52MQBEBUGI62DPAQ/events.json","paper":"https://pith.science/paper/WRTOGX56"},"agent_actions":{"view_html":"https://pith.science/pith/WRTOGX56WF52MQBEBUGI62DPAQ","download_json":"https://pith.science/pith/WRTOGX56WF52MQBEBUGI62DPAQ.json","view_paper":"https://pith.science/paper/WRTOGX56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11940&json=true","fetch_graph":"https://pith.science/api/pith-number/WRTOGX56WF52MQBEBUGI62DPAQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WRTOGX56WF52MQBEBUGI62DPAQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRTOGX56WF52MQBEBUGI62DPAQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRTOGX56WF52MQBEBUGI62DPAQ/action/storage_attestation","attest_author":"https://pith.science/pith/WRTOGX56WF52MQBEBUGI62DPAQ/action/author_attestation","sign_citation":"https://pith.science/pith/WRTOGX56WF52MQBEBUGI62DPAQ/action/citation_signature","submit_replication":"https://pith.science/pith/WRTOGX56WF52MQBEBUGI62DPAQ/action/replication_record"}},"created_at":"2026-07-05T09:04:09.166805+00:00","updated_at":"2026-07-05T09:04:09.166805+00:00"}