{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FDHCNYFNNQJWA4S47Z7HVF3Y7O","short_pith_number":"pith:FDHCNYFN","schema_version":"1.0","canonical_sha256":"28ce26e0ad6c1360725cfe7e7a9778fb84228185711292953b9f33abe6fabe33","source":{"kind":"arxiv","id":"2207.05824","version":1},"attestation_state":"computed","paper":{"title":"Conditional Energy-Based Models for Implicit Policies: The Gap between Theory and Practice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Duy-Nguyen Ta, Eric Cousineau, Huihua Zhao, Siyuan Feng","submitted_at":"2022-07-12T20:35:38Z","abstract_excerpt":"We present our findings in the gap between theory and practice of using conditional energy-based models (EBM) as an implicit representation for behavior-cloned policies. We also clarify several subtle, and potentially confusing, details in previous work in an attempt to help future research in this area. We point out key differences between unconditional and conditional EBMs, and warn that blindly applying training methods for one to the other could lead to undesirable results that do not generalize well. Finally, we emphasize the importance of the Maximum Mutual Information principle as a nec"},"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":"2207.05824","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-07-12T20:35:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"050078aac73a54f1732515bf9f06d6e25f49d93929c49b0542c3db594e774163","abstract_canon_sha256":"2e16c8b75e33e9f9be6b11b388ec0b7a64fc1f1f9a3e6f20506bdad56f1a7ecc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:51.935665Z","signature_b64":"uqHzteGVUVCv5Z836FqYv336AIvYNn6T1J5c/TobooV+9VtPWJNHpewvBGF15Sg95DvbUeSLXqg3fOtNRtOKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28ce26e0ad6c1360725cfe7e7a9778fb84228185711292953b9f33abe6fabe33","last_reissued_at":"2026-07-05T04:39:51.935171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:51.935171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditional Energy-Based Models for Implicit Policies: The Gap between Theory and Practice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Duy-Nguyen Ta, Eric Cousineau, Huihua Zhao, Siyuan Feng","submitted_at":"2022-07-12T20:35:38Z","abstract_excerpt":"We present our findings in the gap between theory and practice of using conditional energy-based models (EBM) as an implicit representation for behavior-cloned policies. We also clarify several subtle, and potentially confusing, details in previous work in an attempt to help future research in this area. We point out key differences between unconditional and conditional EBMs, and warn that blindly applying training methods for one to the other could lead to undesirable results that do not generalize well. Finally, we emphasize the importance of the Maximum Mutual Information principle as a nec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.05824","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/2207.05824/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":"2207.05824","created_at":"2026-07-05T04:39:51.935230+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.05824v1","created_at":"2026-07-05T04:39:51.935230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05824","created_at":"2026-07-05T04:39:51.935230+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDHCNYFNNQJW","created_at":"2026-07-05T04:39:51.935230+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDHCNYFNNQJWA4S4","created_at":"2026-07-05T04:39:51.935230+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDHCNYFN","created_at":"2026-07-05T04:39:51.935230+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.07645","citing_title":"From Action Labels to Sets: Rethinking Action Supervision for Imitation Learning from Corrective Feedback","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2303.04137","citing_title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDHCNYFNNQJWA4S47Z7HVF3Y7O","json":"https://pith.science/pith/FDHCNYFNNQJWA4S47Z7HVF3Y7O.json","graph_json":"https://pith.science/api/pith-number/FDHCNYFNNQJWA4S47Z7HVF3Y7O/graph.json","events_json":"https://pith.science/api/pith-number/FDHCNYFNNQJWA4S47Z7HVF3Y7O/events.json","paper":"https://pith.science/paper/FDHCNYFN"},"agent_actions":{"view_html":"https://pith.science/pith/FDHCNYFNNQJWA4S47Z7HVF3Y7O","download_json":"https://pith.science/pith/FDHCNYFNNQJWA4S47Z7HVF3Y7O.json","view_paper":"https://pith.science/paper/FDHCNYFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.05824&json=true","fetch_graph":"https://pith.science/api/pith-number/FDHCNYFNNQJWA4S47Z7HVF3Y7O/graph.json","fetch_events":"https://pith.science/api/pith-number/FDHCNYFNNQJWA4S47Z7HVF3Y7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDHCNYFNNQJWA4S47Z7HVF3Y7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDHCNYFNNQJWA4S47Z7HVF3Y7O/action/storage_attestation","attest_author":"https://pith.science/pith/FDHCNYFNNQJWA4S47Z7HVF3Y7O/action/author_attestation","sign_citation":"https://pith.science/pith/FDHCNYFNNQJWA4S47Z7HVF3Y7O/action/citation_signature","submit_replication":"https://pith.science/pith/FDHCNYFNNQJWA4S47Z7HVF3Y7O/action/replication_record"}},"created_at":"2026-07-05T04:39:51.935230+00:00","updated_at":"2026-07-05T04:39:51.935230+00:00"}