{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MU5JKQEJCENCRJM6BCYFGFLD65","short_pith_number":"pith:MU5JKQEJ","schema_version":"1.0","canonical_sha256":"653a954089111a28a59e08b0531563f740a34abe0ce16584d455315775b1d556","source":{"kind":"arxiv","id":"1912.12612","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Variational Imitation Learning of Control Programs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dawn Song, Ion Stoica, Ken Goldberg, Pieter Abbeel, Richard Shin, Roy Fox, William Paul, Yitian Zou","submitted_at":"2019-12-29T08:57:02Z","abstract_excerpt":"Autonomous agents can learn by imitating teacher demonstrations of the intended behavior. Hierarchical control policies are ubiquitously useful for such learning, having the potential to break down structured tasks into simpler sub-tasks, thereby improving data efficiency and generalization. In this paper, we propose a variational inference method for imitation learning of a control policy represented by parametrized hierarchical procedures (PHP), a program-like structure in which procedures can invoke sub-procedures to perform sub-tasks. Our method discovers the hierarchical structure in a da"},"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":"1912.12612","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-29T08:57:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fdd458b593496cac04e71177b881d767eac31df95e8cc983585f4aa538f6fa69","abstract_canon_sha256":"41760e9b61d6e1eb7518890762c0a5eeec810ed0742c14f3dbe57cef817de718"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:29:01.786828Z","signature_b64":"wvvNcah+ve7423E6x0otjGrPK2IDAZXfd6PJNu435iWmnJ+kkVIOC38iJA2ggCYZ6Di0F7nifL1v9jJNrxSrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"653a954089111a28a59e08b0531563f740a34abe0ce16584d455315775b1d556","last_reissued_at":"2026-07-05T00:29:01.786353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:29:01.786353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Variational Imitation Learning of Control Programs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dawn Song, Ion Stoica, Ken Goldberg, Pieter Abbeel, Richard Shin, Roy Fox, William Paul, Yitian Zou","submitted_at":"2019-12-29T08:57:02Z","abstract_excerpt":"Autonomous agents can learn by imitating teacher demonstrations of the intended behavior. Hierarchical control policies are ubiquitously useful for such learning, having the potential to break down structured tasks into simpler sub-tasks, thereby improving data efficiency and generalization. In this paper, we propose a variational inference method for imitation learning of a control policy represented by parametrized hierarchical procedures (PHP), a program-like structure in which procedures can invoke sub-procedures to perform sub-tasks. Our method discovers the hierarchical structure in a da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.12612","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/1912.12612/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":"1912.12612","created_at":"2026-07-05T00:29:01.786408+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.12612v1","created_at":"2026-07-05T00:29:01.786408+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.12612","created_at":"2026-07-05T00:29:01.786408+00:00"},{"alias_kind":"pith_short_12","alias_value":"MU5JKQEJCENC","created_at":"2026-07-05T00:29:01.786408+00:00"},{"alias_kind":"pith_short_16","alias_value":"MU5JKQEJCENCRJM6","created_at":"2026-07-05T00:29:01.786408+00:00"},{"alias_kind":"pith_short_8","alias_value":"MU5JKQEJ","created_at":"2026-07-05T00:29:01.786408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25224","citing_title":"Spatio-Temporal Retrieval-based Priors for Adaptive Computational Teaching in Driving","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MU5JKQEJCENCRJM6BCYFGFLD65","json":"https://pith.science/pith/MU5JKQEJCENCRJM6BCYFGFLD65.json","graph_json":"https://pith.science/api/pith-number/MU5JKQEJCENCRJM6BCYFGFLD65/graph.json","events_json":"https://pith.science/api/pith-number/MU5JKQEJCENCRJM6BCYFGFLD65/events.json","paper":"https://pith.science/paper/MU5JKQEJ"},"agent_actions":{"view_html":"https://pith.science/pith/MU5JKQEJCENCRJM6BCYFGFLD65","download_json":"https://pith.science/pith/MU5JKQEJCENCRJM6BCYFGFLD65.json","view_paper":"https://pith.science/paper/MU5JKQEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.12612&json=true","fetch_graph":"https://pith.science/api/pith-number/MU5JKQEJCENCRJM6BCYFGFLD65/graph.json","fetch_events":"https://pith.science/api/pith-number/MU5JKQEJCENCRJM6BCYFGFLD65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MU5JKQEJCENCRJM6BCYFGFLD65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MU5JKQEJCENCRJM6BCYFGFLD65/action/storage_attestation","attest_author":"https://pith.science/pith/MU5JKQEJCENCRJM6BCYFGFLD65/action/author_attestation","sign_citation":"https://pith.science/pith/MU5JKQEJCENCRJM6BCYFGFLD65/action/citation_signature","submit_replication":"https://pith.science/pith/MU5JKQEJCENCRJM6BCYFGFLD65/action/replication_record"}},"created_at":"2026-07-05T00:29:01.786408+00:00","updated_at":"2026-07-05T00:29:01.786408+00:00"}