{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JI7MBLKUAT2FFPENGQGM7SHQX7","short_pith_number":"pith:JI7MBLKU","schema_version":"1.0","canonical_sha256":"4a3ec0ad5404f452bc8d340ccfc8f0bfc3c353f4d89bc4fa3ecfa2886c0fb7ad","source":{"kind":"arxiv","id":"2202.01862","version":2},"attestation_state":"computed","paper":{"title":"Practical Imitation Learning in the Real World via Task Consistency Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Armando Fuentes, Daniel Ho, Eric Jang, Matthew Bennice, Mohi Khansari, Nicolas Sievers, Sean Kirmani, Yunfei Bai, Yuqing Du","submitted_at":"2022-02-03T21:43:06Z","abstract_excerpt":"Recent work in visual end-to-end learning for robotics has shown the promise of imitation learning across a variety of tasks. Such approaches are expensive both because they require large amounts of real world training demonstrations and because identifying the best model to deploy in the real world requires time-consuming real-world evaluations. These challenges can be mitigated by simulation: by supplementing real world data with simulated demonstrations and using simulated evaluations to identify high performing policies. However, this introduces the well-known \"reality gap\" problem, where "},"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":"2202.01862","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-02-03T21:43:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"23b84d954c27ef08a88ba1d42cbc3e9e1dd0cf8d1b4215d3cbadcd4914846ad1","abstract_canon_sha256":"ea8920c58c2804705cf42f09df9ea75f0d517745a0e873e4980f494ff87421a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:40.862729Z","signature_b64":"lWLTT/YExJ2qJ7t+e8rvWHbtqJfkllIEXR5sRkmONC4Up2KhbSlD28vgfxSOPWnbH9si/RSAp54E/iKVapDXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a3ec0ad5404f452bc8d340ccfc8f0bfc3c353f4d89bc4fa3ecfa2886c0fb7ad","last_reissued_at":"2026-07-05T04:02:40.862277Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:40.862277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Practical Imitation Learning in the Real World via Task Consistency Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Armando Fuentes, Daniel Ho, Eric Jang, Matthew Bennice, Mohi Khansari, Nicolas Sievers, Sean Kirmani, Yunfei Bai, Yuqing Du","submitted_at":"2022-02-03T21:43:06Z","abstract_excerpt":"Recent work in visual end-to-end learning for robotics has shown the promise of imitation learning across a variety of tasks. Such approaches are expensive both because they require large amounts of real world training demonstrations and because identifying the best model to deploy in the real world requires time-consuming real-world evaluations. These challenges can be mitigated by simulation: by supplementing real world data with simulated demonstrations and using simulated evaluations to identify high performing policies. However, this introduces the well-known \"reality gap\" problem, where "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.01862","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/2202.01862/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":"2202.01862","created_at":"2026-07-05T04:02:40.862335+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.01862v2","created_at":"2026-07-05T04:02:40.862335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.01862","created_at":"2026-07-05T04:02:40.862335+00:00"},{"alias_kind":"pith_short_12","alias_value":"JI7MBLKUAT2F","created_at":"2026-07-05T04:02:40.862335+00:00"},{"alias_kind":"pith_short_16","alias_value":"JI7MBLKUAT2FFPEN","created_at":"2026-07-05T04:02:40.862335+00:00"},{"alias_kind":"pith_short_8","alias_value":"JI7MBLKU","created_at":"2026-07-05T04:02:40.862335+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.17596","citing_title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JI7MBLKUAT2FFPENGQGM7SHQX7","json":"https://pith.science/pith/JI7MBLKUAT2FFPENGQGM7SHQX7.json","graph_json":"https://pith.science/api/pith-number/JI7MBLKUAT2FFPENGQGM7SHQX7/graph.json","events_json":"https://pith.science/api/pith-number/JI7MBLKUAT2FFPENGQGM7SHQX7/events.json","paper":"https://pith.science/paper/JI7MBLKU"},"agent_actions":{"view_html":"https://pith.science/pith/JI7MBLKUAT2FFPENGQGM7SHQX7","download_json":"https://pith.science/pith/JI7MBLKUAT2FFPENGQGM7SHQX7.json","view_paper":"https://pith.science/paper/JI7MBLKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.01862&json=true","fetch_graph":"https://pith.science/api/pith-number/JI7MBLKUAT2FFPENGQGM7SHQX7/graph.json","fetch_events":"https://pith.science/api/pith-number/JI7MBLKUAT2FFPENGQGM7SHQX7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JI7MBLKUAT2FFPENGQGM7SHQX7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JI7MBLKUAT2FFPENGQGM7SHQX7/action/storage_attestation","attest_author":"https://pith.science/pith/JI7MBLKUAT2FFPENGQGM7SHQX7/action/author_attestation","sign_citation":"https://pith.science/pith/JI7MBLKUAT2FFPENGQGM7SHQX7/action/citation_signature","submit_replication":"https://pith.science/pith/JI7MBLKUAT2FFPENGQGM7SHQX7/action/replication_record"}},"created_at":"2026-07-05T04:02:40.862335+00:00","updated_at":"2026-07-05T04:02:40.862335+00:00"}