{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TBOU43HGYZK7ISL4VKJ5P4OTUJ","short_pith_number":"pith:TBOU43HG","schema_version":"1.0","canonical_sha256":"985d4e6ce6c655f4497caa93d7f1d3a274ebaa79f045fe3664f0e01b90e296b0","source":{"kind":"arxiv","id":"1804.08606","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Visual Imitation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexei A. Efros, Deepak Pathak, Dian Chen, Evan Shelhamer, Guanghao Luo, Jitendra Malik, Parsa Mahmoudieh, Pulkit Agrawal, Trevor Darrell, Yide Shentu","submitted_at":"2018-04-23T17:58:26Z","abstract_excerpt":"The current dominant paradigm for imitation learning relies on strong supervision of expert actions to learn both 'what' and 'how' to imitate. We pursue an alternative paradigm wherein an agent first explores the world without any expert supervision and then distills its experience into a goal-conditioned skill policy with a novel forward consistency loss. In our framework, the role of the expert is only to communicate the goals (i.e., what to imitate) during inference. The learned policy is then employed to mimic the expert (i.e., how to imitate) after seeing just a sequence of images demonst"},"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":"1804.08606","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-23T17:58:26Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO","stat.ML"],"title_canon_sha256":"0c2c7963b469c40227a5fbada0735868a199c8e1144ad1101e687fff4c306e66","abstract_canon_sha256":"05c37f8f9af6140ef80c96c53cb11ac720caf802fc0efc1880d1b4aab049dd4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:47.744791Z","signature_b64":"C8lfc8DQXP7Dkv7IC/XfBCzlPaj3AyTMjbe5d/WrGXverEehIqO0IhZbbfABA5ymcw3mK1ZclMKLoKxxFsEWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"985d4e6ce6c655f4497caa93d7f1d3a274ebaa79f045fe3664f0e01b90e296b0","last_reissued_at":"2026-05-18T00:17:47.744154Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:47.744154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Visual Imitation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexei A. Efros, Deepak Pathak, Dian Chen, Evan Shelhamer, Guanghao Luo, Jitendra Malik, Parsa Mahmoudieh, Pulkit Agrawal, Trevor Darrell, Yide Shentu","submitted_at":"2018-04-23T17:58:26Z","abstract_excerpt":"The current dominant paradigm for imitation learning relies on strong supervision of expert actions to learn both 'what' and 'how' to imitate. We pursue an alternative paradigm wherein an agent first explores the world without any expert supervision and then distills its experience into a goal-conditioned skill policy with a novel forward consistency loss. In our framework, the role of the expert is only to communicate the goals (i.e., what to imitate) during inference. The learned policy is then employed to mimic the expert (i.e., how to imitate) after seeing just a sequence of images demonst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08606","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":""},"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":"1804.08606","created_at":"2026-05-18T00:17:47.744248+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.08606v1","created_at":"2026-05-18T00:17:47.744248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08606","created_at":"2026-05-18T00:17:47.744248+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBOU43HGYZK7","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBOU43HGYZK7ISL4","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBOU43HG","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.11740","citing_title":"Environment Probing Interaction Policies","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2411.04983","citing_title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TBOU43HGYZK7ISL4VKJ5P4OTUJ","json":"https://pith.science/pith/TBOU43HGYZK7ISL4VKJ5P4OTUJ.json","graph_json":"https://pith.science/api/pith-number/TBOU43HGYZK7ISL4VKJ5P4OTUJ/graph.json","events_json":"https://pith.science/api/pith-number/TBOU43HGYZK7ISL4VKJ5P4OTUJ/events.json","paper":"https://pith.science/paper/TBOU43HG"},"agent_actions":{"view_html":"https://pith.science/pith/TBOU43HGYZK7ISL4VKJ5P4OTUJ","download_json":"https://pith.science/pith/TBOU43HGYZK7ISL4VKJ5P4OTUJ.json","view_paper":"https://pith.science/paper/TBOU43HG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.08606&json=true","fetch_graph":"https://pith.science/api/pith-number/TBOU43HGYZK7ISL4VKJ5P4OTUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/TBOU43HGYZK7ISL4VKJ5P4OTUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBOU43HGYZK7ISL4VKJ5P4OTUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBOU43HGYZK7ISL4VKJ5P4OTUJ/action/storage_attestation","attest_author":"https://pith.science/pith/TBOU43HGYZK7ISL4VKJ5P4OTUJ/action/author_attestation","sign_citation":"https://pith.science/pith/TBOU43HGYZK7ISL4VKJ5P4OTUJ/action/citation_signature","submit_replication":"https://pith.science/pith/TBOU43HGYZK7ISL4VKJ5P4OTUJ/action/replication_record"}},"created_at":"2026-05-18T00:17:47.744248+00:00","updated_at":"2026-05-18T00:17:47.744248+00:00"}