{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UMAXXOKZEG4S7HLFFMFW4B2ADG","short_pith_number":"pith:UMAXXOKZ","schema_version":"1.0","canonical_sha256":"a3017bb95921b92f9d652b0b6e074019810554c895c8c88c7bf88e0498688f4a","source":{"kind":"arxiv","id":"2003.06085","version":2},"attestation_state":"computed","paper":{"title":"Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ajay Mandlekar, Danfei Xu, Li Fei-Fei, Roberto Mart\\'in-Mart\\'in, Silvio Savarese","submitted_at":"2020-03-13T02:25:28Z","abstract_excerpt":"Imitation learning is an effective and safe technique to train robot policies in the real world because it does not depend on an expensive random exploration process. However, due to the lack of exploration, learning policies that generalize beyond the demonstrated behaviors is still an open challenge. We present a novel imitation learning framework to enable robots to 1) learn complex real world manipulation tasks efficiently from a small number of human demonstrations, and 2) synthesize new behaviors not contained in the collected demonstrations. Our key insight is that multi-task domains of"},"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":"2003.06085","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-03-13T02:25:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8a9b7b01c4bd509db45ed5e09962711610c4a29a1b9d0e43785e374ac00015f8","abstract_canon_sha256":"388e9816a1821a9eeb8bd3ae837f329ee8dd7361af129b019551da5efc3c97a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:51:36.020103Z","signature_b64":"3JZuL4B49sENVt0OTNStPu00abCTl71rvulovRNlfNGi9h4mEB9E72jaQpkLUrmxExORFImEV+NjF/EONlqVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3017bb95921b92f9d652b0b6e074019810554c895c8c88c7bf88e0498688f4a","last_reissued_at":"2026-07-05T02:51:36.019688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:51:36.019688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ajay Mandlekar, Danfei Xu, Li Fei-Fei, Roberto Mart\\'in-Mart\\'in, Silvio Savarese","submitted_at":"2020-03-13T02:25:28Z","abstract_excerpt":"Imitation learning is an effective and safe technique to train robot policies in the real world because it does not depend on an expensive random exploration process. However, due to the lack of exploration, learning policies that generalize beyond the demonstrated behaviors is still an open challenge. We present a novel imitation learning framework to enable robots to 1) learn complex real world manipulation tasks efficiently from a small number of human demonstrations, and 2) synthesize new behaviors not contained in the collected demonstrations. Our key insight is that multi-task domains of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.06085","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/2003.06085/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":"2003.06085","created_at":"2026-07-05T02:51:36.019745+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.06085v2","created_at":"2026-07-05T02:51:36.019745+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.06085","created_at":"2026-07-05T02:51:36.019745+00:00"},{"alias_kind":"pith_short_12","alias_value":"UMAXXOKZEG4S","created_at":"2026-07-05T02:51:36.019745+00:00"},{"alias_kind":"pith_short_16","alias_value":"UMAXXOKZEG4S7HLF","created_at":"2026-07-05T02:51:36.019745+00:00"},{"alias_kind":"pith_short_8","alias_value":"UMAXXOKZ","created_at":"2026-07-05T02:51:36.019745+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22509","citing_title":"Imagine to Ensure Safety in Hierarchical Reinforcement Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10025","citing_title":"GHOST: Hierarchical Sub-Goal Policies for Generalizing Robot Manipulation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05172","citing_title":"When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2412.02818","citing_title":"RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2310.17596","citing_title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13428","citing_title":"SID: Sliding into Distribution for Robust Few-Demonstration Manipulation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2108.03298","citing_title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05172","citing_title":"When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2005.01643","citing_title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","ref_index":241,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UMAXXOKZEG4S7HLFFMFW4B2ADG","json":"https://pith.science/pith/UMAXXOKZEG4S7HLFFMFW4B2ADG.json","graph_json":"https://pith.science/api/pith-number/UMAXXOKZEG4S7HLFFMFW4B2ADG/graph.json","events_json":"https://pith.science/api/pith-number/UMAXXOKZEG4S7HLFFMFW4B2ADG/events.json","paper":"https://pith.science/paper/UMAXXOKZ"},"agent_actions":{"view_html":"https://pith.science/pith/UMAXXOKZEG4S7HLFFMFW4B2ADG","download_json":"https://pith.science/pith/UMAXXOKZEG4S7HLFFMFW4B2ADG.json","view_paper":"https://pith.science/paper/UMAXXOKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.06085&json=true","fetch_graph":"https://pith.science/api/pith-number/UMAXXOKZEG4S7HLFFMFW4B2ADG/graph.json","fetch_events":"https://pith.science/api/pith-number/UMAXXOKZEG4S7HLFFMFW4B2ADG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UMAXXOKZEG4S7HLFFMFW4B2ADG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UMAXXOKZEG4S7HLFFMFW4B2ADG/action/storage_attestation","attest_author":"https://pith.science/pith/UMAXXOKZEG4S7HLFFMFW4B2ADG/action/author_attestation","sign_citation":"https://pith.science/pith/UMAXXOKZEG4S7HLFFMFW4B2ADG/action/citation_signature","submit_replication":"https://pith.science/pith/UMAXXOKZEG4S7HLFFMFW4B2ADG/action/replication_record"}},"created_at":"2026-07-05T02:51:36.019745+00:00","updated_at":"2026-07-05T02:51:36.019745+00:00"}