{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7PCKNQPWP3X7VSYMTF7D4DYC5K","short_pith_number":"pith:7PCKNQPW","schema_version":"1.0","canonical_sha256":"fbc4a6c1f67eeffacb0c997e3e0f02ea9e175e666abce5d0dc1e4652e3847cb0","source":{"kind":"arxiv","id":"2307.03659","version":1},"attestation_state":"computed","paper":{"title":"Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Annie Xie, Chelsea Finn, Lisa Lee, Ted Xiao","submitted_at":"2023-07-07T15:26:03Z","abstract_excerpt":"What makes generalization hard for imitation learning in visual robotic manipulation? This question is difficult to approach at face value, but the environment from the perspective of a robot can often be decomposed into enumerable factors of variation, such as the lighting conditions or the placement of the camera. Empirically, generalization to some of these factors have presented a greater obstacle than others, but existing work sheds little light on precisely how much each factor contributes to the generalization gap. Towards an answer to this question, we study imitation learning policies"},"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":"2307.03659","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-07-07T15:26:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"59f2dfa3eb7563555c2e4aff1ebe2fb2408195417a81a454959438653214ed2a","abstract_canon_sha256":"fa115ef32b840aa1a9652fedf3e3b89eef74b7964632d2d558d97bf83d177f1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:45.683686Z","signature_b64":"STQ64TwBcI5fOXh/ZgnuGhuhVXTGqHrs4yanelCoRdSmr+2mX0XFt/bHuYzKdnC2yk7ozf97qWdlQmTjVITvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbc4a6c1f67eeffacb0c997e3e0f02ea9e175e666abce5d0dc1e4652e3847cb0","last_reissued_at":"2026-07-05T06:28:45.683089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:45.683089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Annie Xie, Chelsea Finn, Lisa Lee, Ted Xiao","submitted_at":"2023-07-07T15:26:03Z","abstract_excerpt":"What makes generalization hard for imitation learning in visual robotic manipulation? This question is difficult to approach at face value, but the environment from the perspective of a robot can often be decomposed into enumerable factors of variation, such as the lighting conditions or the placement of the camera. Empirically, generalization to some of these factors have presented a greater obstacle than others, but existing work sheds little light on precisely how much each factor contributes to the generalization gap. Towards an answer to this question, we study imitation learning policies"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03659","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/2307.03659/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":"2307.03659","created_at":"2026-07-05T06:28:45.683165+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.03659v1","created_at":"2026-07-05T06:28:45.683165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03659","created_at":"2026-07-05T06:28:45.683165+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PCKNQPWP3X7","created_at":"2026-07-05T06:28:45.683165+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PCKNQPWP3X7VSYM","created_at":"2026-07-05T06:28:45.683165+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PCKNQPW","created_at":"2026-07-05T06:28:45.683165+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02322","citing_title":"The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2412.02818","citing_title":"RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2401.02117","citing_title":"Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2405.05941","citing_title":"Evaluating Real-World Robot Manipulation Policies in Simulation","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11114","citing_title":"SEVO: Semantic-Enhanced Virtual Observation for Robust VLA Manipulation via Active Illumination and Data-Centric Collection","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2406.09246","citing_title":"OpenVLA: An Open-Source Vision-Language-Action Model","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7PCKNQPWP3X7VSYMTF7D4DYC5K","json":"https://pith.science/pith/7PCKNQPWP3X7VSYMTF7D4DYC5K.json","graph_json":"https://pith.science/api/pith-number/7PCKNQPWP3X7VSYMTF7D4DYC5K/graph.json","events_json":"https://pith.science/api/pith-number/7PCKNQPWP3X7VSYMTF7D4DYC5K/events.json","paper":"https://pith.science/paper/7PCKNQPW"},"agent_actions":{"view_html":"https://pith.science/pith/7PCKNQPWP3X7VSYMTF7D4DYC5K","download_json":"https://pith.science/pith/7PCKNQPWP3X7VSYMTF7D4DYC5K.json","view_paper":"https://pith.science/paper/7PCKNQPW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.03659&json=true","fetch_graph":"https://pith.science/api/pith-number/7PCKNQPWP3X7VSYMTF7D4DYC5K/graph.json","fetch_events":"https://pith.science/api/pith-number/7PCKNQPWP3X7VSYMTF7D4DYC5K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PCKNQPWP3X7VSYMTF7D4DYC5K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PCKNQPWP3X7VSYMTF7D4DYC5K/action/storage_attestation","attest_author":"https://pith.science/pith/7PCKNQPWP3X7VSYMTF7D4DYC5K/action/author_attestation","sign_citation":"https://pith.science/pith/7PCKNQPWP3X7VSYMTF7D4DYC5K/action/citation_signature","submit_replication":"https://pith.science/pith/7PCKNQPWP3X7VSYMTF7D4DYC5K/action/replication_record"}},"created_at":"2026-07-05T06:28:45.683165+00:00","updated_at":"2026-07-05T06:28:45.683165+00:00"}