{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7T7Y3AUEDZS6OP5MTL5I3NH7D5","short_pith_number":"pith:7T7Y3AUE","schema_version":"1.0","canonical_sha256":"fcff8d82841e65e73fac9afa8db4ff1f4592b7ef46e80fdcc03499851de42475","source":{"kind":"arxiv","id":"2509.06191","version":1},"attestation_state":"computed","paper":{"title":"Learning in ImaginationLand: Omnidirectional Policies through 3D Generative Models (OP-Gen)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Edward Johns, Yifei Ren","submitted_at":"2025-09-07T20:00:59Z","abstract_excerpt":"Recent 3D generative models, which are capable of generating full object shapes from just a few images, now open up new opportunities in robotics. In this work, we show that 3D generative models can be used to augment a dataset from a single real-world demonstration, after which an omnidirectional policy can be learned within this imagined dataset. We found that this enables a robot to perform a task when initialised from states very far from those observed during the demonstration, including starting from the opposite side of the object relative to the real-world demonstration, significantly "},"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":"2509.06191","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-07T20:00:59Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"94a602f49b7a2676b5744b519ee3bbe5f27adcf5f605431ed322d62594899987","abstract_canon_sha256":"377e30eb04d6c1fc550beb0bffdf46b0eb2ec9f9e7015780c656a7e9e4c8f49c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:31.369034Z","signature_b64":"ns2vIoOo/iWm1HAJhA2OOpQKCJljCmTdNgI811Ut7WOJQa8NiOhZnkIYX95RcA0kcHqow9lbBumBmS2NIOwjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcff8d82841e65e73fac9afa8db4ff1f4592b7ef46e80fdcc03499851de42475","last_reissued_at":"2026-07-05T12:06:31.368595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:31.368595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning in ImaginationLand: Omnidirectional Policies through 3D Generative Models (OP-Gen)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Edward Johns, Yifei Ren","submitted_at":"2025-09-07T20:00:59Z","abstract_excerpt":"Recent 3D generative models, which are capable of generating full object shapes from just a few images, now open up new opportunities in robotics. In this work, we show that 3D generative models can be used to augment a dataset from a single real-world demonstration, after which an omnidirectional policy can be learned within this imagined dataset. We found that this enables a robot to perform a task when initialised from states very far from those observed during the demonstration, including starting from the opposite side of the object relative to the real-world demonstration, significantly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06191","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/2509.06191/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":"2509.06191","created_at":"2026-07-05T12:06:31.368649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06191v1","created_at":"2026-07-05T12:06:31.368649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06191","created_at":"2026-07-05T12:06:31.368649+00:00"},{"alias_kind":"pith_short_12","alias_value":"7T7Y3AUEDZS6","created_at":"2026-07-05T12:06:31.368649+00:00"},{"alias_kind":"pith_short_16","alias_value":"7T7Y3AUEDZS6OP5M","created_at":"2026-07-05T12:06:31.368649+00:00"},{"alias_kind":"pith_short_8","alias_value":"7T7Y3AUE","created_at":"2026-07-05T12:06:31.368649+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7T7Y3AUEDZS6OP5MTL5I3NH7D5","json":"https://pith.science/pith/7T7Y3AUEDZS6OP5MTL5I3NH7D5.json","graph_json":"https://pith.science/api/pith-number/7T7Y3AUEDZS6OP5MTL5I3NH7D5/graph.json","events_json":"https://pith.science/api/pith-number/7T7Y3AUEDZS6OP5MTL5I3NH7D5/events.json","paper":"https://pith.science/paper/7T7Y3AUE"},"agent_actions":{"view_html":"https://pith.science/pith/7T7Y3AUEDZS6OP5MTL5I3NH7D5","download_json":"https://pith.science/pith/7T7Y3AUEDZS6OP5MTL5I3NH7D5.json","view_paper":"https://pith.science/paper/7T7Y3AUE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06191&json=true","fetch_graph":"https://pith.science/api/pith-number/7T7Y3AUEDZS6OP5MTL5I3NH7D5/graph.json","fetch_events":"https://pith.science/api/pith-number/7T7Y3AUEDZS6OP5MTL5I3NH7D5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7T7Y3AUEDZS6OP5MTL5I3NH7D5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7T7Y3AUEDZS6OP5MTL5I3NH7D5/action/storage_attestation","attest_author":"https://pith.science/pith/7T7Y3AUEDZS6OP5MTL5I3NH7D5/action/author_attestation","sign_citation":"https://pith.science/pith/7T7Y3AUEDZS6OP5MTL5I3NH7D5/action/citation_signature","submit_replication":"https://pith.science/pith/7T7Y3AUEDZS6OP5MTL5I3NH7D5/action/replication_record"}},"created_at":"2026-07-05T12:06:31.368649+00:00","updated_at":"2026-07-05T12:06:31.368649+00:00"}