{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VADP4EYSECQTVP5UXQ74SBBSX4","short_pith_number":"pith:VADP4EYS","schema_version":"1.0","canonical_sha256":"a806fe131220a13abfb4bc3fc90432bf0b74189b87b7b8428d5f67223ef721fb","source":{"kind":"arxiv","id":"2404.14064","version":2},"attestation_state":"computed","paper":{"title":"Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Mhairi Dunion, Stefano V. Albrecht","submitted_at":"2024-04-22T10:21:41Z","abstract_excerpt":"The performance of image-based Reinforcement Learning (RL) agents can vary depending on the position of the camera used to capture the images. Training on multiple cameras simultaneously, including a first-person egocentric camera, can leverage information from different camera perspectives to improve the performance of RL. However, hardware constraints may limit the availability of multiple cameras in real-world deployment. Additionally, cameras may become damaged in the real-world preventing access to all cameras that were used during training. To overcome these hardware constraints, we prop"},"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":"2404.14064","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-22T10:21:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2b8651acef315880f2c223d938f158ff3791b4aa957ce0f91b4fcfacce305d80","abstract_canon_sha256":"8480c221c9b9bc01ee33cac45071e9f5a56dad6a27a7c06aa08ace3e6b9634aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:02.377931Z","signature_b64":"gr0ANgh/bsR0Qlt+9V1VL8QL2UaOm0bR5nBB62lk8HJ8OuFdekKhSIdR0fDXfVmmgoy8kvnEEjp64OnqwtVDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a806fe131220a13abfb4bc3fc90432bf0b74189b87b7b8428d5f67223ef721fb","last_reissued_at":"2026-07-05T08:35:02.377450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:02.377450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Mhairi Dunion, Stefano V. Albrecht","submitted_at":"2024-04-22T10:21:41Z","abstract_excerpt":"The performance of image-based Reinforcement Learning (RL) agents can vary depending on the position of the camera used to capture the images. Training on multiple cameras simultaneously, including a first-person egocentric camera, can leverage information from different camera perspectives to improve the performance of RL. However, hardware constraints may limit the availability of multiple cameras in real-world deployment. Additionally, cameras may become damaged in the real-world preventing access to all cameras that were used during training. To overcome these hardware constraints, we prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14064","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/2404.14064/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":"2404.14064","created_at":"2026-07-05T08:35:02.377509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.14064v2","created_at":"2026-07-05T08:35:02.377509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14064","created_at":"2026-07-05T08:35:02.377509+00:00"},{"alias_kind":"pith_short_12","alias_value":"VADP4EYSECQT","created_at":"2026-07-05T08:35:02.377509+00:00"},{"alias_kind":"pith_short_16","alias_value":"VADP4EYSECQTVP5U","created_at":"2026-07-05T08:35:02.377509+00:00"},{"alias_kind":"pith_short_8","alias_value":"VADP4EYS","created_at":"2026-07-05T08:35:02.377509+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06253","citing_title":"Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision","ref_index":74,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VADP4EYSECQTVP5UXQ74SBBSX4","json":"https://pith.science/pith/VADP4EYSECQTVP5UXQ74SBBSX4.json","graph_json":"https://pith.science/api/pith-number/VADP4EYSECQTVP5UXQ74SBBSX4/graph.json","events_json":"https://pith.science/api/pith-number/VADP4EYSECQTVP5UXQ74SBBSX4/events.json","paper":"https://pith.science/paper/VADP4EYS"},"agent_actions":{"view_html":"https://pith.science/pith/VADP4EYSECQTVP5UXQ74SBBSX4","download_json":"https://pith.science/pith/VADP4EYSECQTVP5UXQ74SBBSX4.json","view_paper":"https://pith.science/paper/VADP4EYS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.14064&json=true","fetch_graph":"https://pith.science/api/pith-number/VADP4EYSECQTVP5UXQ74SBBSX4/graph.json","fetch_events":"https://pith.science/api/pith-number/VADP4EYSECQTVP5UXQ74SBBSX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VADP4EYSECQTVP5UXQ74SBBSX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VADP4EYSECQTVP5UXQ74SBBSX4/action/storage_attestation","attest_author":"https://pith.science/pith/VADP4EYSECQTVP5UXQ74SBBSX4/action/author_attestation","sign_citation":"https://pith.science/pith/VADP4EYSECQTVP5UXQ74SBBSX4/action/citation_signature","submit_replication":"https://pith.science/pith/VADP4EYSECQTVP5UXQ74SBBSX4/action/replication_record"}},"created_at":"2026-07-05T08:35:02.377509+00:00","updated_at":"2026-07-05T08:35:02.377509+00:00"}