{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DCBCXX3W6U4O44DXWDQS4V7Y32","short_pith_number":"pith:DCBCXX3W","schema_version":"1.0","canonical_sha256":"18822bdf76f538ee7077b0e12e57f8de8369e04efc3ea60df1c51def774c222f","source":{"kind":"arxiv","id":"2011.14381","version":1},"attestation_state":"computed","paper":{"title":"Self-supervised Visual Reinforcement Learning with Object-centric Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrii Zadaianchuk, Georg Martius, Maximilian Seitzer","submitted_at":"2020-11-29T14:55:09Z","abstract_excerpt":"Autonomous agents need large repertoires of skills to act reasonably on new tasks that they have not seen before. However, acquiring these skills using only a stream of high-dimensional, unstructured, and unlabeled observations is a tricky challenge for any autonomous agent. Previous methods have used variational autoencoders to encode a scene into a low-dimensional vector that can be used as a goal for an agent to discover new skills. Nevertheless, in compositional/multi-object environments it is difficult to disentangle all the factors of variation into such a fixed-length representation 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":"2011.14381","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-29T14:55:09Z","cross_cats_sorted":[],"title_canon_sha256":"8e2b08bacc3fc0c68cbd3a74b750a6901750f94febad97c1e59d06a9e8fc21d9","abstract_canon_sha256":"36a280d70f303f70974fd8680bd1b9a12c20e43c2e4cb4af0b1911877854503a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:20.557001Z","signature_b64":"TOnfytXdXXB3M3agx8k6DlRt7Xmg6Ywfbx4otcwbgI/BVLGvjiNUZhA3evgSBzk92q3KhN2oyquTGghYhkHgAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18822bdf76f538ee7077b0e12e57f8de8369e04efc3ea60df1c51def774c222f","last_reissued_at":"2026-07-05T02:13:20.556490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:20.556490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Visual Reinforcement Learning with Object-centric Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrii Zadaianchuk, Georg Martius, Maximilian Seitzer","submitted_at":"2020-11-29T14:55:09Z","abstract_excerpt":"Autonomous agents need large repertoires of skills to act reasonably on new tasks that they have not seen before. However, acquiring these skills using only a stream of high-dimensional, unstructured, and unlabeled observations is a tricky challenge for any autonomous agent. Previous methods have used variational autoencoders to encode a scene into a low-dimensional vector that can be used as a goal for an agent to discover new skills. Nevertheless, in compositional/multi-object environments it is difficult to disentangle all the factors of variation into such a fixed-length representation of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14381","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/2011.14381/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":"2011.14381","created_at":"2026-07-05T02:13:20.556554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.14381v1","created_at":"2026-07-05T02:13:20.556554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14381","created_at":"2026-07-05T02:13:20.556554+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCBCXX3W6U4O","created_at":"2026-07-05T02:13:20.556554+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCBCXX3W6U4O44DX","created_at":"2026-07-05T02:13:20.556554+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCBCXX3W","created_at":"2026-07-05T02:13:20.556554+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/DCBCXX3W6U4O44DXWDQS4V7Y32","json":"https://pith.science/pith/DCBCXX3W6U4O44DXWDQS4V7Y32.json","graph_json":"https://pith.science/api/pith-number/DCBCXX3W6U4O44DXWDQS4V7Y32/graph.json","events_json":"https://pith.science/api/pith-number/DCBCXX3W6U4O44DXWDQS4V7Y32/events.json","paper":"https://pith.science/paper/DCBCXX3W"},"agent_actions":{"view_html":"https://pith.science/pith/DCBCXX3W6U4O44DXWDQS4V7Y32","download_json":"https://pith.science/pith/DCBCXX3W6U4O44DXWDQS4V7Y32.json","view_paper":"https://pith.science/paper/DCBCXX3W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.14381&json=true","fetch_graph":"https://pith.science/api/pith-number/DCBCXX3W6U4O44DXWDQS4V7Y32/graph.json","fetch_events":"https://pith.science/api/pith-number/DCBCXX3W6U4O44DXWDQS4V7Y32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCBCXX3W6U4O44DXWDQS4V7Y32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCBCXX3W6U4O44DXWDQS4V7Y32/action/storage_attestation","attest_author":"https://pith.science/pith/DCBCXX3W6U4O44DXWDQS4V7Y32/action/author_attestation","sign_citation":"https://pith.science/pith/DCBCXX3W6U4O44DXWDQS4V7Y32/action/citation_signature","submit_replication":"https://pith.science/pith/DCBCXX3W6U4O44DXWDQS4V7Y32/action/replication_record"}},"created_at":"2026-07-05T02:13:20.556554+00:00","updated_at":"2026-07-05T02:13:20.556554+00:00"}