{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JPMCDKJA4IT22PR7BVV24QTMAC","short_pith_number":"pith:JPMCDKJA","schema_version":"1.0","canonical_sha256":"4bd821a920e227ad3e3f0d6bae426c00841e2c97bf420235177524195614c17a","source":{"kind":"arxiv","id":"2107.00848","version":1},"attestation_state":"computed","paper":{"title":"Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aniket Didolkar, Anirudh Goyal, Christopher Pal, Danilo Rezende, Guillaume Lajoie, Michael Mozer, Nan Rosemary Ke, Sarthak Mittal, Stefan Bauer, Yoshua Bengio","submitted_at":"2021-07-02T05:44:56Z","abstract_excerpt":"Inducing causal relationships from observations is a classic problem in machine learning. Most work in causality starts from the premise that the causal variables themselves are observed. However, for AI agents such as robots trying to make sense of their environment, the only observables are low-level variables like pixels in images. To generalize well, an agent must induce high-level variables, particularly those which are causal or are affected by causal variables. A central goal for AI and causality is thus the joint discovery of abstract representations and causal structure. However, we n"},"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":"2107.00848","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-07-02T05:44:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b8f4fdfae1c46d85b0dc45217088dcbd5fc4161358bda7cdc64c63d47230aa06","abstract_canon_sha256":"e44f63581becef426256e4ddccf1e4fa11a58c947c50c07a6fde30c32599121c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:34.401499Z","signature_b64":"oz1eANfwv+Z0bmzTldWE8QqXoxkIg0fmWguBDJLHJl1iFhv22DFQ5VOT6kYne6fZQL8vpRzyoaZnWr+eWiOKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bd821a920e227ad3e3f0d6bae426c00841e2c97bf420235177524195614c17a","last_reissued_at":"2026-07-05T02:54:34.401039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:34.401039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aniket Didolkar, Anirudh Goyal, Christopher Pal, Danilo Rezende, Guillaume Lajoie, Michael Mozer, Nan Rosemary Ke, Sarthak Mittal, Stefan Bauer, Yoshua Bengio","submitted_at":"2021-07-02T05:44:56Z","abstract_excerpt":"Inducing causal relationships from observations is a classic problem in machine learning. Most work in causality starts from the premise that the causal variables themselves are observed. However, for AI agents such as robots trying to make sense of their environment, the only observables are low-level variables like pixels in images. To generalize well, an agent must induce high-level variables, particularly those which are causal or are affected by causal variables. A central goal for AI and causality is thus the joint discovery of abstract representations and causal structure. However, we n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00848","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/2107.00848/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":"2107.00848","created_at":"2026-07-05T02:54:34.401096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.00848v1","created_at":"2026-07-05T02:54:34.401096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00848","created_at":"2026-07-05T02:54:34.401096+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPMCDKJA4IT2","created_at":"2026-07-05T02:54:34.401096+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPMCDKJA4IT22PR7","created_at":"2026-07-05T02:54:34.401096+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPMCDKJA","created_at":"2026-07-05T02:54:34.401096+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07712","citing_title":"CausalVAE as a Plug-in for World Models: Towards Reliable Counterfactual Dynamics","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JPMCDKJA4IT22PR7BVV24QTMAC","json":"https://pith.science/pith/JPMCDKJA4IT22PR7BVV24QTMAC.json","graph_json":"https://pith.science/api/pith-number/JPMCDKJA4IT22PR7BVV24QTMAC/graph.json","events_json":"https://pith.science/api/pith-number/JPMCDKJA4IT22PR7BVV24QTMAC/events.json","paper":"https://pith.science/paper/JPMCDKJA"},"agent_actions":{"view_html":"https://pith.science/pith/JPMCDKJA4IT22PR7BVV24QTMAC","download_json":"https://pith.science/pith/JPMCDKJA4IT22PR7BVV24QTMAC.json","view_paper":"https://pith.science/paper/JPMCDKJA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.00848&json=true","fetch_graph":"https://pith.science/api/pith-number/JPMCDKJA4IT22PR7BVV24QTMAC/graph.json","fetch_events":"https://pith.science/api/pith-number/JPMCDKJA4IT22PR7BVV24QTMAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPMCDKJA4IT22PR7BVV24QTMAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPMCDKJA4IT22PR7BVV24QTMAC/action/storage_attestation","attest_author":"https://pith.science/pith/JPMCDKJA4IT22PR7BVV24QTMAC/action/author_attestation","sign_citation":"https://pith.science/pith/JPMCDKJA4IT22PR7BVV24QTMAC/action/citation_signature","submit_replication":"https://pith.science/pith/JPMCDKJA4IT22PR7BVV24QTMAC/action/replication_record"}},"created_at":"2026-07-05T02:54:34.401096+00:00","updated_at":"2026-07-05T02:54:34.401096+00:00"}