{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NGY2AXZZODNLTMGAB5CCKFRB4U","short_pith_number":"pith:NGY2AXZZ","schema_version":"1.0","canonical_sha256":"69b1a05f3970dab9b0c00f44251621e51653fbb95d0d65fe351371bfdb3c6fee","source":{"kind":"arxiv","id":"2306.01828","version":1},"attestation_state":"computed","paper":{"title":"Unifying (Machine) Vision via Counterfactual World Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alex Durango, Daniel L.K. Yamins, Daniel M. Bear, Honglin Chen, Kevin Feigelis, Klemen Kotar, Rahul Venkatesh, Wanhee Lee","submitted_at":"2023-06-02T17:45:44Z","abstract_excerpt":"Leading approaches in machine vision employ different architectures for different tasks, trained on costly task-specific labeled datasets. This complexity has held back progress in areas, such as robotics, where robust task-general perception remains a bottleneck. In contrast, \"foundation models\" of natural language have shown how large pre-trained neural networks can provide zero-shot solutions to a broad spectrum of apparently distinct tasks. Here we introduce Counterfactual World Modeling (CWM), a framework for constructing a visual foundation model: a unified, unsupervised network that can"},"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":"2306.01828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-02T17:45:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b8738f8becf4396ddf6f69cf21edaf9a55afd09cb4525f7831a6150e1a5c0406","abstract_canon_sha256":"6f7e8d9632fbcd295e1f42115c5b7fcc69f4635ab7d2681438690bf3e707aa67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:10.040587Z","signature_b64":"b0n+qr4Nl0FbGFg2GUIMyCYOLeaR+fZQq8d8QrF9ch/xag5idmqrnOuAL9OcbYtV/6ZCeOZCw5LvyFpu7jXZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69b1a05f3970dab9b0c00f44251621e51653fbb95d0d65fe351371bfdb3c6fee","last_reissued_at":"2026-07-05T06:17:10.040167Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:10.040167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying (Machine) Vision via Counterfactual World Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alex Durango, Daniel L.K. Yamins, Daniel M. Bear, Honglin Chen, Kevin Feigelis, Klemen Kotar, Rahul Venkatesh, Wanhee Lee","submitted_at":"2023-06-02T17:45:44Z","abstract_excerpt":"Leading approaches in machine vision employ different architectures for different tasks, trained on costly task-specific labeled datasets. This complexity has held back progress in areas, such as robotics, where robust task-general perception remains a bottleneck. In contrast, \"foundation models\" of natural language have shown how large pre-trained neural networks can provide zero-shot solutions to a broad spectrum of apparently distinct tasks. Here we introduce Counterfactual World Modeling (CWM), a framework for constructing a visual foundation model: a unified, unsupervised network that can"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01828","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/2306.01828/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":"2306.01828","created_at":"2026-07-05T06:17:10.040223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01828v1","created_at":"2026-07-05T06:17:10.040223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01828","created_at":"2026-07-05T06:17:10.040223+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGY2AXZZODNL","created_at":"2026-07-05T06:17:10.040223+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGY2AXZZODNLTMGA","created_at":"2026-07-05T06:17:10.040223+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGY2AXZZ","created_at":"2026-07-05T06:17:10.040223+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24321","citing_title":"Unified 3D Scene Understanding Through Physical World Modeling","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13684","citing_title":"Recurrent Video Masked Autoencoders","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10333","citing_title":"Zero-shot World Models Are Developmentally Efficient Learners","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NGY2AXZZODNLTMGAB5CCKFRB4U","json":"https://pith.science/pith/NGY2AXZZODNLTMGAB5CCKFRB4U.json","graph_json":"https://pith.science/api/pith-number/NGY2AXZZODNLTMGAB5CCKFRB4U/graph.json","events_json":"https://pith.science/api/pith-number/NGY2AXZZODNLTMGAB5CCKFRB4U/events.json","paper":"https://pith.science/paper/NGY2AXZZ"},"agent_actions":{"view_html":"https://pith.science/pith/NGY2AXZZODNLTMGAB5CCKFRB4U","download_json":"https://pith.science/pith/NGY2AXZZODNLTMGAB5CCKFRB4U.json","view_paper":"https://pith.science/paper/NGY2AXZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01828&json=true","fetch_graph":"https://pith.science/api/pith-number/NGY2AXZZODNLTMGAB5CCKFRB4U/graph.json","fetch_events":"https://pith.science/api/pith-number/NGY2AXZZODNLTMGAB5CCKFRB4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGY2AXZZODNLTMGAB5CCKFRB4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGY2AXZZODNLTMGAB5CCKFRB4U/action/storage_attestation","attest_author":"https://pith.science/pith/NGY2AXZZODNLTMGAB5CCKFRB4U/action/author_attestation","sign_citation":"https://pith.science/pith/NGY2AXZZODNLTMGAB5CCKFRB4U/action/citation_signature","submit_replication":"https://pith.science/pith/NGY2AXZZODNLTMGAB5CCKFRB4U/action/replication_record"}},"created_at":"2026-07-05T06:17:10.040223+00:00","updated_at":"2026-07-05T06:17:10.040223+00:00"}