{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7NV22DCJ454JCJS5USBJZBFOJW","short_pith_number":"pith:7NV22DCJ","schema_version":"1.0","canonical_sha256":"fb6bad0c49e77891265da4829c84ae4dae71ba05b0a22c05c624942939084c27","source":{"kind":"arxiv","id":"2210.04303","version":1},"attestation_state":"computed","paper":{"title":"Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gap","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexander Amini, Daniela Rus, Mathias Lechner, Ramin Hasani, Thomas A. Henzinger, Tsun-Hsuan Wang","submitted_at":"2022-10-09T16:56:45Z","abstract_excerpt":"There is an ever-growing zoo of modern neural network models that can efficiently learn end-to-end control from visual observations. These advanced deep models, ranging from convolutional to patch-based networks, have been extensively tested on offline image classification and regression tasks. In this paper, we study these vision architectures with respect to the open-loop to closed-loop causality gap, i.e., offline training followed by an online closed-loop deployment. This causality gap typically emerges in robotics applications such as autonomous driving, where a network is trained to imit"},"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":"2210.04303","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-09T16:56:45Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE","cs.RO"],"title_canon_sha256":"e752b67d5bc365aa8ebb1092162ccba1b7d55fdf835eb1d15729c3148d18e327","abstract_canon_sha256":"45300bb7893be7df75125dabaecf180161f0f2ed7bfe0319f8e34b597cefee85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:51.915034Z","signature_b64":"Cn2VRR8oN9XsFj39wsVtcOr2HU9p0xpPYRNpwaIqRpwPXbkaFR2X7pzzMFzTIv2N+ZbA5eAZJSECzQ0KiUjRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb6bad0c49e77891265da4829c84ae4dae71ba05b0a22c05c624942939084c27","last_reissued_at":"2026-07-05T05:04:51.914696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:51.914696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gap","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alexander Amini, Daniela Rus, Mathias Lechner, Ramin Hasani, Thomas A. Henzinger, Tsun-Hsuan Wang","submitted_at":"2022-10-09T16:56:45Z","abstract_excerpt":"There is an ever-growing zoo of modern neural network models that can efficiently learn end-to-end control from visual observations. These advanced deep models, ranging from convolutional to patch-based networks, have been extensively tested on offline image classification and regression tasks. In this paper, we study these vision architectures with respect to the open-loop to closed-loop causality gap, i.e., offline training followed by an online closed-loop deployment. This causality gap typically emerges in robotics applications such as autonomous driving, where a network is trained to imit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04303","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/2210.04303/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":"2210.04303","created_at":"2026-07-05T05:04:51.914752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.04303v1","created_at":"2026-07-05T05:04:51.914752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04303","created_at":"2026-07-05T05:04:51.914752+00:00"},{"alias_kind":"pith_short_12","alias_value":"7NV22DCJ454J","created_at":"2026-07-05T05:04:51.914752+00:00"},{"alias_kind":"pith_short_16","alias_value":"7NV22DCJ454JCJS5","created_at":"2026-07-05T05:04:51.914752+00:00"},{"alias_kind":"pith_short_8","alias_value":"7NV22DCJ","created_at":"2026-07-05T05:04:51.914752+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/7NV22DCJ454JCJS5USBJZBFOJW","json":"https://pith.science/pith/7NV22DCJ454JCJS5USBJZBFOJW.json","graph_json":"https://pith.science/api/pith-number/7NV22DCJ454JCJS5USBJZBFOJW/graph.json","events_json":"https://pith.science/api/pith-number/7NV22DCJ454JCJS5USBJZBFOJW/events.json","paper":"https://pith.science/paper/7NV22DCJ"},"agent_actions":{"view_html":"https://pith.science/pith/7NV22DCJ454JCJS5USBJZBFOJW","download_json":"https://pith.science/pith/7NV22DCJ454JCJS5USBJZBFOJW.json","view_paper":"https://pith.science/paper/7NV22DCJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.04303&json=true","fetch_graph":"https://pith.science/api/pith-number/7NV22DCJ454JCJS5USBJZBFOJW/graph.json","fetch_events":"https://pith.science/api/pith-number/7NV22DCJ454JCJS5USBJZBFOJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7NV22DCJ454JCJS5USBJZBFOJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7NV22DCJ454JCJS5USBJZBFOJW/action/storage_attestation","attest_author":"https://pith.science/pith/7NV22DCJ454JCJS5USBJZBFOJW/action/author_attestation","sign_citation":"https://pith.science/pith/7NV22DCJ454JCJS5USBJZBFOJW/action/citation_signature","submit_replication":"https://pith.science/pith/7NV22DCJ454JCJS5USBJZBFOJW/action/replication_record"}},"created_at":"2026-07-05T05:04:51.914752+00:00","updated_at":"2026-07-05T05:04:51.914752+00:00"}