{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YE3W7GELHSRHOSHGTPULIZ45UA","short_pith_number":"pith:YE3W7GEL","schema_version":"1.0","canonical_sha256":"c1376f988b3ca27748e69be8b4679da01a78602959697f2c0743b4c884b577e7","source":{"kind":"arxiv","id":"2212.14020","version":2},"attestation_state":"computed","paper":{"title":"A System-Level View on Out-of-Distribution Data in Robotics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Apoorva Sharma, Edward Schmerling, Marco Pavone, Rachel Luo, Rohan Sinha, Somrita Banerjee, Spencer M. Richards, Thomas Lew, Yixiao Sun","submitted_at":"2022-12-28T18:45:05Z","abstract_excerpt":"When testing conditions differ from those represented in training data, so-called out-of-distribution (OOD) inputs can mar the reliability of learned components in the modern robot autonomy stack. Therefore, coping with OOD data is an important challenge on the path towards trustworthy learning-enabled open-world autonomy. In this paper, we aim to demystify the topic of OOD data and its associated challenges in the context of data-driven robotic systems, drawing connections to emerging paradigms in the ML community that study the effect of OOD data on learned models in isolation. We argue that"},"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":"2212.14020","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-12-28T18:45:05Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"c88351a322f72628d22471c93796ce7e64e4825a4219279e014e57b53f392228","abstract_canon_sha256":"a09796ce39904fec06ff720090badce0d547349ace5372a8db1924eebe5951c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:29.146213Z","signature_b64":"k/3Fs4QsyV3aYv/QbYCmnAE6N7nZ7XB+de9hSrA8Vopm8g5vvndjfWusUZb6P80Zv3N4KmBnUi8GIksRQPxHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1376f988b3ca27748e69be8b4679da01a78602959697f2c0743b4c884b577e7","last_reissued_at":"2026-07-05T06:44:29.145760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:29.145760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A System-Level View on Out-of-Distribution Data in Robotics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Apoorva Sharma, Edward Schmerling, Marco Pavone, Rachel Luo, Rohan Sinha, Somrita Banerjee, Spencer M. Richards, Thomas Lew, Yixiao Sun","submitted_at":"2022-12-28T18:45:05Z","abstract_excerpt":"When testing conditions differ from those represented in training data, so-called out-of-distribution (OOD) inputs can mar the reliability of learned components in the modern robot autonomy stack. Therefore, coping with OOD data is an important challenge on the path towards trustworthy learning-enabled open-world autonomy. In this paper, we aim to demystify the topic of OOD data and its associated challenges in the context of data-driven robotic systems, drawing connections to emerging paradigms in the ML community that study the effect of OOD data on learned models in isolation. We argue that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.14020","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/2212.14020/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":"2212.14020","created_at":"2026-07-05T06:44:29.145812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.14020v2","created_at":"2026-07-05T06:44:29.145812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.14020","created_at":"2026-07-05T06:44:29.145812+00:00"},{"alias_kind":"pith_short_12","alias_value":"YE3W7GELHSRH","created_at":"2026-07-05T06:44:29.145812+00:00"},{"alias_kind":"pith_short_16","alias_value":"YE3W7GELHSRHOSHG","created_at":"2026-07-05T06:44:29.145812+00:00"},{"alias_kind":"pith_short_8","alias_value":"YE3W7GEL","created_at":"2026-07-05T06:44:29.145812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29699","citing_title":"Early Warning Signals for OpenVLA Failure under Visual Distribution Shift","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29605","citing_title":"VLAConf: Calibrated Task-Success Confidence for Vision-Language-Action Models","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YE3W7GELHSRHOSHGTPULIZ45UA","json":"https://pith.science/pith/YE3W7GELHSRHOSHGTPULIZ45UA.json","graph_json":"https://pith.science/api/pith-number/YE3W7GELHSRHOSHGTPULIZ45UA/graph.json","events_json":"https://pith.science/api/pith-number/YE3W7GELHSRHOSHGTPULIZ45UA/events.json","paper":"https://pith.science/paper/YE3W7GEL"},"agent_actions":{"view_html":"https://pith.science/pith/YE3W7GELHSRHOSHGTPULIZ45UA","download_json":"https://pith.science/pith/YE3W7GELHSRHOSHGTPULIZ45UA.json","view_paper":"https://pith.science/paper/YE3W7GEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.14020&json=true","fetch_graph":"https://pith.science/api/pith-number/YE3W7GELHSRHOSHGTPULIZ45UA/graph.json","fetch_events":"https://pith.science/api/pith-number/YE3W7GELHSRHOSHGTPULIZ45UA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YE3W7GELHSRHOSHGTPULIZ45UA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YE3W7GELHSRHOSHGTPULIZ45UA/action/storage_attestation","attest_author":"https://pith.science/pith/YE3W7GELHSRHOSHGTPULIZ45UA/action/author_attestation","sign_citation":"https://pith.science/pith/YE3W7GELHSRHOSHGTPULIZ45UA/action/citation_signature","submit_replication":"https://pith.science/pith/YE3W7GELHSRHOSHGTPULIZ45UA/action/replication_record"}},"created_at":"2026-07-05T06:44:29.145812+00:00","updated_at":"2026-07-05T06:44:29.145812+00:00"}