{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KQWSUTZ4CJ2UIHO3IMU6ZC7QUO","short_pith_number":"pith:KQWSUTZ4","schema_version":"1.0","canonical_sha256":"542d2a4f3c1275441ddb4329ec8bf0a387fd488e3c4c802e30a86c65b1cd4b97","source":{"kind":"arxiv","id":"2303.10147","version":2},"attestation_state":"computed","paper":{"title":"CoDEPS: Online Continual Learning for Depth Estimation and Panoptic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Abhinav Valada, K\\\"ursat Petek, Niclas V\\\"odisch, Wolfram Burgard","submitted_at":"2023-03-17T17:31:55Z","abstract_excerpt":"Operating a robot in the open world requires a high level of robustness with respect to previously unseen environments. Optimally, the robot is able to adapt by itself to new conditions without human supervision, e.g., automatically adjusting its perception system to changing lighting conditions. In this work, we address the task of continual learning for deep learning-based monocular depth estimation and panoptic segmentation in new environments in an online manner. We introduce CoDEPS to perform continual learning involving multiple real-world domains while mitigating catastrophic forgetting"},"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":"2303.10147","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-03-17T17:31:55Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"86e3eb2016e0a9ca95805a8bd36831e81c1378a1ff288c2653b929fc30d9d3fc","abstract_canon_sha256":"27ab9b389b17cf7bc45f97adba175686ee81cb923b508fb148a497c9d9440ad0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:30.333303Z","signature_b64":"LnFeFQXxrtNuuWxyxugD/oeuN5FVUoJjVC74oiWwSa8qyFt1hjoiwsl6BWOoHGACTRNceVzYjMsisvLqDD6uDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"542d2a4f3c1275441ddb4329ec8bf0a387fd488e3c4c802e30a86c65b1cd4b97","last_reissued_at":"2026-07-05T09:05:30.332814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:30.332814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoDEPS: Online Continual Learning for Depth Estimation and Panoptic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Abhinav Valada, K\\\"ursat Petek, Niclas V\\\"odisch, Wolfram Burgard","submitted_at":"2023-03-17T17:31:55Z","abstract_excerpt":"Operating a robot in the open world requires a high level of robustness with respect to previously unseen environments. Optimally, the robot is able to adapt by itself to new conditions without human supervision, e.g., automatically adjusting its perception system to changing lighting conditions. In this work, we address the task of continual learning for deep learning-based monocular depth estimation and panoptic segmentation in new environments in an online manner. We introduce CoDEPS to perform continual learning involving multiple real-world domains while mitigating catastrophic forgetting"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.10147","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/2303.10147/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":"2303.10147","created_at":"2026-07-05T09:05:30.332873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.10147v2","created_at":"2026-07-05T09:05:30.332873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.10147","created_at":"2026-07-05T09:05:30.332873+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQWSUTZ4CJ2U","created_at":"2026-07-05T09:05:30.332873+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQWSUTZ4CJ2UIHO3","created_at":"2026-07-05T09:05:30.332873+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQWSUTZ4","created_at":"2026-07-05T09:05:30.332873+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26473","citing_title":"Orion: Enabling Self-adaptive Memory Management for On-device Online Continual Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02580","citing_title":"Hyp2Former: Hierarchy-Aware Hyperbolic Embeddings for Open-Set Panoptic Segmentation","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KQWSUTZ4CJ2UIHO3IMU6ZC7QUO","json":"https://pith.science/pith/KQWSUTZ4CJ2UIHO3IMU6ZC7QUO.json","graph_json":"https://pith.science/api/pith-number/KQWSUTZ4CJ2UIHO3IMU6ZC7QUO/graph.json","events_json":"https://pith.science/api/pith-number/KQWSUTZ4CJ2UIHO3IMU6ZC7QUO/events.json","paper":"https://pith.science/paper/KQWSUTZ4"},"agent_actions":{"view_html":"https://pith.science/pith/KQWSUTZ4CJ2UIHO3IMU6ZC7QUO","download_json":"https://pith.science/pith/KQWSUTZ4CJ2UIHO3IMU6ZC7QUO.json","view_paper":"https://pith.science/paper/KQWSUTZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.10147&json=true","fetch_graph":"https://pith.science/api/pith-number/KQWSUTZ4CJ2UIHO3IMU6ZC7QUO/graph.json","fetch_events":"https://pith.science/api/pith-number/KQWSUTZ4CJ2UIHO3IMU6ZC7QUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQWSUTZ4CJ2UIHO3IMU6ZC7QUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQWSUTZ4CJ2UIHO3IMU6ZC7QUO/action/storage_attestation","attest_author":"https://pith.science/pith/KQWSUTZ4CJ2UIHO3IMU6ZC7QUO/action/author_attestation","sign_citation":"https://pith.science/pith/KQWSUTZ4CJ2UIHO3IMU6ZC7QUO/action/citation_signature","submit_replication":"https://pith.science/pith/KQWSUTZ4CJ2UIHO3IMU6ZC7QUO/action/replication_record"}},"created_at":"2026-07-05T09:05:30.332873+00:00","updated_at":"2026-07-05T09:05:30.332873+00:00"}