{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6CO2UTIRRGNZJ2TZQLC47GS5DW","short_pith_number":"pith:6CO2UTIR","schema_version":"1.0","canonical_sha256":"f09daa4d11899b94ea7982c5cf9a5d1dbe646cc428e5b8d74e61b208f7d486ba","source":{"kind":"arxiv","id":"2210.11590","version":1},"attestation_state":"computed","paper":{"title":"XC: Exploring Quantitative Use Cases for Explanations in 3D Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Krzysztof Czarnecki, Sunsheng Gu, Vahdat Abdelzad","submitted_at":"2022-10-20T21:02:55Z","abstract_excerpt":"Explainable AI (XAI) methods are frequently applied to obtain qualitative insights about deep models' predictions. However, such insights need to be interpreted by a human observer to be useful. In this paper, we aim to use explanations directly to make decisions without human observers. We adopt two gradient-based explanation methods, Integrated Gradients (IG) and backprop, for the task of 3D object detection. Then, we propose a set of quantitative measures, named Explanation Concentration (XC) scores, that can be used for downstream tasks. These scores quantify the concentration of attributi"},"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":"2210.11590","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T21:02:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f379106f209b05529d36e24b496d91f68a02505c47608ec6f4501f64ddf32c5d","abstract_canon_sha256":"22f74435487db549b75a28ed0731598b9a980d153630d67f3d060af0a5f24347"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:55.232564Z","signature_b64":"YWRUdJSYauOHbCPLcHfAPa13zfQd/Zh5wGFXAhsFnKC8ywFB9rMxn0+2YYAtojBqQtdvxMFrmeeelXjNtYx6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f09daa4d11899b94ea7982c5cf9a5d1dbe646cc428e5b8d74e61b208f7d486ba","last_reissued_at":"2026-07-05T05:08:55.232189Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:55.232189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XC: Exploring Quantitative Use Cases for Explanations in 3D Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Krzysztof Czarnecki, Sunsheng Gu, Vahdat Abdelzad","submitted_at":"2022-10-20T21:02:55Z","abstract_excerpt":"Explainable AI (XAI) methods are frequently applied to obtain qualitative insights about deep models' predictions. However, such insights need to be interpreted by a human observer to be useful. In this paper, we aim to use explanations directly to make decisions without human observers. We adopt two gradient-based explanation methods, Integrated Gradients (IG) and backprop, for the task of 3D object detection. Then, we propose a set of quantitative measures, named Explanation Concentration (XC) scores, that can be used for downstream tasks. These scores quantify the concentration of attributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11590","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/2210.11590/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":"2210.11590","created_at":"2026-07-05T05:08:55.232245+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.11590v1","created_at":"2026-07-05T05:08:55.232245+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11590","created_at":"2026-07-05T05:08:55.232245+00:00"},{"alias_kind":"pith_short_12","alias_value":"6CO2UTIRRGNZ","created_at":"2026-07-05T05:08:55.232245+00:00"},{"alias_kind":"pith_short_16","alias_value":"6CO2UTIRRGNZJ2TZ","created_at":"2026-07-05T05:08:55.232245+00:00"},{"alias_kind":"pith_short_8","alias_value":"6CO2UTIR","created_at":"2026-07-05T05:08:55.232245+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/6CO2UTIRRGNZJ2TZQLC47GS5DW","json":"https://pith.science/pith/6CO2UTIRRGNZJ2TZQLC47GS5DW.json","graph_json":"https://pith.science/api/pith-number/6CO2UTIRRGNZJ2TZQLC47GS5DW/graph.json","events_json":"https://pith.science/api/pith-number/6CO2UTIRRGNZJ2TZQLC47GS5DW/events.json","paper":"https://pith.science/paper/6CO2UTIR"},"agent_actions":{"view_html":"https://pith.science/pith/6CO2UTIRRGNZJ2TZQLC47GS5DW","download_json":"https://pith.science/pith/6CO2UTIRRGNZJ2TZQLC47GS5DW.json","view_paper":"https://pith.science/paper/6CO2UTIR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.11590&json=true","fetch_graph":"https://pith.science/api/pith-number/6CO2UTIRRGNZJ2TZQLC47GS5DW/graph.json","fetch_events":"https://pith.science/api/pith-number/6CO2UTIRRGNZJ2TZQLC47GS5DW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6CO2UTIRRGNZJ2TZQLC47GS5DW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6CO2UTIRRGNZJ2TZQLC47GS5DW/action/storage_attestation","attest_author":"https://pith.science/pith/6CO2UTIRRGNZJ2TZQLC47GS5DW/action/author_attestation","sign_citation":"https://pith.science/pith/6CO2UTIRRGNZJ2TZQLC47GS5DW/action/citation_signature","submit_replication":"https://pith.science/pith/6CO2UTIRRGNZJ2TZQLC47GS5DW/action/replication_record"}},"created_at":"2026-07-05T05:08:55.232245+00:00","updated_at":"2026-07-05T05:08:55.232245+00:00"}