{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6XIH6PHPIBPPFJ5TNND3PJYA37","short_pith_number":"pith:6XIH6PHP","schema_version":"1.0","canonical_sha256":"f5d07f3cef405ef2a7b36b47b7a700dff8dd810ad3b4ca5977ded4b55ec04ff9","source":{"kind":"arxiv","id":"2606.00372","version":1},"attestation_state":"computed","paper":{"title":"LFA: Layer Feature Attention for Run-Time Introspection of 2D Object Detectors in Automated Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alois Knoll, Mert Keser","submitted_at":"2026-05-29T21:27:13Z","abstract_excerpt":"Reliable object detection is critical for automated driving, yet even state-of-the-art detectors inevitably make errors that can compromise safety. Introspection methods that predict detector failures enable safer deployment by triggering fallback mechanisms or alerting human operators. However, existing approaches rely solely on last-layer features or hand-crafted statistics, discarding valuable information from earlier layers that capture different levels of visual abstraction. We propose Layer Feature Attention (LFA), a lightweight introspection method that learns to aggregate features from"},"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":"2606.00372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T21:27:13Z","cross_cats_sorted":[],"title_canon_sha256":"8bcabb756642c57e865384b28752f47698eb102652ba767d15d06b267bf25612","abstract_canon_sha256":"16edbdaff06af798b8ed9fd026b8045f7448936b34206a7709872e015a4a9dd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:52.902742Z","signature_b64":"cvA/bvdJyb6MOKYJXFrEeIMvQGTmEows78Av9fzhkc1dmYTd2IHEIFsjYeuuRSLGWznkuJAoAeZhBu2u/psRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5d07f3cef405ef2a7b36b47b7a700dff8dd810ad3b4ca5977ded4b55ec04ff9","last_reissued_at":"2026-06-02T01:03:52.902308Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:52.902308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LFA: Layer Feature Attention for Run-Time Introspection of 2D Object Detectors in Automated Driving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alois Knoll, Mert Keser","submitted_at":"2026-05-29T21:27:13Z","abstract_excerpt":"Reliable object detection is critical for automated driving, yet even state-of-the-art detectors inevitably make errors that can compromise safety. Introspection methods that predict detector failures enable safer deployment by triggering fallback mechanisms or alerting human operators. However, existing approaches rely solely on last-layer features or hand-crafted statistics, discarding valuable information from earlier layers that capture different levels of visual abstraction. We propose Layer Feature Attention (LFA), a lightweight introspection method that learns to aggregate features from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00372","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/2606.00372/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":"2606.00372","created_at":"2026-06-02T01:03:52.902376+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00372v1","created_at":"2026-06-02T01:03:52.902376+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00372","created_at":"2026-06-02T01:03:52.902376+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XIH6PHPIBPP","created_at":"2026-06-02T01:03:52.902376+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XIH6PHPIBPPFJ5T","created_at":"2026-06-02T01:03:52.902376+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XIH6PHP","created_at":"2026-06-02T01:03:52.902376+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/6XIH6PHPIBPPFJ5TNND3PJYA37","json":"https://pith.science/pith/6XIH6PHPIBPPFJ5TNND3PJYA37.json","graph_json":"https://pith.science/api/pith-number/6XIH6PHPIBPPFJ5TNND3PJYA37/graph.json","events_json":"https://pith.science/api/pith-number/6XIH6PHPIBPPFJ5TNND3PJYA37/events.json","paper":"https://pith.science/paper/6XIH6PHP"},"agent_actions":{"view_html":"https://pith.science/pith/6XIH6PHPIBPPFJ5TNND3PJYA37","download_json":"https://pith.science/pith/6XIH6PHPIBPPFJ5TNND3PJYA37.json","view_paper":"https://pith.science/paper/6XIH6PHP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00372&json=true","fetch_graph":"https://pith.science/api/pith-number/6XIH6PHPIBPPFJ5TNND3PJYA37/graph.json","fetch_events":"https://pith.science/api/pith-number/6XIH6PHPIBPPFJ5TNND3PJYA37/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XIH6PHPIBPPFJ5TNND3PJYA37/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XIH6PHPIBPPFJ5TNND3PJYA37/action/storage_attestation","attest_author":"https://pith.science/pith/6XIH6PHPIBPPFJ5TNND3PJYA37/action/author_attestation","sign_citation":"https://pith.science/pith/6XIH6PHPIBPPFJ5TNND3PJYA37/action/citation_signature","submit_replication":"https://pith.science/pith/6XIH6PHPIBPPFJ5TNND3PJYA37/action/replication_record"}},"created_at":"2026-06-02T01:03:52.902376+00:00","updated_at":"2026-06-02T01:03:52.902376+00:00"}