{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:74PKCW623UHY52ZH3Z44CUOTBA","short_pith_number":"pith:74PKCW62","schema_version":"1.0","canonical_sha256":"ff1ea15bdadd0f8eeb27de79c151d3081ce87c07b72843bad793758d19de4705","source":{"kind":"arxiv","id":"2107.08976","version":2},"attestation_state":"computed","paper":{"title":"OODformer: Out-Of-Distribution Detection Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Karsten Roscher, Poulami Sinhamahapatra, Rajat Koner, Stephan G\\\"unnemann, Volker Tresp","submitted_at":"2021-07-19T15:46:38Z","abstract_excerpt":"A serious problem in image classification is that a trained model might perform well for input data that originates from the same distribution as the data available for model training, but performs much worse for out-of-distribution (OOD) samples. In real-world safety-critical applications, in particular, it is important to be aware if a new data point is OOD. To date, OOD detection is typically addressed using either confidence scores, auto-encoder based reconstruction, or by contrastive learning. However, the global image context has not yet been explored to discriminate the non-local object"},"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":"2107.08976","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-19T15:46:38Z","cross_cats_sorted":[],"title_canon_sha256":"a5b39a1969f1601b3a7fa87b70cb58a7d2b79e7a7c4f4fc91da7234fe3bb717a","abstract_canon_sha256":"10c3ef2e757334bd08ba628e3ca1e6501648d36ce5bd94d6a11eb8bb8769122f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:08.086789Z","signature_b64":"A1KBzmUgJYmBDpwbZ0Qn7y9hk0ZAKCMAuRX06dtp9QR4zYCofTRXK1Se87JyFuj20dOsLaNc37HvKEnE0lbFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff1ea15bdadd0f8eeb27de79c151d3081ce87c07b72843bad793758d19de4705","last_reissued_at":"2026-07-05T03:38:08.086295Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:08.086295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OODformer: Out-Of-Distribution Detection Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Karsten Roscher, Poulami Sinhamahapatra, Rajat Koner, Stephan G\\\"unnemann, Volker Tresp","submitted_at":"2021-07-19T15:46:38Z","abstract_excerpt":"A serious problem in image classification is that a trained model might perform well for input data that originates from the same distribution as the data available for model training, but performs much worse for out-of-distribution (OOD) samples. In real-world safety-critical applications, in particular, it is important to be aware if a new data point is OOD. To date, OOD detection is typically addressed using either confidence scores, auto-encoder based reconstruction, or by contrastive learning. However, the global image context has not yet been explored to discriminate the non-local object"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.08976","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/2107.08976/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":"2107.08976","created_at":"2026-07-05T03:38:08.086365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.08976v2","created_at":"2026-07-05T03:38:08.086365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.08976","created_at":"2026-07-05T03:38:08.086365+00:00"},{"alias_kind":"pith_short_12","alias_value":"74PKCW623UHY","created_at":"2026-07-05T03:38:08.086365+00:00"},{"alias_kind":"pith_short_16","alias_value":"74PKCW623UHY52ZH","created_at":"2026-07-05T03:38:08.086365+00:00"},{"alias_kind":"pith_short_8","alias_value":"74PKCW62","created_at":"2026-07-05T03:38:08.086365+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/74PKCW623UHY52ZH3Z44CUOTBA","json":"https://pith.science/pith/74PKCW623UHY52ZH3Z44CUOTBA.json","graph_json":"https://pith.science/api/pith-number/74PKCW623UHY52ZH3Z44CUOTBA/graph.json","events_json":"https://pith.science/api/pith-number/74PKCW623UHY52ZH3Z44CUOTBA/events.json","paper":"https://pith.science/paper/74PKCW62"},"agent_actions":{"view_html":"https://pith.science/pith/74PKCW623UHY52ZH3Z44CUOTBA","download_json":"https://pith.science/pith/74PKCW623UHY52ZH3Z44CUOTBA.json","view_paper":"https://pith.science/paper/74PKCW62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.08976&json=true","fetch_graph":"https://pith.science/api/pith-number/74PKCW623UHY52ZH3Z44CUOTBA/graph.json","fetch_events":"https://pith.science/api/pith-number/74PKCW623UHY52ZH3Z44CUOTBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74PKCW623UHY52ZH3Z44CUOTBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74PKCW623UHY52ZH3Z44CUOTBA/action/storage_attestation","attest_author":"https://pith.science/pith/74PKCW623UHY52ZH3Z44CUOTBA/action/author_attestation","sign_citation":"https://pith.science/pith/74PKCW623UHY52ZH3Z44CUOTBA/action/citation_signature","submit_replication":"https://pith.science/pith/74PKCW623UHY52ZH3Z44CUOTBA/action/replication_record"}},"created_at":"2026-07-05T03:38:08.086365+00:00","updated_at":"2026-07-05T03:38:08.086365+00:00"}