{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:W2VI7TEPH2N7Z44MPHBBT6WR75","short_pith_number":"pith:W2VI7TEP","schema_version":"1.0","canonical_sha256":"b6aa8fcc8f3e9bfcf38c79c219fad1ff7c72bdbbc1aa401e45c21b27a88f360e","source":{"kind":"arxiv","id":"2112.06384","version":1},"attestation_state":"computed","paper":{"title":"WOOD: Wasserstein-based Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jionghua \"Judy\" Jin, Wenbo Sun, Xiaowei Yue, Yinan Wang, Zhenyu \"James\" Kong","submitted_at":"2021-12-13T02:35:15Z","abstract_excerpt":"The training and test data for deep-neural-network-based classifiers are usually assumed to be sampled from the same distribution. When part of the test samples are drawn from a distribution that is sufficiently far away from that of the training samples (a.k.a. out-of-distribution (OOD) samples), the trained neural network has a tendency to make high confidence predictions for these OOD samples. Detection of the OOD samples is critical when training a neural network used for image classification, object detection, etc. It can enhance the classifier's robustness to irrelevant inputs, and impro"},"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":"2112.06384","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-13T02:35:15Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"304725bc425462b58be62e1730c815c54282af22ed689ef313139d39acbd78a6","abstract_canon_sha256":"f202295d550e53f8063a57ee272fcfc03b59af9fb04d6e26eec4bc6da816da1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:40:13.382522Z","signature_b64":"P3gTj58ksxCW73zEbukAPC+qUAs4knmwba6ogCaG9j/7FyVUs8yIVlFbLip71MCTJpDKeN+bH4B+8xcNvLHqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6aa8fcc8f3e9bfcf38c79c219fad1ff7c72bdbbc1aa401e45c21b27a88f360e","last_reissued_at":"2026-07-05T03:40:13.382082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:40:13.382082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WOOD: Wasserstein-based Out-of-Distribution Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jionghua \"Judy\" Jin, Wenbo Sun, Xiaowei Yue, Yinan Wang, Zhenyu \"James\" Kong","submitted_at":"2021-12-13T02:35:15Z","abstract_excerpt":"The training and test data for deep-neural-network-based classifiers are usually assumed to be sampled from the same distribution. When part of the test samples are drawn from a distribution that is sufficiently far away from that of the training samples (a.k.a. out-of-distribution (OOD) samples), the trained neural network has a tendency to make high confidence predictions for these OOD samples. Detection of the OOD samples is critical when training a neural network used for image classification, object detection, etc. It can enhance the classifier's robustness to irrelevant inputs, and impro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.06384","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/2112.06384/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":"2112.06384","created_at":"2026-07-05T03:40:13.382141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.06384v1","created_at":"2026-07-05T03:40:13.382141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.06384","created_at":"2026-07-05T03:40:13.382141+00:00"},{"alias_kind":"pith_short_12","alias_value":"W2VI7TEPH2N7","created_at":"2026-07-05T03:40:13.382141+00:00"},{"alias_kind":"pith_short_16","alias_value":"W2VI7TEPH2N7Z44M","created_at":"2026-07-05T03:40:13.382141+00:00"},{"alias_kind":"pith_short_8","alias_value":"W2VI7TEP","created_at":"2026-07-05T03:40:13.382141+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/W2VI7TEPH2N7Z44MPHBBT6WR75","json":"https://pith.science/pith/W2VI7TEPH2N7Z44MPHBBT6WR75.json","graph_json":"https://pith.science/api/pith-number/W2VI7TEPH2N7Z44MPHBBT6WR75/graph.json","events_json":"https://pith.science/api/pith-number/W2VI7TEPH2N7Z44MPHBBT6WR75/events.json","paper":"https://pith.science/paper/W2VI7TEP"},"agent_actions":{"view_html":"https://pith.science/pith/W2VI7TEPH2N7Z44MPHBBT6WR75","download_json":"https://pith.science/pith/W2VI7TEPH2N7Z44MPHBBT6WR75.json","view_paper":"https://pith.science/paper/W2VI7TEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.06384&json=true","fetch_graph":"https://pith.science/api/pith-number/W2VI7TEPH2N7Z44MPHBBT6WR75/graph.json","fetch_events":"https://pith.science/api/pith-number/W2VI7TEPH2N7Z44MPHBBT6WR75/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W2VI7TEPH2N7Z44MPHBBT6WR75/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W2VI7TEPH2N7Z44MPHBBT6WR75/action/storage_attestation","attest_author":"https://pith.science/pith/W2VI7TEPH2N7Z44MPHBBT6WR75/action/author_attestation","sign_citation":"https://pith.science/pith/W2VI7TEPH2N7Z44MPHBBT6WR75/action/citation_signature","submit_replication":"https://pith.science/pith/W2VI7TEPH2N7Z44MPHBBT6WR75/action/replication_record"}},"created_at":"2026-07-05T03:40:13.382141+00:00","updated_at":"2026-07-05T03:40:13.382141+00:00"}