{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KZ233P6NRSXXMKUT7RXFU3LPQD","short_pith_number":"pith:KZ233P6N","schema_version":"1.0","canonical_sha256":"5675bdbfcd8caf762a93fc6e5a6d6f80c5f7714a4ab8ea166e3366169f67c9ec","source":{"kind":"arxiv","id":"2007.08176","version":2},"attestation_state":"computed","paper":{"title":"CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jihoon Tack, Jinwoo Shin, Jongheon Jeong, Sangwoo Mo","submitted_at":"2020-07-16T08:32:56Z","abstract_excerpt":"Novelty detection, i.e., identifying whether a given sample is drawn from outside the training distribution, is essential for reliable machine learning. To this end, there have been many attempts at learning a representation well-suited for novelty detection and designing a score based on such representation. In this paper, we propose a simple, yet effective method named contrasting shifted instances (CSI), inspired by the recent success on contrastive learning of visual representations. Specifically, in addition to contrasting a given sample with other instances as in conventional contrastive"},"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":"2007.08176","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-16T08:32:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a2c66010fa137b7411c2a351a24afeb7f3dfca0389851a8be6c0348d9e991307","abstract_canon_sha256":"c30f49df232788368f0b457a6fc2d19a797efc579a36b2fa23675d9aad8fa156"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:44:49.631797Z","signature_b64":"cX6eT2wFJ1xAtjoK05zJgaZzy/jSlkRWUQ3ZF8FG/o3TNFrIaX48+rNAsStEXOgb2xREJAf3uav4aFbK6E3ZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5675bdbfcd8caf762a93fc6e5a6d6f80c5f7714a4ab8ea166e3366169f67c9ec","last_reissued_at":"2026-07-05T01:44:49.631359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:44:49.631359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jihoon Tack, Jinwoo Shin, Jongheon Jeong, Sangwoo Mo","submitted_at":"2020-07-16T08:32:56Z","abstract_excerpt":"Novelty detection, i.e., identifying whether a given sample is drawn from outside the training distribution, is essential for reliable machine learning. To this end, there have been many attempts at learning a representation well-suited for novelty detection and designing a score based on such representation. In this paper, we propose a simple, yet effective method named contrasting shifted instances (CSI), inspired by the recent success on contrastive learning of visual representations. Specifically, in addition to contrasting a given sample with other instances as in conventional contrastive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.08176","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/2007.08176/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":"2007.08176","created_at":"2026-07-05T01:44:49.631421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.08176v2","created_at":"2026-07-05T01:44:49.631421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.08176","created_at":"2026-07-05T01:44:49.631421+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZ233P6NRSXX","created_at":"2026-07-05T01:44:49.631421+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZ233P6NRSXXMKUT","created_at":"2026-07-05T01:44:49.631421+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZ233P6N","created_at":"2026-07-05T01:44:49.631421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04529","citing_title":"A Data-Driven Novelty Score for Diverse In-Vehicle Data Recording","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KZ233P6NRSXXMKUT7RXFU3LPQD","json":"https://pith.science/pith/KZ233P6NRSXXMKUT7RXFU3LPQD.json","graph_json":"https://pith.science/api/pith-number/KZ233P6NRSXXMKUT7RXFU3LPQD/graph.json","events_json":"https://pith.science/api/pith-number/KZ233P6NRSXXMKUT7RXFU3LPQD/events.json","paper":"https://pith.science/paper/KZ233P6N"},"agent_actions":{"view_html":"https://pith.science/pith/KZ233P6NRSXXMKUT7RXFU3LPQD","download_json":"https://pith.science/pith/KZ233P6NRSXXMKUT7RXFU3LPQD.json","view_paper":"https://pith.science/paper/KZ233P6N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.08176&json=true","fetch_graph":"https://pith.science/api/pith-number/KZ233P6NRSXXMKUT7RXFU3LPQD/graph.json","fetch_events":"https://pith.science/api/pith-number/KZ233P6NRSXXMKUT7RXFU3LPQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZ233P6NRSXXMKUT7RXFU3LPQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZ233P6NRSXXMKUT7RXFU3LPQD/action/storage_attestation","attest_author":"https://pith.science/pith/KZ233P6NRSXXMKUT7RXFU3LPQD/action/author_attestation","sign_citation":"https://pith.science/pith/KZ233P6NRSXXMKUT7RXFU3LPQD/action/citation_signature","submit_replication":"https://pith.science/pith/KZ233P6NRSXXMKUT7RXFU3LPQD/action/replication_record"}},"created_at":"2026-07-05T01:44:49.631421+00:00","updated_at":"2026-07-05T01:44:49.631421+00:00"}