{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:73P3BEZV3QZXFXIYNXQDOW56UU","short_pith_number":"pith:73P3BEZV","schema_version":"1.0","canonical_sha256":"fedfb09335dc3372dd186de0375bbea515d7cef973bc72e26910ddc4beae72e9","source":{"kind":"arxiv","id":"2301.04660","version":2},"attestation_state":"computed","paper":{"title":"Anomalies, Representations, and Self-Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","hep-ex"],"primary_cat":"hep-ph","authors_text":"Barry M. Dillon, Friedrich Feiden, Luigi Favaro, Tanmoy Modak, Tilman Plehn","submitted_at":"2023-01-11T19:00:00Z","abstract_excerpt":"We develop a self-supervised method for density-based anomaly detection using contrastive learning, and test it using event-level anomaly data from CMS ADC2021. The AnomalyCLR technique is data-driven and uses augmentations of the background data to mimic non-Standard-Model events in a model-agnostic way. It uses a permutation-invariant Transformer Encoder architecture to map the objects measured in a collider event to the representation space, where the data augmentations define a representation space which is sensitive to potential anomalous features. An AutoEncoder trained on background rep"},"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":"2301.04660","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"hep-ph","submitted_at":"2023-01-11T19:00:00Z","cross_cats_sorted":["cs.LG","hep-ex"],"title_canon_sha256":"41759613a03712acf2ee7a8b79a77574cd2afa548149fcd053c56f0a46261738","abstract_canon_sha256":"b70b57ac498a0fc47947a9db3498a2379eabed545e8a7954a5bc7e5d283d65b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:20.795447Z","signature_b64":"oy0F6GhMkGwQa8ZbSGn2WkJRZXU/TgZqcnTaj0Vbqb+MbQoTwerQflf7pTuO5WYL4nYQGMIloq8l3y3ye7+VAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fedfb09335dc3372dd186de0375bbea515d7cef973bc72e26910ddc4beae72e9","last_reissued_at":"2026-07-05T09:26:20.794885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:20.794885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Anomalies, Representations, and Self-Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","hep-ex"],"primary_cat":"hep-ph","authors_text":"Barry M. Dillon, Friedrich Feiden, Luigi Favaro, Tanmoy Modak, Tilman Plehn","submitted_at":"2023-01-11T19:00:00Z","abstract_excerpt":"We develop a self-supervised method for density-based anomaly detection using contrastive learning, and test it using event-level anomaly data from CMS ADC2021. The AnomalyCLR technique is data-driven and uses augmentations of the background data to mimic non-Standard-Model events in a model-agnostic way. It uses a permutation-invariant Transformer Encoder architecture to map the objects measured in a collider event to the representation space, where the data augmentations define a representation space which is sensitive to potential anomalous features. An AutoEncoder trained on background rep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.04660","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/2301.04660/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":"2301.04660","created_at":"2026-07-05T09:26:20.794957+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.04660v2","created_at":"2026-07-05T09:26:20.794957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.04660","created_at":"2026-07-05T09:26:20.794957+00:00"},{"alias_kind":"pith_short_12","alias_value":"73P3BEZV3QZX","created_at":"2026-07-05T09:26:20.794957+00:00"},{"alias_kind":"pith_short_16","alias_value":"73P3BEZV3QZXFXIY","created_at":"2026-07-05T09:26:20.794957+00:00"},{"alias_kind":"pith_short_8","alias_value":"73P3BEZV","created_at":"2026-07-05T09:26:20.794957+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01354","citing_title":"Local Conformal Predictions for Calibrated Surrogates","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/73P3BEZV3QZXFXIYNXQDOW56UU","json":"https://pith.science/pith/73P3BEZV3QZXFXIYNXQDOW56UU.json","graph_json":"https://pith.science/api/pith-number/73P3BEZV3QZXFXIYNXQDOW56UU/graph.json","events_json":"https://pith.science/api/pith-number/73P3BEZV3QZXFXIYNXQDOW56UU/events.json","paper":"https://pith.science/paper/73P3BEZV"},"agent_actions":{"view_html":"https://pith.science/pith/73P3BEZV3QZXFXIYNXQDOW56UU","download_json":"https://pith.science/pith/73P3BEZV3QZXFXIYNXQDOW56UU.json","view_paper":"https://pith.science/paper/73P3BEZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.04660&json=true","fetch_graph":"https://pith.science/api/pith-number/73P3BEZV3QZXFXIYNXQDOW56UU/graph.json","fetch_events":"https://pith.science/api/pith-number/73P3BEZV3QZXFXIYNXQDOW56UU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73P3BEZV3QZXFXIYNXQDOW56UU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73P3BEZV3QZXFXIYNXQDOW56UU/action/storage_attestation","attest_author":"https://pith.science/pith/73P3BEZV3QZXFXIYNXQDOW56UU/action/author_attestation","sign_citation":"https://pith.science/pith/73P3BEZV3QZXFXIYNXQDOW56UU/action/citation_signature","submit_replication":"https://pith.science/pith/73P3BEZV3QZXFXIYNXQDOW56UU/action/replication_record"}},"created_at":"2026-07-05T09:26:20.794957+00:00","updated_at":"2026-07-05T09:26:20.794957+00:00"}