{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EN5VL3SNDBIJT7RRNICDAI3DGK","short_pith_number":"pith:EN5VL3SN","schema_version":"1.0","canonical_sha256":"237b55ee4d185099fe316a0430236332853d224f4db15886f5690cc73591c77e","source":{"kind":"arxiv","id":"2508.07085","version":1},"attestation_state":"computed","paper":{"title":"Improving Real-Time Concept Drift Detection using a Hybrid Transformer-Autoencoder Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"K Mounvik, N Harshit","submitted_at":"2025-08-09T19:39:33Z","abstract_excerpt":"In applied machine learning, concept drift, which is either gradual or abrupt changes in data distribution, can significantly reduce model performance. Typical detection methods,such as statistical tests or reconstruction-based models,are generally reactive and not very sensitive to early detection. Our study proposes a hybrid framework consisting of Transformers and Autoencoders to model complex temporal dynamics and provide online drift detection. We create a distinct Trust Score methodology, which includes signals on (1) statistical and reconstruction-based drift metrics, more specifically,"},"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":"2508.07085","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-09T19:39:33Z","cross_cats_sorted":[],"title_canon_sha256":"f06c3a14dd2d245bea3bbff522bc563aed615f9746a81fa00158aadd23546c95","abstract_canon_sha256":"b4685e82c40dee3c600fef77450d097f59626979f86492c1f459946518b4e678"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:40.614631Z","signature_b64":"BqpmJMiWb7O2Gu49OuToSg3cIA7Ey1tfQof0miHtVCEqILc52U8qM66z/DJgW6eQD2iZxH3pBxouQi0EllJ8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"237b55ee4d185099fe316a0430236332853d224f4db15886f5690cc73591c77e","last_reissued_at":"2026-07-05T11:51:40.614035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:40.614035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Real-Time Concept Drift Detection using a Hybrid Transformer-Autoencoder Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"K Mounvik, N Harshit","submitted_at":"2025-08-09T19:39:33Z","abstract_excerpt":"In applied machine learning, concept drift, which is either gradual or abrupt changes in data distribution, can significantly reduce model performance. Typical detection methods,such as statistical tests or reconstruction-based models,are generally reactive and not very sensitive to early detection. Our study proposes a hybrid framework consisting of Transformers and Autoencoders to model complex temporal dynamics and provide online drift detection. We create a distinct Trust Score methodology, which includes signals on (1) statistical and reconstruction-based drift metrics, more specifically,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07085","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/2508.07085/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":"2508.07085","created_at":"2026-07-05T11:51:40.614100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.07085v1","created_at":"2026-07-05T11:51:40.614100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07085","created_at":"2026-07-05T11:51:40.614100+00:00"},{"alias_kind":"pith_short_12","alias_value":"EN5VL3SNDBIJ","created_at":"2026-07-05T11:51:40.614100+00:00"},{"alias_kind":"pith_short_16","alias_value":"EN5VL3SNDBIJT7RR","created_at":"2026-07-05T11:51:40.614100+00:00"},{"alias_kind":"pith_short_8","alias_value":"EN5VL3SN","created_at":"2026-07-05T11:51:40.614100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.19567","citing_title":"Counterfactual Reward Model Training for Bias Mitigation in Multimodal Reinforcement Learning","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EN5VL3SNDBIJT7RRNICDAI3DGK","json":"https://pith.science/pith/EN5VL3SNDBIJT7RRNICDAI3DGK.json","graph_json":"https://pith.science/api/pith-number/EN5VL3SNDBIJT7RRNICDAI3DGK/graph.json","events_json":"https://pith.science/api/pith-number/EN5VL3SNDBIJT7RRNICDAI3DGK/events.json","paper":"https://pith.science/paper/EN5VL3SN"},"agent_actions":{"view_html":"https://pith.science/pith/EN5VL3SNDBIJT7RRNICDAI3DGK","download_json":"https://pith.science/pith/EN5VL3SNDBIJT7RRNICDAI3DGK.json","view_paper":"https://pith.science/paper/EN5VL3SN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.07085&json=true","fetch_graph":"https://pith.science/api/pith-number/EN5VL3SNDBIJT7RRNICDAI3DGK/graph.json","fetch_events":"https://pith.science/api/pith-number/EN5VL3SNDBIJT7RRNICDAI3DGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EN5VL3SNDBIJT7RRNICDAI3DGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EN5VL3SNDBIJT7RRNICDAI3DGK/action/storage_attestation","attest_author":"https://pith.science/pith/EN5VL3SNDBIJT7RRNICDAI3DGK/action/author_attestation","sign_citation":"https://pith.science/pith/EN5VL3SNDBIJT7RRNICDAI3DGK/action/citation_signature","submit_replication":"https://pith.science/pith/EN5VL3SNDBIJT7RRNICDAI3DGK/action/replication_record"}},"created_at":"2026-07-05T11:51:40.614100+00:00","updated_at":"2026-07-05T11:51:40.614100+00:00"}