{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DMS4MAHKE6ZBPVYGAYYG3IDH7A","short_pith_number":"pith:DMS4MAHK","schema_version":"1.0","canonical_sha256":"1b25c600ea27b217d70606306da067f802c5637eeaa53dbc2416af98b474ff08","source":{"kind":"arxiv","id":"2407.02968","version":1},"attestation_state":"computed","paper":{"title":"Unified Anomaly Detection methods on Edge Device using Knowledge Distillation and Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CC","cs.ET"],"primary_cat":"cs.CV","authors_text":"Ananth Ganesh, Anoushka Banerjee, Arnav Bhavsar, Arya Pulkit, Dinesh Singh, Kajal Singh, Sharad Joshi, Sushovan Jena","submitted_at":"2024-07-03T10:04:48Z","abstract_excerpt":"With the rapid advances in deep learning and smart manufacturing in Industry 4.0, there is an imperative for high-throughput, high-performance, and fully integrated visual inspection systems. Most anomaly detection approaches using defect detection datasets, such as MVTec AD, employ one-class models that require fitting separate models for each class. On the contrary, unified models eliminate the need for fitting separate models for each class and significantly reduce cost and memory requirements. Thus, in this work, we experiment with considering a unified multi-class setup. Our experimental "},"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":"2407.02968","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-03T10:04:48Z","cross_cats_sorted":["cs.AI","cs.CC","cs.ET"],"title_canon_sha256":"62828bb45a4a0ccd136561cd16c42385360885206dea155738bec00989f021d1","abstract_canon_sha256":"42722ab1dcd1f8f496e8a7b4fa0eed13916e4a8cc481a10ce0c7c3e84a16dc99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:44.411304Z","signature_b64":"0KLFIEO/PzIchUWV7s/7d+50oUkjHLOJ6EEZPUH4KGsLdDWxsqlaU1U6JReE3zfEijR6Gpm8N5HC/gI0XmkPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b25c600ea27b217d70606306da067f802c5637eeaa53dbc2416af98b474ff08","last_reissued_at":"2026-07-05T08:39:44.410894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:44.410894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Anomaly Detection methods on Edge Device using Knowledge Distillation and Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CC","cs.ET"],"primary_cat":"cs.CV","authors_text":"Ananth Ganesh, Anoushka Banerjee, Arnav Bhavsar, Arya Pulkit, Dinesh Singh, Kajal Singh, Sharad Joshi, Sushovan Jena","submitted_at":"2024-07-03T10:04:48Z","abstract_excerpt":"With the rapid advances in deep learning and smart manufacturing in Industry 4.0, there is an imperative for high-throughput, high-performance, and fully integrated visual inspection systems. Most anomaly detection approaches using defect detection datasets, such as MVTec AD, employ one-class models that require fitting separate models for each class. On the contrary, unified models eliminate the need for fitting separate models for each class and significantly reduce cost and memory requirements. Thus, in this work, we experiment with considering a unified multi-class setup. Our experimental "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02968","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/2407.02968/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":"2407.02968","created_at":"2026-07-05T08:39:44.410952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02968v1","created_at":"2026-07-05T08:39:44.410952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02968","created_at":"2026-07-05T08:39:44.410952+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMS4MAHKE6ZB","created_at":"2026-07-05T08:39:44.410952+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMS4MAHKE6ZBPVYG","created_at":"2026-07-05T08:39:44.410952+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMS4MAHK","created_at":"2026-07-05T08:39:44.410952+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08189","citing_title":"Breaking the Bias: Recalibrating the Attention of Industrial Anomaly Detection","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DMS4MAHKE6ZBPVYGAYYG3IDH7A","json":"https://pith.science/pith/DMS4MAHKE6ZBPVYGAYYG3IDH7A.json","graph_json":"https://pith.science/api/pith-number/DMS4MAHKE6ZBPVYGAYYG3IDH7A/graph.json","events_json":"https://pith.science/api/pith-number/DMS4MAHKE6ZBPVYGAYYG3IDH7A/events.json","paper":"https://pith.science/paper/DMS4MAHK"},"agent_actions":{"view_html":"https://pith.science/pith/DMS4MAHKE6ZBPVYGAYYG3IDH7A","download_json":"https://pith.science/pith/DMS4MAHKE6ZBPVYGAYYG3IDH7A.json","view_paper":"https://pith.science/paper/DMS4MAHK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02968&json=true","fetch_graph":"https://pith.science/api/pith-number/DMS4MAHKE6ZBPVYGAYYG3IDH7A/graph.json","fetch_events":"https://pith.science/api/pith-number/DMS4MAHKE6ZBPVYGAYYG3IDH7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMS4MAHKE6ZBPVYGAYYG3IDH7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMS4MAHKE6ZBPVYGAYYG3IDH7A/action/storage_attestation","attest_author":"https://pith.science/pith/DMS4MAHKE6ZBPVYGAYYG3IDH7A/action/author_attestation","sign_citation":"https://pith.science/pith/DMS4MAHKE6ZBPVYGAYYG3IDH7A/action/citation_signature","submit_replication":"https://pith.science/pith/DMS4MAHKE6ZBPVYGAYYG3IDH7A/action/replication_record"}},"created_at":"2026-07-05T08:39:44.410952+00:00","updated_at":"2026-07-05T08:39:44.410952+00:00"}