{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AV3POWCPSUPMHDZY4M6GLJYBN6","short_pith_number":"pith:AV3POWCP","schema_version":"1.0","canonical_sha256":"0576f7584f951ec38f38e33c65a7016f938e09d25be395898a2d768a3f8b60bf","source":{"kind":"arxiv","id":"2402.09780","version":4},"attestation_state":"computed","paper":{"title":"TinyCL: An Efficient Hardware Architecture for Continual Learning on Autonomous Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alberto Marchisio, Eugenio Ressa, Guido Masera, Maurizio Martina, Muhammad Shafique","submitted_at":"2024-02-15T08:09:17Z","abstract_excerpt":"The Continuous Learning (CL) paradigm consists of continuously evolving the parameters of the Deep Neural Network (DNN) model to progressively learn to perform new tasks without reducing the performance on previous tasks, i.e., avoiding the so-called catastrophic forgetting. However, the DNN parameter update in CL-based autonomous systems is extremely resource-hungry. The existing DNN accelerators cannot be directly employed in CL because they only support the execution of the forward propagation. Only a few prior architectures execute the backpropagation and weight update, but they lack the c"},"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":"2402.09780","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T08:09:17Z","cross_cats_sorted":[],"title_canon_sha256":"6f5fc586621676894a0255633539cec824fe88e651e2a8b4a369a7095e9a1d46","abstract_canon_sha256":"752cb4dc8f0d2907398496019378e3eec4fc72e3cb115eaa52d3659d582fe7f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:59.344159Z","signature_b64":"W7q4WTiwnuWhmeKB2jseaKjL86amu4cjb16xP4YeWO7JhIn9hEqQVwJV7PDYBUasM0a2C1uEY9A/89iskZyaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0576f7584f951ec38f38e33c65a7016f938e09d25be395898a2d768a3f8b60bf","last_reissued_at":"2026-07-05T10:58:59.343563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:59.343563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TinyCL: An Efficient Hardware Architecture for Continual Learning on Autonomous Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alberto Marchisio, Eugenio Ressa, Guido Masera, Maurizio Martina, Muhammad Shafique","submitted_at":"2024-02-15T08:09:17Z","abstract_excerpt":"The Continuous Learning (CL) paradigm consists of continuously evolving the parameters of the Deep Neural Network (DNN) model to progressively learn to perform new tasks without reducing the performance on previous tasks, i.e., avoiding the so-called catastrophic forgetting. However, the DNN parameter update in CL-based autonomous systems is extremely resource-hungry. The existing DNN accelerators cannot be directly employed in CL because they only support the execution of the forward propagation. Only a few prior architectures execute the backpropagation and weight update, but they lack the c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09780","kind":"arxiv","version":4},"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/2402.09780/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":"2402.09780","created_at":"2026-07-05T10:58:59.343629+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09780v4","created_at":"2026-07-05T10:58:59.343629+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09780","created_at":"2026-07-05T10:58:59.343629+00:00"},{"alias_kind":"pith_short_12","alias_value":"AV3POWCPSUPM","created_at":"2026-07-05T10:58:59.343629+00:00"},{"alias_kind":"pith_short_16","alias_value":"AV3POWCPSUPMHDZY","created_at":"2026-07-05T10:58:59.343629+00:00"},{"alias_kind":"pith_short_8","alias_value":"AV3POWCP","created_at":"2026-07-05T10:58:59.343629+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05858","citing_title":"Genesis: A Spiking Neuromorphic Accelerator With On-chip Continual Learning","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AV3POWCPSUPMHDZY4M6GLJYBN6","json":"https://pith.science/pith/AV3POWCPSUPMHDZY4M6GLJYBN6.json","graph_json":"https://pith.science/api/pith-number/AV3POWCPSUPMHDZY4M6GLJYBN6/graph.json","events_json":"https://pith.science/api/pith-number/AV3POWCPSUPMHDZY4M6GLJYBN6/events.json","paper":"https://pith.science/paper/AV3POWCP"},"agent_actions":{"view_html":"https://pith.science/pith/AV3POWCPSUPMHDZY4M6GLJYBN6","download_json":"https://pith.science/pith/AV3POWCPSUPMHDZY4M6GLJYBN6.json","view_paper":"https://pith.science/paper/AV3POWCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09780&json=true","fetch_graph":"https://pith.science/api/pith-number/AV3POWCPSUPMHDZY4M6GLJYBN6/graph.json","fetch_events":"https://pith.science/api/pith-number/AV3POWCPSUPMHDZY4M6GLJYBN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AV3POWCPSUPMHDZY4M6GLJYBN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AV3POWCPSUPMHDZY4M6GLJYBN6/action/storage_attestation","attest_author":"https://pith.science/pith/AV3POWCPSUPMHDZY4M6GLJYBN6/action/author_attestation","sign_citation":"https://pith.science/pith/AV3POWCPSUPMHDZY4M6GLJYBN6/action/citation_signature","submit_replication":"https://pith.science/pith/AV3POWCPSUPMHDZY4M6GLJYBN6/action/replication_record"}},"created_at":"2026-07-05T10:58:59.343629+00:00","updated_at":"2026-07-05T10:58:59.343629+00:00"}