{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SHIPL4P2MAMOPCIEAOND6RL6JI","short_pith_number":"pith:SHIPL4P2","schema_version":"1.0","canonical_sha256":"91d0f5f1fa6018e78904039a3f457e4a0c8b65bec53fd9d242701c1616fad77e","source":{"kind":"arxiv","id":"2207.06810","version":1},"attestation_state":"computed","paper":{"title":"In-memory Realization of In-situ Few-shot Continual Learning with a Dynamically Evolving Explicit Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abbas Rahimi, Abu Sebastian, Geethan Karunaratne, Giovanni Cherubini, INJO OK, Ishtiaq Ahsan, Jovin Langenegger, Kevin Brew, Luca Benini, Manuel Le Gallo-Bourdeau, Mary Claire Silvestre, Michael Hersche, Nicole Saulnier, Ning Li, Sam Choi, Urs Egger, Victor Chan, Vijay Narayanan","submitted_at":"2022-07-14T10:38:21Z","abstract_excerpt":"Continually learning new classes from a few training examples without forgetting previous old classes demands a flexible architecture with an inevitably growing portion of storage, in which new examples and classes can be incrementally stored and efficiently retrieved. One viable architectural solution is to tightly couple a stationary deep neural network to a dynamically evolving explicit memory (EM). As the centerpiece of this architecture, we propose an EM unit that leverages energy-efficient in-memory compute (IMC) cores during the course of continual learning operations. We demonstrate fo"},"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":"2207.06810","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-14T10:38:21Z","cross_cats_sorted":[],"title_canon_sha256":"ddbdb388b526bbed61e9967b32c20e76b60e90a65b61ed167b2c26f2498cf1bc","abstract_canon_sha256":"0a1e36da8e439a168124991898462683fa1a1c43e812df6811e2283a67507f4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:17.353289Z","signature_b64":"0vEaeW6KNYFvMqjDvWo+vK7e9gIRgvGqeZ7daRpPz+vrAMNzvCklOzkM02fLC3eXs06/zQFRJDfU2D9EHwEsDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91d0f5f1fa6018e78904039a3f457e4a0c8b65bec53fd9d242701c1616fad77e","last_reissued_at":"2026-07-05T04:40:17.352800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:17.352800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-memory Realization of In-situ Few-shot Continual Learning with a Dynamically Evolving Explicit Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abbas Rahimi, Abu Sebastian, Geethan Karunaratne, Giovanni Cherubini, INJO OK, Ishtiaq Ahsan, Jovin Langenegger, Kevin Brew, Luca Benini, Manuel Le Gallo-Bourdeau, Mary Claire Silvestre, Michael Hersche, Nicole Saulnier, Ning Li, Sam Choi, Urs Egger, Victor Chan, Vijay Narayanan","submitted_at":"2022-07-14T10:38:21Z","abstract_excerpt":"Continually learning new classes from a few training examples without forgetting previous old classes demands a flexible architecture with an inevitably growing portion of storage, in which new examples and classes can be incrementally stored and efficiently retrieved. One viable architectural solution is to tightly couple a stationary deep neural network to a dynamically evolving explicit memory (EM). As the centerpiece of this architecture, we propose an EM unit that leverages energy-efficient in-memory compute (IMC) cores during the course of continual learning operations. We demonstrate fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06810","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/2207.06810/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":"2207.06810","created_at":"2026-07-05T04:40:17.352872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.06810v1","created_at":"2026-07-05T04:40:17.352872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06810","created_at":"2026-07-05T04:40:17.352872+00:00"},{"alias_kind":"pith_short_12","alias_value":"SHIPL4P2MAMO","created_at":"2026-07-05T04:40:17.352872+00:00"},{"alias_kind":"pith_short_16","alias_value":"SHIPL4P2MAMOPCIE","created_at":"2026-07-05T04:40:17.352872+00:00"},{"alias_kind":"pith_short_8","alias_value":"SHIPL4P2","created_at":"2026-07-05T04:40:17.352872+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SHIPL4P2MAMOPCIEAOND6RL6JI","json":"https://pith.science/pith/SHIPL4P2MAMOPCIEAOND6RL6JI.json","graph_json":"https://pith.science/api/pith-number/SHIPL4P2MAMOPCIEAOND6RL6JI/graph.json","events_json":"https://pith.science/api/pith-number/SHIPL4P2MAMOPCIEAOND6RL6JI/events.json","paper":"https://pith.science/paper/SHIPL4P2"},"agent_actions":{"view_html":"https://pith.science/pith/SHIPL4P2MAMOPCIEAOND6RL6JI","download_json":"https://pith.science/pith/SHIPL4P2MAMOPCIEAOND6RL6JI.json","view_paper":"https://pith.science/paper/SHIPL4P2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.06810&json=true","fetch_graph":"https://pith.science/api/pith-number/SHIPL4P2MAMOPCIEAOND6RL6JI/graph.json","fetch_events":"https://pith.science/api/pith-number/SHIPL4P2MAMOPCIEAOND6RL6JI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SHIPL4P2MAMOPCIEAOND6RL6JI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SHIPL4P2MAMOPCIEAOND6RL6JI/action/storage_attestation","attest_author":"https://pith.science/pith/SHIPL4P2MAMOPCIEAOND6RL6JI/action/author_attestation","sign_citation":"https://pith.science/pith/SHIPL4P2MAMOPCIEAOND6RL6JI/action/citation_signature","submit_replication":"https://pith.science/pith/SHIPL4P2MAMOPCIEAOND6RL6JI/action/replication_record"}},"created_at":"2026-07-05T04:40:17.352872+00:00","updated_at":"2026-07-05T04:40:17.352872+00:00"}