{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WI6B73RSTXZYZVYHYL2EELUIGW","short_pith_number":"pith:WI6B73RS","schema_version":"1.0","canonical_sha256":"b23c1fee329df38cd707c2f4422e8835b377d8d32b8317958ee74401a4010d90","source":{"kind":"arxiv","id":"2505.11067","version":1},"attestation_state":"computed","paper":{"title":"Assessing the Performance of Analog Training for Transfer Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.AR","cs.CV","cs.DC","cs.NE"],"primary_cat":"cs.LG","authors_text":"Corey Lammie, Malte J. Rasch, Omobayode Fagbohungbe, Takashi Ando, Tayfun Gokmen, Vijay Narayanan","submitted_at":"2025-05-16T10:02:32Z","abstract_excerpt":"Analog in-memory computing is a next-generation computing paradigm that promises fast, parallel, and energy-efficient deep learning training and transfer learning (TL). However, achieving this promise has remained elusive due to a lack of suitable training algorithms. Analog memory devices exhibit asymmetric and non-linear switching behavior in addition to device-to-device variation, meaning that most, if not all, of the current off-the-shelf training algorithms cannot achieve good training outcomes. Also, recently introduced algorithms have enjoyed limited attention, as they require bi-direct"},"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":"2505.11067","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T10:02:32Z","cross_cats_sorted":["cs.AI","cs.AR","cs.CV","cs.DC","cs.NE"],"title_canon_sha256":"ce24fa2423a265200fc204a4c6cb5e3b1dc8c38f13b5598ccb49b198b2fceb36","abstract_canon_sha256":"5b320c31f01b9950f65d7587e8fde7c046120d6c931743098e431a0104743aeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:10.183626Z","signature_b64":"8jQCwGLPVEGfq8Q1sCW9Qy99WclA2NNsXJxE1m2bwxkJTafg7+PSjjkqSH1TkklpalDZMLIXoEnXiCrmo56tCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b23c1fee329df38cd707c2f4422e8835b377d8d32b8317958ee74401a4010d90","last_reissued_at":"2026-07-05T11:04:10.182938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:10.182938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing the Performance of Analog Training for Transfer Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.AR","cs.CV","cs.DC","cs.NE"],"primary_cat":"cs.LG","authors_text":"Corey Lammie, Malte J. Rasch, Omobayode Fagbohungbe, Takashi Ando, Tayfun Gokmen, Vijay Narayanan","submitted_at":"2025-05-16T10:02:32Z","abstract_excerpt":"Analog in-memory computing is a next-generation computing paradigm that promises fast, parallel, and energy-efficient deep learning training and transfer learning (TL). However, achieving this promise has remained elusive due to a lack of suitable training algorithms. Analog memory devices exhibit asymmetric and non-linear switching behavior in addition to device-to-device variation, meaning that most, if not all, of the current off-the-shelf training algorithms cannot achieve good training outcomes. Also, recently introduced algorithms have enjoyed limited attention, as they require bi-direct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11067","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/2505.11067/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":"2505.11067","created_at":"2026-07-05T11:04:10.183009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11067v1","created_at":"2026-07-05T11:04:10.183009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11067","created_at":"2026-07-05T11:04:10.183009+00:00"},{"alias_kind":"pith_short_12","alias_value":"WI6B73RSTXZY","created_at":"2026-07-05T11:04:10.183009+00:00"},{"alias_kind":"pith_short_16","alias_value":"WI6B73RSTXZYZVYH","created_at":"2026-07-05T11:04:10.183009+00:00"},{"alias_kind":"pith_short_8","alias_value":"WI6B73RS","created_at":"2026-07-05T11:04:10.183009+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/WI6B73RSTXZYZVYHYL2EELUIGW","json":"https://pith.science/pith/WI6B73RSTXZYZVYHYL2EELUIGW.json","graph_json":"https://pith.science/api/pith-number/WI6B73RSTXZYZVYHYL2EELUIGW/graph.json","events_json":"https://pith.science/api/pith-number/WI6B73RSTXZYZVYHYL2EELUIGW/events.json","paper":"https://pith.science/paper/WI6B73RS"},"agent_actions":{"view_html":"https://pith.science/pith/WI6B73RSTXZYZVYHYL2EELUIGW","download_json":"https://pith.science/pith/WI6B73RSTXZYZVYHYL2EELUIGW.json","view_paper":"https://pith.science/paper/WI6B73RS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11067&json=true","fetch_graph":"https://pith.science/api/pith-number/WI6B73RSTXZYZVYHYL2EELUIGW/graph.json","fetch_events":"https://pith.science/api/pith-number/WI6B73RSTXZYZVYHYL2EELUIGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WI6B73RSTXZYZVYHYL2EELUIGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WI6B73RSTXZYZVYHYL2EELUIGW/action/storage_attestation","attest_author":"https://pith.science/pith/WI6B73RSTXZYZVYHYL2EELUIGW/action/author_attestation","sign_citation":"https://pith.science/pith/WI6B73RSTXZYZVYHYL2EELUIGW/action/citation_signature","submit_replication":"https://pith.science/pith/WI6B73RSTXZYZVYHYL2EELUIGW/action/replication_record"}},"created_at":"2026-07-05T11:04:10.183009+00:00","updated_at":"2026-07-05T11:04:10.183009+00:00"}