{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WI6B73RSTXZYZVYHYL2EELUIGW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5b320c31f01b9950f65d7587e8fde7c046120d6c931743098e431a0104743aeb","cross_cats_sorted":["cs.AI","cs.AR","cs.CV","cs.DC","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T10:02:32Z","title_canon_sha256":"ce24fa2423a265200fc204a4c6cb5e3b1dc8c38f13b5598ccb49b198b2fceb36"},"schema_version":"1.0","source":{"id":"2505.11067","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11067","created_at":"2026-07-05T11:04:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11067v1","created_at":"2026-07-05T11:04:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11067","created_at":"2026-07-05T11:04:10Z"},{"alias_kind":"pith_short_12","alias_value":"WI6B73RSTXZY","created_at":"2026-07-05T11:04:10Z"},{"alias_kind":"pith_short_16","alias_value":"WI6B73RSTXZYZVYH","created_at":"2026-07-05T11:04:10Z"},{"alias_kind":"pith_short_8","alias_value":"WI6B73RS","created_at":"2026-07-05T11:04:10Z"}],"graph_snapshots":[{"event_id":"sha256:0adcdda7a2e081166268496efa51d18dfe2823a65c7adc20dc551680bf27052b","target":"graph","created_at":"2026-07-05T11:04:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.11067/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Corey Lammie, Malte J. Rasch, Omobayode Fagbohungbe, Takashi Ando, Tayfun Gokmen, Vijay Narayanan","cross_cats":["cs.AI","cs.AR","cs.CV","cs.DC","cs.NE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11067","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0cc5feaa7c78047661e7ca3432b5e20500284a6a36720d58b90d902d7434e1cb","target":"record","created_at":"2026-07-05T11:04:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5b320c31f01b9950f65d7587e8fde7c046120d6c931743098e431a0104743aeb","cross_cats_sorted":["cs.AI","cs.AR","cs.CV","cs.DC","cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T10:02:32Z","title_canon_sha256":"ce24fa2423a265200fc204a4c6cb5e3b1dc8c38f13b5598ccb49b198b2fceb36"},"schema_version":"1.0","source":{"id":"2505.11067","kind":"arxiv","version":1}},"canonical_sha256":"b23c1fee329df38cd707c2f4422e8835b377d8d32b8317958ee74401a4010d90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b23c1fee329df38cd707c2f4422e8835b377d8d32b8317958ee74401a4010d90","first_computed_at":"2026-07-05T11:04:10.182938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:10.182938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8jQCwGLPVEGfq8Q1sCW9Qy99WclA2NNsXJxE1m2bwxkJTafg7+PSjjkqSH1TkklpalDZMLIXoEnXiCrmo56tCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:10.183626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11067","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cc5feaa7c78047661e7ca3432b5e20500284a6a36720d58b90d902d7434e1cb","sha256:0adcdda7a2e081166268496efa51d18dfe2823a65c7adc20dc551680bf27052b"],"state_sha256":"5ea30a35c8fccf73dfb44dba6308ff1c6591f0c8bd92860060201a2186a3086a"}