{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D7VZJ4RVKOGNCB2S25OSOBGPO7","short_pith_number":"pith:D7VZJ4RV","schema_version":"1.0","canonical_sha256":"1feb94f235538cd10752d75d2704cf77f9b0f6999ab9fb855bdb77891d8570fe","source":{"kind":"arxiv","id":"2403.12116","version":4},"attestation_state":"computed","paper":{"title":"Unsupervised End-to-End Training with a Self-Defined Target","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.ET","cs.LG"],"primary_cat":"cs.NE","authors_text":"Adrien Pontlevy, Damien Querlioz, Dongshu Liu, J\\'er\\'emie Laydevant, Julie Grollier","submitted_at":"2024-03-18T16:14:28Z","abstract_excerpt":"Designing algorithms for versatile AI hardware that can learn on the edge using both labeled and unlabeled data is challenging. Deep end-to-end training methods incorporating phases of self-supervised and supervised learning are accurate and adaptable to input data but self-supervised learning requires even more computational and memory resources than supervised learning, too high for current embedded hardware. Conversely, unsupervised layer-by-layer training, such as Hebbian learning, is more compatible with existing hardware but does not integrate well with supervised learning. To address th"},"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":"2403.12116","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2024-03-18T16:14:28Z","cross_cats_sorted":["cs.ET","cs.LG"],"title_canon_sha256":"1a6799dfa01c89d412787de125ae4aba991aa32f263b7f5db38491eb760d29a3","abstract_canon_sha256":"0df95d74dac27ba2e7d8dc5b90e095a1f4c17ad526621cbe102773279a3ba484"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:25.051483Z","signature_b64":"kxPw8Ur8bFYdiHAZlBr4hNn5uiAwHl8XtzVirTqfUYP1Tg77uxZK8ICDzHXV81UmjotDGzed+ZkFdZpe9M6lBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1feb94f235538cd10752d75d2704cf77f9b0f6999ab9fb855bdb77891d8570fe","last_reissued_at":"2026-07-05T09:38:25.051000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:25.051000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised End-to-End Training with a Self-Defined Target","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.ET","cs.LG"],"primary_cat":"cs.NE","authors_text":"Adrien Pontlevy, Damien Querlioz, Dongshu Liu, J\\'er\\'emie Laydevant, Julie Grollier","submitted_at":"2024-03-18T16:14:28Z","abstract_excerpt":"Designing algorithms for versatile AI hardware that can learn on the edge using both labeled and unlabeled data is challenging. Deep end-to-end training methods incorporating phases of self-supervised and supervised learning are accurate and adaptable to input data but self-supervised learning requires even more computational and memory resources than supervised learning, too high for current embedded hardware. Conversely, unsupervised layer-by-layer training, such as Hebbian learning, is more compatible with existing hardware but does not integrate well with supervised learning. To address th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12116","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/2403.12116/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":"2403.12116","created_at":"2026-07-05T09:38:25.051053+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12116v4","created_at":"2026-07-05T09:38:25.051053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12116","created_at":"2026-07-05T09:38:25.051053+00:00"},{"alias_kind":"pith_short_12","alias_value":"D7VZJ4RVKOGN","created_at":"2026-07-05T09:38:25.051053+00:00"},{"alias_kind":"pith_short_16","alias_value":"D7VZJ4RVKOGNCB2S","created_at":"2026-07-05T09:38:25.051053+00:00"},{"alias_kind":"pith_short_8","alias_value":"D7VZJ4RV","created_at":"2026-07-05T09:38:25.051053+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/D7VZJ4RVKOGNCB2S25OSOBGPO7","json":"https://pith.science/pith/D7VZJ4RVKOGNCB2S25OSOBGPO7.json","graph_json":"https://pith.science/api/pith-number/D7VZJ4RVKOGNCB2S25OSOBGPO7/graph.json","events_json":"https://pith.science/api/pith-number/D7VZJ4RVKOGNCB2S25OSOBGPO7/events.json","paper":"https://pith.science/paper/D7VZJ4RV"},"agent_actions":{"view_html":"https://pith.science/pith/D7VZJ4RVKOGNCB2S25OSOBGPO7","download_json":"https://pith.science/pith/D7VZJ4RVKOGNCB2S25OSOBGPO7.json","view_paper":"https://pith.science/paper/D7VZJ4RV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12116&json=true","fetch_graph":"https://pith.science/api/pith-number/D7VZJ4RVKOGNCB2S25OSOBGPO7/graph.json","fetch_events":"https://pith.science/api/pith-number/D7VZJ4RVKOGNCB2S25OSOBGPO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D7VZJ4RVKOGNCB2S25OSOBGPO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D7VZJ4RVKOGNCB2S25OSOBGPO7/action/storage_attestation","attest_author":"https://pith.science/pith/D7VZJ4RVKOGNCB2S25OSOBGPO7/action/author_attestation","sign_citation":"https://pith.science/pith/D7VZJ4RVKOGNCB2S25OSOBGPO7/action/citation_signature","submit_replication":"https://pith.science/pith/D7VZJ4RVKOGNCB2S25OSOBGPO7/action/replication_record"}},"created_at":"2026-07-05T09:38:25.051053+00:00","updated_at":"2026-07-05T09:38:25.051053+00:00"}