{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:66GP7TOWCEMVZASFHWLTX6BNI7","short_pith_number":"pith:66GP7TOW","schema_version":"1.0","canonical_sha256":"f78cffcdd611195c82453d973bf82d47ffae1d509d33f0bfd8b821253b31c790","source":{"kind":"arxiv","id":"2301.07635","version":1},"attestation_state":"computed","paper":{"title":"Local Learning with Neuron Groups","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Adeetya Patel, Eugene Belilovsky, Michael Eickenberg","submitted_at":"2023-01-18T16:25:10Z","abstract_excerpt":"Traditional deep network training methods optimize a monolithic objective function jointly for all the components. This can lead to various inefficiencies in terms of potential parallelization. Local learning is an approach to model-parallelism that removes the standard end-to-end learning setup and utilizes local objective functions to permit parallel learning amongst model components in a deep network. Recent works have demonstrated that variants of local learning can lead to efficient training of modern deep networks. However, in terms of how much computation can be distributed, these appro"},"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":"2301.07635","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-18T16:25:10Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"a67c9edeb3fdebf1861dd3ffd6f5e098018bc38073b4b81dd7bec19932c81a03","abstract_canon_sha256":"c9a16045d002765fa8bbaa539732917208f743593cf35f36e357741e9cc507bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:11.390840Z","signature_b64":"aa7pEbMNLOOJ7e7+uFf53vZ+vwDPoNk/lRCRlpjr8ItCWgonXL48wtj3FDjbwvz6YvSj9GjVEbD5lSaL1Hb5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f78cffcdd611195c82453d973bf82d47ffae1d509d33f0bfd8b821253b31c790","last_reissued_at":"2026-07-05T05:34:11.390436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:11.390436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local Learning with Neuron Groups","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Adeetya Patel, Eugene Belilovsky, Michael Eickenberg","submitted_at":"2023-01-18T16:25:10Z","abstract_excerpt":"Traditional deep network training methods optimize a monolithic objective function jointly for all the components. This can lead to various inefficiencies in terms of potential parallelization. Local learning is an approach to model-parallelism that removes the standard end-to-end learning setup and utilizes local objective functions to permit parallel learning amongst model components in a deep network. Recent works have demonstrated that variants of local learning can lead to efficient training of modern deep networks. However, in terms of how much computation can be distributed, these appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.07635","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/2301.07635/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":"2301.07635","created_at":"2026-07-05T05:34:11.390493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.07635v1","created_at":"2026-07-05T05:34:11.390493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.07635","created_at":"2026-07-05T05:34:11.390493+00:00"},{"alias_kind":"pith_short_12","alias_value":"66GP7TOWCEMV","created_at":"2026-07-05T05:34:11.390493+00:00"},{"alias_kind":"pith_short_16","alias_value":"66GP7TOWCEMVZASF","created_at":"2026-07-05T05:34:11.390493+00:00"},{"alias_kind":"pith_short_8","alias_value":"66GP7TOW","created_at":"2026-07-05T05:34:11.390493+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.12780","citing_title":"Faster Multi-GPU Training with PPLL: A Pipeline Parallelism Framework Leveraging Local Learning","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66GP7TOWCEMVZASFHWLTX6BNI7","json":"https://pith.science/pith/66GP7TOWCEMVZASFHWLTX6BNI7.json","graph_json":"https://pith.science/api/pith-number/66GP7TOWCEMVZASFHWLTX6BNI7/graph.json","events_json":"https://pith.science/api/pith-number/66GP7TOWCEMVZASFHWLTX6BNI7/events.json","paper":"https://pith.science/paper/66GP7TOW"},"agent_actions":{"view_html":"https://pith.science/pith/66GP7TOWCEMVZASFHWLTX6BNI7","download_json":"https://pith.science/pith/66GP7TOWCEMVZASFHWLTX6BNI7.json","view_paper":"https://pith.science/paper/66GP7TOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.07635&json=true","fetch_graph":"https://pith.science/api/pith-number/66GP7TOWCEMVZASFHWLTX6BNI7/graph.json","fetch_events":"https://pith.science/api/pith-number/66GP7TOWCEMVZASFHWLTX6BNI7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66GP7TOWCEMVZASFHWLTX6BNI7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66GP7TOWCEMVZASFHWLTX6BNI7/action/storage_attestation","attest_author":"https://pith.science/pith/66GP7TOWCEMVZASFHWLTX6BNI7/action/author_attestation","sign_citation":"https://pith.science/pith/66GP7TOWCEMVZASFHWLTX6BNI7/action/citation_signature","submit_replication":"https://pith.science/pith/66GP7TOWCEMVZASFHWLTX6BNI7/action/replication_record"}},"created_at":"2026-07-05T05:34:11.390493+00:00","updated_at":"2026-07-05T05:34:11.390493+00:00"}