{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MF7ZK3HGNE626HMIO6IUTLZPLR","short_pith_number":"pith:MF7ZK3HG","canonical_record":{"source":{"id":"2307.06565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-13T05:33:44Z","cross_cats_sorted":[],"title_canon_sha256":"1b33d83664e7a6a2275b8cd1ccad9b3c7391fe9d2f24a28b62dc37c579df0d59","abstract_canon_sha256":"893ba56c852d8c714e2c79af4705bcd191240a7730f5664196692ec8626231d4"},"schema_version":"1.0"},"canonical_sha256":"617f956ce6693daf1d88779149af2f5c7e0cd9dc5a48fdda48dd761f30dd7354","source":{"kind":"arxiv","id":"2307.06565","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06565","created_at":"2026-07-05T06:30:35Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06565v1","created_at":"2026-07-05T06:30:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06565","created_at":"2026-07-05T06:30:35Z"},{"alias_kind":"pith_short_12","alias_value":"MF7ZK3HGNE62","created_at":"2026-07-05T06:30:35Z"},{"alias_kind":"pith_short_16","alias_value":"MF7ZK3HGNE626HMI","created_at":"2026-07-05T06:30:35Z"},{"alias_kind":"pith_short_8","alias_value":"MF7ZK3HG","created_at":"2026-07-05T06:30:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MF7ZK3HGNE626HMIO6IUTLZPLR","target":"record","payload":{"canonical_record":{"source":{"id":"2307.06565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-13T05:33:44Z","cross_cats_sorted":[],"title_canon_sha256":"1b33d83664e7a6a2275b8cd1ccad9b3c7391fe9d2f24a28b62dc37c579df0d59","abstract_canon_sha256":"893ba56c852d8c714e2c79af4705bcd191240a7730f5664196692ec8626231d4"},"schema_version":"1.0"},"canonical_sha256":"617f956ce6693daf1d88779149af2f5c7e0cd9dc5a48fdda48dd761f30dd7354","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:35.132256Z","signature_b64":"9YgqKgfNrNWHp24R0bS7RYHx69pzSP3CMl4TETw3hsju6LA2AF7f3KFmAsPPCDdj/LqfQIj7EpSJxmYtomlkAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"617f956ce6693daf1d88779149af2f5c7e0cd9dc5a48fdda48dd761f30dd7354","last_reissued_at":"2026-07-05T06:30:35.131769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:35.131769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.06565","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:30:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rk5HP3avpYy5wQsnF7Swyd6APFxTg67P58yvZr9UP+OLKwDmH8wKI5/sK8gLlCrnW/QXYmEmzDaILlS/AOoMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:51:30.024798Z"},"content_sha256":"ea9139044dbef7a9a76dd66c51c137323fc0a45b6ee09834c6c11b1b9b93f270","schema_version":"1.0","event_id":"sha256:ea9139044dbef7a9a76dd66c51c137323fc0a45b6ee09834c6c11b1b9b93f270"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MF7ZK3HGNE626HMIO6IUTLZPLR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient SGD Neural Network Training via Sublinear Activated Neuron Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lianke Qin, Yuanyuan Yang, Zhao Song","submitted_at":"2023-07-13T05:33:44Z","abstract_excerpt":"Deep learning has been widely used in many fields, but the model training process usually consumes massive computational resources and time. Therefore, designing an efficient neural network training method with a provable convergence guarantee is a fundamental and important research question. In this paper, we present a static half-space report data structure that consists of a fully connected two-layer neural network for shifted ReLU activation to enable activated neuron identification in sublinear time via geometric search. We also prove that our algorithm can converge in $O(M^2/\\epsilon^2)$"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06565","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/2307.06565/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:30:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QXQQFDVHfiZ65h+EK8GDksKmztsgZZck51zsJMOnu26WTI9m0YWKgz7TTp8S3k970vCAXKj+NNBwmLt/yxbRCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:51:30.025178Z"},"content_sha256":"7d8175647cf79da1160c1e4791cf2cc6cc79610465c64f16153f28616da3f406","schema_version":"1.0","event_id":"sha256:7d8175647cf79da1160c1e4791cf2cc6cc79610465c64f16153f28616da3f406"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MF7ZK3HGNE626HMIO6IUTLZPLR/bundle.json","state_url":"https://pith.science/pith/MF7ZK3HGNE626HMIO6IUTLZPLR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MF7ZK3HGNE626HMIO6IUTLZPLR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T03:51:30Z","links":{"resolver":"https://pith.science/pith/MF7ZK3HGNE626HMIO6IUTLZPLR","bundle":"https://pith.science/pith/MF7ZK3HGNE626HMIO6IUTLZPLR/bundle.json","state":"https://pith.science/pith/MF7ZK3HGNE626HMIO6IUTLZPLR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MF7ZK3HGNE626HMIO6IUTLZPLR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MF7ZK3HGNE626HMIO6IUTLZPLR","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":"893ba56c852d8c714e2c79af4705bcd191240a7730f5664196692ec8626231d4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-13T05:33:44Z","title_canon_sha256":"1b33d83664e7a6a2275b8cd1ccad9b3c7391fe9d2f24a28b62dc37c579df0d59"},"schema_version":"1.0","source":{"id":"2307.06565","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06565","created_at":"2026-07-05T06:30:35Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06565v1","created_at":"2026-07-05T06:30:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06565","created_at":"2026-07-05T06:30:35Z"},{"alias_kind":"pith_short_12","alias_value":"MF7ZK3HGNE62","created_at":"2026-07-05T06:30:35Z"},{"alias_kind":"pith_short_16","alias_value":"MF7ZK3HGNE626HMI","created_at":"2026-07-05T06:30:35Z"},{"alias_kind":"pith_short_8","alias_value":"MF7ZK3HG","created_at":"2026-07-05T06:30:35Z"}],"graph_snapshots":[{"event_id":"sha256:7d8175647cf79da1160c1e4791cf2cc6cc79610465c64f16153f28616da3f406","target":"graph","created_at":"2026-07-05T06:30:35Z","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/2307.06565/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning has been widely used in many fields, but the model training process usually consumes massive computational resources and time. Therefore, designing an efficient neural network training method with a provable convergence guarantee is a fundamental and important research question. In this paper, we present a static half-space report data structure that consists of a fully connected two-layer neural network for shifted ReLU activation to enable activated neuron identification in sublinear time via geometric search. We also prove that our algorithm can converge in $O(M^2/\\epsilon^2)$","authors_text":"Lianke Qin, Yuanyuan Yang, Zhao Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-13T05:33:44Z","title":"Efficient SGD Neural Network Training via Sublinear Activated Neuron Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06565","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:ea9139044dbef7a9a76dd66c51c137323fc0a45b6ee09834c6c11b1b9b93f270","target":"record","created_at":"2026-07-05T06:30:35Z","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":"893ba56c852d8c714e2c79af4705bcd191240a7730f5664196692ec8626231d4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-13T05:33:44Z","title_canon_sha256":"1b33d83664e7a6a2275b8cd1ccad9b3c7391fe9d2f24a28b62dc37c579df0d59"},"schema_version":"1.0","source":{"id":"2307.06565","kind":"arxiv","version":1}},"canonical_sha256":"617f956ce6693daf1d88779149af2f5c7e0cd9dc5a48fdda48dd761f30dd7354","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"617f956ce6693daf1d88779149af2f5c7e0cd9dc5a48fdda48dd761f30dd7354","first_computed_at":"2026-07-05T06:30:35.131769Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:30:35.131769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9YgqKgfNrNWHp24R0bS7RYHx69pzSP3CMl4TETw3hsju6LA2AF7f3KFmAsPPCDdj/LqfQIj7EpSJxmYtomlkAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:30:35.132256Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.06565","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea9139044dbef7a9a76dd66c51c137323fc0a45b6ee09834c6c11b1b9b93f270","sha256:7d8175647cf79da1160c1e4791cf2cc6cc79610465c64f16153f28616da3f406"],"state_sha256":"4b24188bcab51ad3736ac684610c78d9cc71c3e3bc1da70efd4ea33380c2db7d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"My4OCyr7BTJwFGWm3BR6Y0AKxn6CUd+xWEHwgQGQIYoKesJKtO7nL7CbMo5SA02ItidL43YllEM3XUQe+AseCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:51:30.027173Z","bundle_sha256":"d4c4eedc83b234c6de0ad961cba214fcee0a4f4a40528e8c9cb8100eab5d39fc"}}