{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:HBMIPTT46H2LQCQHANM3DKZ7HH","short_pith_number":"pith:HBMIPTT4","canonical_record":{"source":{"id":"2001.05992","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-16T18:48:34Z","cross_cats_sorted":["cs.NE","math.OC","stat.ML"],"title_canon_sha256":"095c773b7b292c5732cf9d2f0ed481faf0e739e1d00d8c2dd0dd0bb49c2fa56c","abstract_canon_sha256":"90f1d26dbd364eb671c411d35e66095a3649232a51be00830c8197c0456176f2"},"schema_version":"1.0"},"canonical_sha256":"385887ce7cf1f4b80a070359b1ab3f39ec23e8f93c842729b6209a84d98df18e","source":{"kind":"arxiv","id":"2001.05992","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.05992","created_at":"2026-07-05T00:33:57Z"},{"alias_kind":"arxiv_version","alias_value":"2001.05992v1","created_at":"2026-07-05T00:33:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.05992","created_at":"2026-07-05T00:33:57Z"},{"alias_kind":"pith_short_12","alias_value":"HBMIPTT46H2L","created_at":"2026-07-05T00:33:57Z"},{"alias_kind":"pith_short_16","alias_value":"HBMIPTT46H2LQCQH","created_at":"2026-07-05T00:33:57Z"},{"alias_kind":"pith_short_8","alias_value":"HBMIPTT4","created_at":"2026-07-05T00:33:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:HBMIPTT46H2LQCQHANM3DKZ7HH","target":"record","payload":{"canonical_record":{"source":{"id":"2001.05992","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-16T18:48:34Z","cross_cats_sorted":["cs.NE","math.OC","stat.ML"],"title_canon_sha256":"095c773b7b292c5732cf9d2f0ed481faf0e739e1d00d8c2dd0dd0bb49c2fa56c","abstract_canon_sha256":"90f1d26dbd364eb671c411d35e66095a3649232a51be00830c8197c0456176f2"},"schema_version":"1.0"},"canonical_sha256":"385887ce7cf1f4b80a070359b1ab3f39ec23e8f93c842729b6209a84d98df18e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:33:57.755068Z","signature_b64":"2jADpGjJRy30nKeHkPiY9F6LdnMdYNbi7tILHjkHAxO/CbMDRkkvUpZXYdb/FMuRc+Us0W35AlEfW7BCDJkqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"385887ce7cf1f4b80a070359b1ab3f39ec23e8f93c842729b6209a84d98df18e","last_reissued_at":"2026-07-05T00:33:57.754590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:33:57.754590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.05992","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":"2026-07-05T00:33:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GRHVLEBUMJUfF0vy8swn6hKM7CAXrB7MsSzeeIxw9Zdefk9RL3WklrLNv4rvGEuVOKk/pLx/l4jvz1Mjr4zzAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:50:31.452967Z"},"content_sha256":"ea5251ad5a8d9bf2a7cd6a43be76981a763d53d3e1a6501c805f565bc8b3c1ac","schema_version":"1.0","event_id":"sha256:ea5251ad5a8d9bf2a7cd6a43be76981a763d53d3e1a6501c805f565bc8b3c1ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:HBMIPTT46H2LQCQHANM3DKZ7HH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jeffrey Pennington, Lechao Xiao, Wei Hu","submitted_at":"2020-01-16T18:48:34Z","abstract_excerpt":"The selection of initial parameter values for gradient-based optimization of deep neural networks is one of the most impactful hyperparameter choices in deep learning systems, affecting both convergence times and model performance. Yet despite significant empirical and theoretical analysis, relatively little has been proved about the concrete effects of different initialization schemes. In this work, we analyze the effect of initialization in deep linear networks, and provide for the first time a rigorous proof that drawing the initial weights from the orthogonal group speeds up convergence re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.05992","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/2001.05992/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":"2026-07-05T00:33:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5NCQ8asF3AZLADK+81YKDBxeVC8did2yzhq3dngiS+4ppRW9owpzHjquKjjAFga5E401tIuUnkxNyDxv1Ht4Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:50:31.453484Z"},"content_sha256":"0e23c38f8a44bb9cc72e6ce25bbbd19177212eb79026a309934a66d44bd9afa1","schema_version":"1.0","event_id":"sha256:0e23c38f8a44bb9cc72e6ce25bbbd19177212eb79026a309934a66d44bd9afa1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HBMIPTT46H2LQCQHANM3DKZ7HH/bundle.json","state_url":"https://pith.science/pith/HBMIPTT46H2LQCQHANM3DKZ7HH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HBMIPTT46H2LQCQHANM3DKZ7HH/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":"2026-08-20T17:50:31Z","links":{"resolver":"https://pith.science/pith/HBMIPTT46H2LQCQHANM3DKZ7HH","bundle":"https://pith.science/pith/HBMIPTT46H2LQCQHANM3DKZ7HH/bundle.json","state":"https://pith.science/pith/HBMIPTT46H2LQCQHANM3DKZ7HH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HBMIPTT46H2LQCQHANM3DKZ7HH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HBMIPTT46H2LQCQHANM3DKZ7HH","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":"90f1d26dbd364eb671c411d35e66095a3649232a51be00830c8197c0456176f2","cross_cats_sorted":["cs.NE","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-16T18:48:34Z","title_canon_sha256":"095c773b7b292c5732cf9d2f0ed481faf0e739e1d00d8c2dd0dd0bb49c2fa56c"},"schema_version":"1.0","source":{"id":"2001.05992","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.05992","created_at":"2026-07-05T00:33:57Z"},{"alias_kind":"arxiv_version","alias_value":"2001.05992v1","created_at":"2026-07-05T00:33:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.05992","created_at":"2026-07-05T00:33:57Z"},{"alias_kind":"pith_short_12","alias_value":"HBMIPTT46H2L","created_at":"2026-07-05T00:33:57Z"},{"alias_kind":"pith_short_16","alias_value":"HBMIPTT46H2LQCQH","created_at":"2026-07-05T00:33:57Z"},{"alias_kind":"pith_short_8","alias_value":"HBMIPTT4","created_at":"2026-07-05T00:33:57Z"}],"graph_snapshots":[{"event_id":"sha256:0e23c38f8a44bb9cc72e6ce25bbbd19177212eb79026a309934a66d44bd9afa1","target":"graph","created_at":"2026-07-05T00:33:57Z","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/2001.05992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The selection of initial parameter values for gradient-based optimization of deep neural networks is one of the most impactful hyperparameter choices in deep learning systems, affecting both convergence times and model performance. Yet despite significant empirical and theoretical analysis, relatively little has been proved about the concrete effects of different initialization schemes. In this work, we analyze the effect of initialization in deep linear networks, and provide for the first time a rigorous proof that drawing the initial weights from the orthogonal group speeds up convergence re","authors_text":"Jeffrey Pennington, Lechao Xiao, Wei Hu","cross_cats":["cs.NE","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-16T18:48:34Z","title":"Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.05992","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:ea5251ad5a8d9bf2a7cd6a43be76981a763d53d3e1a6501c805f565bc8b3c1ac","target":"record","created_at":"2026-07-05T00:33:57Z","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":"90f1d26dbd364eb671c411d35e66095a3649232a51be00830c8197c0456176f2","cross_cats_sorted":["cs.NE","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-16T18:48:34Z","title_canon_sha256":"095c773b7b292c5732cf9d2f0ed481faf0e739e1d00d8c2dd0dd0bb49c2fa56c"},"schema_version":"1.0","source":{"id":"2001.05992","kind":"arxiv","version":1}},"canonical_sha256":"385887ce7cf1f4b80a070359b1ab3f39ec23e8f93c842729b6209a84d98df18e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"385887ce7cf1f4b80a070359b1ab3f39ec23e8f93c842729b6209a84d98df18e","first_computed_at":"2026-07-05T00:33:57.754590Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:33:57.754590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2jADpGjJRy30nKeHkPiY9F6LdnMdYNbi7tILHjkHAxO/CbMDRkkvUpZXYdb/FMuRc+Us0W35AlEfW7BCDJkqDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:33:57.755068Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.05992","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea5251ad5a8d9bf2a7cd6a43be76981a763d53d3e1a6501c805f565bc8b3c1ac","sha256:0e23c38f8a44bb9cc72e6ce25bbbd19177212eb79026a309934a66d44bd9afa1"],"state_sha256":"20cd27885b9aba7776954b1716bb1385bd481be6c5583cb00f0b5379bc724a29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ir4k43OabnkmRTgsSZYDYtMLtxWH/DrZR+F4Hyd+KjGR3oQ2TKi/nv0ASQZm6Y09zuvJ6aQn+heQYV7oX9sNCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T17:50:31.458073Z","bundle_sha256":"b4d718d017685d02b002b1ee61d4397667f3cbe041a0580fa7f71a496409614c"}}