{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PY6XETD4KV6HZFI6KOMYFZY2GD","short_pith_number":"pith:PY6XETD4","canonical_record":{"source":{"id":"2010.02519","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-05T14:36:59Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"0d30b4f7e1ff2a4d36c0b970e37e7bc49f568ebd45e13ce7ba59554b265b907b","abstract_canon_sha256":"0d15d865ab948cede4a2c5fb4654ffa81a39fac196b55c8840fbaf0e701edb83"},"schema_version":"1.0"},"canonical_sha256":"7e3d724c7c557c7c951e539982e71a30e2bb6ad8d874f1aaeeb419d2f9b22657","source":{"kind":"arxiv","id":"2010.02519","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.02519","created_at":"2026-07-05T01:47:33Z"},{"alias_kind":"arxiv_version","alias_value":"2010.02519v2","created_at":"2026-07-05T01:47:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02519","created_at":"2026-07-05T01:47:33Z"},{"alias_kind":"pith_short_12","alias_value":"PY6XETD4KV6H","created_at":"2026-07-05T01:47:33Z"},{"alias_kind":"pith_short_16","alias_value":"PY6XETD4KV6HZFI6","created_at":"2026-07-05T01:47:33Z"},{"alias_kind":"pith_short_8","alias_value":"PY6XETD4","created_at":"2026-07-05T01:47:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PY6XETD4KV6HZFI6KOMYFZY2GD","target":"record","payload":{"canonical_record":{"source":{"id":"2010.02519","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-05T14:36:59Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"0d30b4f7e1ff2a4d36c0b970e37e7bc49f568ebd45e13ce7ba59554b265b907b","abstract_canon_sha256":"0d15d865ab948cede4a2c5fb4654ffa81a39fac196b55c8840fbaf0e701edb83"},"schema_version":"1.0"},"canonical_sha256":"7e3d724c7c557c7c951e539982e71a30e2bb6ad8d874f1aaeeb419d2f9b22657","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:33.065582Z","signature_b64":"eNgAyny+6idcYlrOwPCM/rffOybn8x4BIxIEtWplgCjmJkBUQgOrSlgKMbBULKkDzoS8ISSec46DfLEa6sAhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e3d724c7c557c7c951e539982e71a30e2bb6ad8d874f1aaeeb419d2f9b22657","last_reissued_at":"2026-07-05T01:47:33.065156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:33.065156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.02519","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:47:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jFXzl86JCIl6taYbg4WF7leQI4U9kghXXk0wYmJK0SUwmR4m9IwNhvgxkCcLK2ZYCunhPX2txA6Fk8irZXHXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T15:36:16.369459Z"},"content_sha256":"94968228deddc228af385d64e68b574784d94f387ac8feb8b4d8b859eddc3ed3","schema_version":"1.0","event_id":"sha256:94968228deddc228af385d64e68b574784d94f387ac8feb8b4d8b859eddc3ed3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PY6XETD4KV6HZFI6KOMYFZY2GD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improved Analysis of Clipping Algorithms for Non-convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bohang Zhang, Cong Fang, Jikai Jin, Liwei Wang","submitted_at":"2020-10-05T14:36:59Z","abstract_excerpt":"Gradient clipping is commonly used in training deep neural networks partly due to its practicability in relieving the exploding gradient problem. Recently, \\citet{zhang2019gradient} show that clipped (stochastic) Gradient Descent (GD) converges faster than vanilla GD/SGD via introducing a new assumption called $(L_0, L_1)$-smoothness, which characterizes the violent fluctuation of gradients typically encountered in deep neural networks. However, their iteration complexities on the problem-dependent parameters are rather pessimistic, and theoretical justification of clipping combined with other"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02519","kind":"arxiv","version":2},"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/2010.02519/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":"2026-07-05T01:47:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3l2d+hLZdJrXbCCD66bYM00+Ncc8DoTu2TP6VIDHKqYGhK8blcvCd7ZpFSU5oXSkfo4LCYRt0SjzhgfITiC8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T15:36:16.370259Z"},"content_sha256":"6abbadf2e3d0805377877b28377c8a5ab467f0e48c267c42293109c7c6675a9a","schema_version":"1.0","event_id":"sha256:6abbadf2e3d0805377877b28377c8a5ab467f0e48c267c42293109c7c6675a9a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PY6XETD4KV6HZFI6KOMYFZY2GD/bundle.json","state_url":"https://pith.science/pith/PY6XETD4KV6HZFI6KOMYFZY2GD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PY6XETD4KV6HZFI6KOMYFZY2GD/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":"2026-08-10T15:36:16Z","links":{"resolver":"https://pith.science/pith/PY6XETD4KV6HZFI6KOMYFZY2GD","bundle":"https://pith.science/pith/PY6XETD4KV6HZFI6KOMYFZY2GD/bundle.json","state":"https://pith.science/pith/PY6XETD4KV6HZFI6KOMYFZY2GD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PY6XETD4KV6HZFI6KOMYFZY2GD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PY6XETD4KV6HZFI6KOMYFZY2GD","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":"0d15d865ab948cede4a2c5fb4654ffa81a39fac196b55c8840fbaf0e701edb83","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-05T14:36:59Z","title_canon_sha256":"0d30b4f7e1ff2a4d36c0b970e37e7bc49f568ebd45e13ce7ba59554b265b907b"},"schema_version":"1.0","source":{"id":"2010.02519","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.02519","created_at":"2026-07-05T01:47:33Z"},{"alias_kind":"arxiv_version","alias_value":"2010.02519v2","created_at":"2026-07-05T01:47:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02519","created_at":"2026-07-05T01:47:33Z"},{"alias_kind":"pith_short_12","alias_value":"PY6XETD4KV6H","created_at":"2026-07-05T01:47:33Z"},{"alias_kind":"pith_short_16","alias_value":"PY6XETD4KV6HZFI6","created_at":"2026-07-05T01:47:33Z"},{"alias_kind":"pith_short_8","alias_value":"PY6XETD4","created_at":"2026-07-05T01:47:33Z"}],"graph_snapshots":[{"event_id":"sha256:6abbadf2e3d0805377877b28377c8a5ab467f0e48c267c42293109c7c6675a9a","target":"graph","created_at":"2026-07-05T01:47:33Z","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/2010.02519/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gradient clipping is commonly used in training deep neural networks partly due to its practicability in relieving the exploding gradient problem. Recently, \\citet{zhang2019gradient} show that clipped (stochastic) Gradient Descent (GD) converges faster than vanilla GD/SGD via introducing a new assumption called $(L_0, L_1)$-smoothness, which characterizes the violent fluctuation of gradients typically encountered in deep neural networks. However, their iteration complexities on the problem-dependent parameters are rather pessimistic, and theoretical justification of clipping combined with other","authors_text":"Bohang Zhang, Cong Fang, Jikai Jin, Liwei Wang","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-05T14:36:59Z","title":"Improved Analysis of Clipping Algorithms for Non-convex Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02519","kind":"arxiv","version":2},"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":"sha256:94968228deddc228af385d64e68b574784d94f387ac8feb8b4d8b859eddc3ed3","target":"record","created_at":"2026-07-05T01:47:33Z","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":"0d15d865ab948cede4a2c5fb4654ffa81a39fac196b55c8840fbaf0e701edb83","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-05T14:36:59Z","title_canon_sha256":"0d30b4f7e1ff2a4d36c0b970e37e7bc49f568ebd45e13ce7ba59554b265b907b"},"schema_version":"1.0","source":{"id":"2010.02519","kind":"arxiv","version":2}},"canonical_sha256":"7e3d724c7c557c7c951e539982e71a30e2bb6ad8d874f1aaeeb419d2f9b22657","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e3d724c7c557c7c951e539982e71a30e2bb6ad8d874f1aaeeb419d2f9b22657","first_computed_at":"2026-07-05T01:47:33.065156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:47:33.065156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eNgAyny+6idcYlrOwPCM/rffOybn8x4BIxIEtWplgCjmJkBUQgOrSlgKMbBULKkDzoS8ISSec46DfLEa6sAhBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:47:33.065582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.02519","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94968228deddc228af385d64e68b574784d94f387ac8feb8b4d8b859eddc3ed3","sha256:6abbadf2e3d0805377877b28377c8a5ab467f0e48c267c42293109c7c6675a9a"],"state_sha256":"65875f2bef9614cee61ddbde0e1f38757b32d67e118625fbda3598d244899a8a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3WBUQupNkpynpwU5iOZqkcLkwfmOMoa/wywEYDuWAqPds7TFQu45qLkjXDj21CG4WFK731TRDdI3swBmStCQCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T15:36:16.374919Z","bundle_sha256":"c3f8138d69073d6f76766e81f40b86f6027b068aee0cff8c24bd1229ca510902"}}