{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KPOFZDJ4OIHWKTQUU2YXRKJPAV","short_pith_number":"pith:KPOFZDJ4","canonical_record":{"source":{"id":"2303.00883","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-02T00:57:38Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"367c50240177c9dd7e53401729549d120bc51f3c41593e8b468f4c0463457ec0","abstract_canon_sha256":"40da724b3d1b00f28caf10ec3724900cfc596d4849699ce0f34abd4ab0b89a7f"},"schema_version":"1.0"},"canonical_sha256":"53dc5c8d3c720f654e14a6b178a92f05472734c6d1ec27f278f29fc3c24e17a6","source":{"kind":"arxiv","id":"2303.00883","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.00883","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"arxiv_version","alias_value":"2303.00883v2","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00883","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"pith_short_12","alias_value":"KPOFZDJ4OIHW","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"pith_short_16","alias_value":"KPOFZDJ4OIHWKTQU","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"pith_short_8","alias_value":"KPOFZDJ4","created_at":"2026-07-05T06:17:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KPOFZDJ4OIHWKTQUU2YXRKJPAV","target":"record","payload":{"canonical_record":{"source":{"id":"2303.00883","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-02T00:57:38Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"367c50240177c9dd7e53401729549d120bc51f3c41593e8b468f4c0463457ec0","abstract_canon_sha256":"40da724b3d1b00f28caf10ec3724900cfc596d4849699ce0f34abd4ab0b89a7f"},"schema_version":"1.0"},"canonical_sha256":"53dc5c8d3c720f654e14a6b178a92f05472734c6d1ec27f278f29fc3c24e17a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:05.206493Z","signature_b64":"JUKdkspjUyGtX6KmQToTtSJ2CPr5TRTKPcs+mp7LkIa97/oraJ0w1aheRts5xfKmZr8UPtQpGHyAlZal5xP5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53dc5c8d3c720f654e14a6b178a92f05472734c6d1ec27f278f29fc3c24e17a6","last_reissued_at":"2026-07-05T06:17:05.206071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:05.206071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.00883","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":"2026-07-05T06:17:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IMr/ZUU7nfm3U1IjU8uckZl9ORUt5j4X5obmVIptPFfKM6xa/OfH5eFef9dTmCaFbfO2amgtMFdv5wwqRRgcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T03:06:26.432242Z"},"content_sha256":"9fc120a75758e549b5a73db15bd5db72bed7b98aa032ec405ceab53555125ca6","schema_version":"1.0","event_id":"sha256:9fc120a75758e549b5a73db15bd5db72bed7b98aa032ec405ceab53555125ca6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KPOFZDJ4OIHWKTQUU2YXRKJPAV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variance-reduced Clipping for Non-convex Optimization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ali Jadbabaie, Amirhossein Reisizadeh, Haochuan Li, Subhro Das","submitted_at":"2023-03-02T00:57:38Z","abstract_excerpt":"Gradient clipping is a standard training technique used in deep learning applications such as large-scale language modeling to mitigate exploding gradients. Recent experimental studies have demonstrated a fairly special behavior in the smoothness of the training objective along its trajectory when trained with gradient clipping. That is, the smoothness grows with the gradient norm. This is in clear contrast to the well-established assumption in folklore non-convex optimization, a.k.a. $L$--smoothness, where the smoothness is assumed to be bounded by a constant $L$ globally. The recently introd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00883","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/2303.00883/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":"2026-07-05T06:17:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TMi4nDq1wLNrJKUQSEO2mRsRjnUFVQQjQscp3VEzwtFEvA/VbJrqizBqiDSOyShY6iH8FIFn+gp5s3WHSBsNCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T03:06:26.432961Z"},"content_sha256":"30d999aded90bcb5b9eba83656735e1b943989b7342b2de06a238cbdada79a33","schema_version":"1.0","event_id":"sha256:30d999aded90bcb5b9eba83656735e1b943989b7342b2de06a238cbdada79a33"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KPOFZDJ4OIHWKTQUU2YXRKJPAV/bundle.json","state_url":"https://pith.science/pith/KPOFZDJ4OIHWKTQUU2YXRKJPAV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KPOFZDJ4OIHWKTQUU2YXRKJPAV/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":"2026-08-14T03:06:26Z","links":{"resolver":"https://pith.science/pith/KPOFZDJ4OIHWKTQUU2YXRKJPAV","bundle":"https://pith.science/pith/KPOFZDJ4OIHWKTQUU2YXRKJPAV/bundle.json","state":"https://pith.science/pith/KPOFZDJ4OIHWKTQUU2YXRKJPAV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KPOFZDJ4OIHWKTQUU2YXRKJPAV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KPOFZDJ4OIHWKTQUU2YXRKJPAV","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":"40da724b3d1b00f28caf10ec3724900cfc596d4849699ce0f34abd4ab0b89a7f","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-02T00:57:38Z","title_canon_sha256":"367c50240177c9dd7e53401729549d120bc51f3c41593e8b468f4c0463457ec0"},"schema_version":"1.0","source":{"id":"2303.00883","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.00883","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"arxiv_version","alias_value":"2303.00883v2","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00883","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"pith_short_12","alias_value":"KPOFZDJ4OIHW","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"pith_short_16","alias_value":"KPOFZDJ4OIHWKTQU","created_at":"2026-07-05T06:17:05Z"},{"alias_kind":"pith_short_8","alias_value":"KPOFZDJ4","created_at":"2026-07-05T06:17:05Z"}],"graph_snapshots":[{"event_id":"sha256:30d999aded90bcb5b9eba83656735e1b943989b7342b2de06a238cbdada79a33","target":"graph","created_at":"2026-07-05T06:17:05Z","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/2303.00883/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gradient clipping is a standard training technique used in deep learning applications such as large-scale language modeling to mitigate exploding gradients. Recent experimental studies have demonstrated a fairly special behavior in the smoothness of the training objective along its trajectory when trained with gradient clipping. That is, the smoothness grows with the gradient norm. This is in clear contrast to the well-established assumption in folklore non-convex optimization, a.k.a. $L$--smoothness, where the smoothness is assumed to be bounded by a constant $L$ globally. The recently introd","authors_text":"Ali Jadbabaie, Amirhossein Reisizadeh, Haochuan Li, Subhro Das","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-02T00:57:38Z","title":"Variance-reduced Clipping for Non-convex Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00883","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":"sha256:9fc120a75758e549b5a73db15bd5db72bed7b98aa032ec405ceab53555125ca6","target":"record","created_at":"2026-07-05T06:17:05Z","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":"40da724b3d1b00f28caf10ec3724900cfc596d4849699ce0f34abd4ab0b89a7f","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-02T00:57:38Z","title_canon_sha256":"367c50240177c9dd7e53401729549d120bc51f3c41593e8b468f4c0463457ec0"},"schema_version":"1.0","source":{"id":"2303.00883","kind":"arxiv","version":2}},"canonical_sha256":"53dc5c8d3c720f654e14a6b178a92f05472734c6d1ec27f278f29fc3c24e17a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53dc5c8d3c720f654e14a6b178a92f05472734c6d1ec27f278f29fc3c24e17a6","first_computed_at":"2026-07-05T06:17:05.206071Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:05.206071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JUKdkspjUyGtX6KmQToTtSJ2CPr5TRTKPcs+mp7LkIa97/oraJ0w1aheRts5xfKmZr8UPtQpGHyAlZal5xP5Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:05.206493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.00883","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fc120a75758e549b5a73db15bd5db72bed7b98aa032ec405ceab53555125ca6","sha256:30d999aded90bcb5b9eba83656735e1b943989b7342b2de06a238cbdada79a33"],"state_sha256":"c3c8a2b9137cf8ebf02ce7e94b0c2f346e4bca5fb1f50fb6404d61487f9bed29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PNHGh+BkpdK0CooSQ+XXl78aayi+rEmfTfjD+AoxLDDT7TjWdGTqLKsxy2ognMmflQWBEqxWliaAd1opK2DNBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T03:06:26.448206Z","bundle_sha256":"7f3c919ba6674d3963eaabc7f54f4eaa2b101a23142b9f75fc4fec417e161a9b"}}