{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4TN3LGYDBSIKGR3HAPSRXUORYE","short_pith_number":"pith:4TN3LGYD","canonical_record":{"source":{"id":"2303.15725","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-28T04:26:51Z","cross_cats_sorted":[],"title_canon_sha256":"15c62f4b68f295ac07cba3b2e3a4837b702f21a0dc37da3c0717a87c912d2a8f","abstract_canon_sha256":"ccbe02e3ac560d512841bc5b1f8814c7a4cffb664e2c61399bbee3598a3de831"},"schema_version":"1.0"},"canonical_sha256":"e4dbb59b030c90a3476703e51bd1d1c116524ebdd154479f31ab1c90fe829049","source":{"kind":"arxiv","id":"2303.15725","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.15725","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"arxiv_version","alias_value":"2303.15725v2","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.15725","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"pith_short_12","alias_value":"4TN3LGYDBSIK","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"pith_short_16","alias_value":"4TN3LGYDBSIKGR3H","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"pith_short_8","alias_value":"4TN3LGYD","created_at":"2026-07-05T06:09:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4TN3LGYDBSIKGR3HAPSRXUORYE","target":"record","payload":{"canonical_record":{"source":{"id":"2303.15725","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-28T04:26:51Z","cross_cats_sorted":[],"title_canon_sha256":"15c62f4b68f295ac07cba3b2e3a4837b702f21a0dc37da3c0717a87c912d2a8f","abstract_canon_sha256":"ccbe02e3ac560d512841bc5b1f8814c7a4cffb664e2c61399bbee3598a3de831"},"schema_version":"1.0"},"canonical_sha256":"e4dbb59b030c90a3476703e51bd1d1c116524ebdd154479f31ab1c90fe829049","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:09.317045Z","signature_b64":"HtBSl6vuZNSyaVD6yX3i/BPv4mVz7jXn4rkPteM7Yg4G0tmDMmhM4wRn6A4wil1vrHuN0CZgw/86psLz/4YQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4dbb59b030c90a3476703e51bd1d1c116524ebdd154479f31ab1c90fe829049","last_reissued_at":"2026-07-05T06:09:09.316515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:09.316515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.15725","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":"2026-07-05T06:09:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2edLfyDB0/F9f2ABf9++gtXK4PGVCuEQRisDsY5/BjqpGo9D7/o3pIsRrNqUObk+v8TOOLzIukMooKh2e5h/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:01:54.257559Z"},"content_sha256":"a0662cf710bec623d2f88cc2d34894360acd6234776d1a31345f744d7084aac2","schema_version":"1.0","event_id":"sha256:a0662cf710bec623d2f88cc2d34894360acd6234776d1a31345f744d7084aac2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4TN3LGYDBSIKGR3HAPSRXUORYE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Solving Regularized Exp, Cosh and Sinh Regression Problems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Tianyi Zhou, Zhao Song, Zhihang Li","submitted_at":"2023-03-28T04:26:51Z","abstract_excerpt":"In modern machine learning, attention computation is a fundamental task for training large language models such as Transformer, GPT-4 and ChatGPT. In this work, we study exponential regression problem which is inspired by the softmax/exp unit in the attention mechanism in large language models. The standard exponential regression is non-convex. We study the regularization version of exponential regression problem which is a convex problem. We use approximate newton method to solve in input sparsity time.\n  Formally, in this problem, one is given matrix $A \\in \\mathbb{R}^{n \\times d}$, $b \\in \\"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.15725","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/2303.15725/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":"2026-07-05T06:09:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UR6IPuIjlZW5Gybd8E442J4uyPt1LMBoybEAZKG5JK6H+kH6YbpTKmCqWduTrRleM8F+DVlAKX1OiBoLKtoPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:01:54.258441Z"},"content_sha256":"7b12f403ba889ba6f762c4560908ab14cdf73f7a2c53d1ba5fbab37bc9080571","schema_version":"1.0","event_id":"sha256:7b12f403ba889ba6f762c4560908ab14cdf73f7a2c53d1ba5fbab37bc9080571"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4TN3LGYDBSIKGR3HAPSRXUORYE/bundle.json","state_url":"https://pith.science/pith/4TN3LGYDBSIKGR3HAPSRXUORYE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4TN3LGYDBSIKGR3HAPSRXUORYE/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":"2026-08-10T08:01:54Z","links":{"resolver":"https://pith.science/pith/4TN3LGYDBSIKGR3HAPSRXUORYE","bundle":"https://pith.science/pith/4TN3LGYDBSIKGR3HAPSRXUORYE/bundle.json","state":"https://pith.science/pith/4TN3LGYDBSIKGR3HAPSRXUORYE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4TN3LGYDBSIKGR3HAPSRXUORYE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4TN3LGYDBSIKGR3HAPSRXUORYE","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":"ccbe02e3ac560d512841bc5b1f8814c7a4cffb664e2c61399bbee3598a3de831","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-28T04:26:51Z","title_canon_sha256":"15c62f4b68f295ac07cba3b2e3a4837b702f21a0dc37da3c0717a87c912d2a8f"},"schema_version":"1.0","source":{"id":"2303.15725","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.15725","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"arxiv_version","alias_value":"2303.15725v2","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.15725","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"pith_short_12","alias_value":"4TN3LGYDBSIK","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"pith_short_16","alias_value":"4TN3LGYDBSIKGR3H","created_at":"2026-07-05T06:09:09Z"},{"alias_kind":"pith_short_8","alias_value":"4TN3LGYD","created_at":"2026-07-05T06:09:09Z"}],"graph_snapshots":[{"event_id":"sha256:7b12f403ba889ba6f762c4560908ab14cdf73f7a2c53d1ba5fbab37bc9080571","target":"graph","created_at":"2026-07-05T06:09:09Z","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/2303.15725/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In modern machine learning, attention computation is a fundamental task for training large language models such as Transformer, GPT-4 and ChatGPT. In this work, we study exponential regression problem which is inspired by the softmax/exp unit in the attention mechanism in large language models. The standard exponential regression is non-convex. We study the regularization version of exponential regression problem which is a convex problem. We use approximate newton method to solve in input sparsity time.\n  Formally, in this problem, one is given matrix $A \\in \\mathbb{R}^{n \\times d}$, $b \\in \\","authors_text":"Tianyi Zhou, Zhao Song, Zhihang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-28T04:26:51Z","title":"Solving Regularized Exp, Cosh and Sinh Regression Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.15725","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:a0662cf710bec623d2f88cc2d34894360acd6234776d1a31345f744d7084aac2","target":"record","created_at":"2026-07-05T06:09:09Z","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":"ccbe02e3ac560d512841bc5b1f8814c7a4cffb664e2c61399bbee3598a3de831","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-28T04:26:51Z","title_canon_sha256":"15c62f4b68f295ac07cba3b2e3a4837b702f21a0dc37da3c0717a87c912d2a8f"},"schema_version":"1.0","source":{"id":"2303.15725","kind":"arxiv","version":2}},"canonical_sha256":"e4dbb59b030c90a3476703e51bd1d1c116524ebdd154479f31ab1c90fe829049","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4dbb59b030c90a3476703e51bd1d1c116524ebdd154479f31ab1c90fe829049","first_computed_at":"2026-07-05T06:09:09.316515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:09.316515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HtBSl6vuZNSyaVD6yX3i/BPv4mVz7jXn4rkPteM7Yg4G0tmDMmhM4wRn6A4wil1vrHuN0CZgw/86psLz/4YQCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:09.317045Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.15725","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0662cf710bec623d2f88cc2d34894360acd6234776d1a31345f744d7084aac2","sha256:7b12f403ba889ba6f762c4560908ab14cdf73f7a2c53d1ba5fbab37bc9080571"],"state_sha256":"70eb0f47b6f099a0961447b7cd7b92c6b9cc171758b721eb2fd6b0544f9b0f4b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nAIsqXOjbrmin1jAXvudIbjktzk5qgZL6blAwl7UsqndKcCn+dEajZ5NHypdhlvklWNYOP25/zqhuPxLApDKAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:01:54.263339Z","bundle_sha256":"bfd66c8a3373c1cfd447ffbabd617cddfad4dda520b138621943ce56c58edcca"}}