{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:QZDKAHQJ2NUZWYP6BXLK4WYUJV","short_pith_number":"pith:QZDKAHQJ","canonical_record":{"source":{"id":"2212.09921","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-20T00:08:37Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"c224a96847366a2d248924917bb3f259face78ad6a05f718ec8790cc8e1d1890","abstract_canon_sha256":"d43011e0536c8e582d8d151feb8bad630618f2d32d7d3308948cdc7148f9dc6e"},"schema_version":"1.0"},"canonical_sha256":"8646a01e09d3699b61fe0dd6ae5b144d6656610ef3e6bcdba8f6e61872863c15","source":{"kind":"arxiv","id":"2212.09921","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09921","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09921v2","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09921","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"pith_short_12","alias_value":"QZDKAHQJ2NUZ","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"pith_short_16","alias_value":"QZDKAHQJ2NUZWYP6","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"pith_short_8","alias_value":"QZDKAHQJ","created_at":"2026-07-05T06:24:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:QZDKAHQJ2NUZWYP6BXLK4WYUJV","target":"record","payload":{"canonical_record":{"source":{"id":"2212.09921","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-20T00:08:37Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"c224a96847366a2d248924917bb3f259face78ad6a05f718ec8790cc8e1d1890","abstract_canon_sha256":"d43011e0536c8e582d8d151feb8bad630618f2d32d7d3308948cdc7148f9dc6e"},"schema_version":"1.0"},"canonical_sha256":"8646a01e09d3699b61fe0dd6ae5b144d6656610ef3e6bcdba8f6e61872863c15","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:47.737643Z","signature_b64":"dUV0Ou0eno9rpWJTT3Yn5DSQnXFnGFGy3hKX8s/iX1HCck9spVhftsWPwwFN+uerWK/og9HIHacU7zTMpoHVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8646a01e09d3699b61fe0dd6ae5b144d6656610ef3e6bcdba8f6e61872863c15","last_reissued_at":"2026-07-05T06:24:47.737171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:47.737171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.09921","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":"2026-07-05T06:24:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Td4StR2tx4s5bmojQweMFU9T8g31zk5Rt4UzY+5zjBB7cfVNWrQyORxAgjEAp3pDjfzgvXHbUBYXIksnmfG4Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T05:02:21.107231Z"},"content_sha256":"d3a60ab409b247db4bfa52a5c06bb2235b9e43a1aaffc2c727d8339d3c1da177","schema_version":"1.0","event_id":"sha256:d3a60ab409b247db4bfa52a5c06bb2235b9e43a1aaffc2c727d8339d3c1da177"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:QZDKAHQJ2NUZWYP6BXLK4WYUJV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Input Normalized Stochastic Gradient Descent Training of Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Ahmet Enis Cetin, Hongyi Pan, Salih Atici","submitted_at":"2022-12-20T00:08:37Z","abstract_excerpt":"In this paper, we propose a novel optimization algorithm for training machine learning models called Input Normalized Stochastic Gradient Descent (INSGD), inspired by the Normalized Least Mean Squares (NLMS) algorithm used in adaptive filtering. When training complex models on large datasets, the choice of optimizer parameters, particularly the learning rate, is crucial to avoid divergence. Our algorithm updates the network weights using stochastic gradient descent with $\\ell_1$ and $\\ell_2$-based normalizations applied to the learning rate, similar to NLMS. However, unlike existing normalizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09921","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/2212.09921/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":"2026-07-05T06:24:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2DfWNQqrnFxL2ed+d/iDLdrgqo2XOARhbiTJwur7nuiIIBpyF6LiL7j3DOWK6mUiPNF6e6z1c9zFOG35HBroBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T05:02:21.108227Z"},"content_sha256":"905c7b576d451fc784a9bae28edaca7c9c4d0ca7a1c6d295235c06344d3b4451","schema_version":"1.0","event_id":"sha256:905c7b576d451fc784a9bae28edaca7c9c4d0ca7a1c6d295235c06344d3b4451"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QZDKAHQJ2NUZWYP6BXLK4WYUJV/bundle.json","state_url":"https://pith.science/pith/QZDKAHQJ2NUZWYP6BXLK4WYUJV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QZDKAHQJ2NUZWYP6BXLK4WYUJV/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":"2026-08-18T05:02:21Z","links":{"resolver":"https://pith.science/pith/QZDKAHQJ2NUZWYP6BXLK4WYUJV","bundle":"https://pith.science/pith/QZDKAHQJ2NUZWYP6BXLK4WYUJV/bundle.json","state":"https://pith.science/pith/QZDKAHQJ2NUZWYP6BXLK4WYUJV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QZDKAHQJ2NUZWYP6BXLK4WYUJV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QZDKAHQJ2NUZWYP6BXLK4WYUJV","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":"d43011e0536c8e582d8d151feb8bad630618f2d32d7d3308948cdc7148f9dc6e","cross_cats_sorted":["eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-20T00:08:37Z","title_canon_sha256":"c224a96847366a2d248924917bb3f259face78ad6a05f718ec8790cc8e1d1890"},"schema_version":"1.0","source":{"id":"2212.09921","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09921","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09921v2","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09921","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"pith_short_12","alias_value":"QZDKAHQJ2NUZ","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"pith_short_16","alias_value":"QZDKAHQJ2NUZWYP6","created_at":"2026-07-05T06:24:47Z"},{"alias_kind":"pith_short_8","alias_value":"QZDKAHQJ","created_at":"2026-07-05T06:24:47Z"}],"graph_snapshots":[{"event_id":"sha256:905c7b576d451fc784a9bae28edaca7c9c4d0ca7a1c6d295235c06344d3b4451","target":"graph","created_at":"2026-07-05T06:24:47Z","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/2212.09921/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a novel optimization algorithm for training machine learning models called Input Normalized Stochastic Gradient Descent (INSGD), inspired by the Normalized Least Mean Squares (NLMS) algorithm used in adaptive filtering. When training complex models on large datasets, the choice of optimizer parameters, particularly the learning rate, is crucial to avoid divergence. Our algorithm updates the network weights using stochastic gradient descent with $\\ell_1$ and $\\ell_2$-based normalizations applied to the learning rate, similar to NLMS. However, unlike existing normalizat","authors_text":"Ahmet Enis Cetin, Hongyi Pan, Salih Atici","cross_cats":["eess.SP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-20T00:08:37Z","title":"Input Normalized Stochastic Gradient Descent Training of Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09921","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:d3a60ab409b247db4bfa52a5c06bb2235b9e43a1aaffc2c727d8339d3c1da177","target":"record","created_at":"2026-07-05T06:24:47Z","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":"d43011e0536c8e582d8d151feb8bad630618f2d32d7d3308948cdc7148f9dc6e","cross_cats_sorted":["eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-20T00:08:37Z","title_canon_sha256":"c224a96847366a2d248924917bb3f259face78ad6a05f718ec8790cc8e1d1890"},"schema_version":"1.0","source":{"id":"2212.09921","kind":"arxiv","version":2}},"canonical_sha256":"8646a01e09d3699b61fe0dd6ae5b144d6656610ef3e6bcdba8f6e61872863c15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8646a01e09d3699b61fe0dd6ae5b144d6656610ef3e6bcdba8f6e61872863c15","first_computed_at":"2026-07-05T06:24:47.737171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:47.737171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dUV0Ou0eno9rpWJTT3Yn5DSQnXFnGFGy3hKX8s/iX1HCck9spVhftsWPwwFN+uerWK/og9HIHacU7zTMpoHVDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:47.737643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.09921","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3a60ab409b247db4bfa52a5c06bb2235b9e43a1aaffc2c727d8339d3c1da177","sha256:905c7b576d451fc784a9bae28edaca7c9c4d0ca7a1c6d295235c06344d3b4451"],"state_sha256":"0cae27276418767398dabc9964b84e93d2aee7db2fefc491ede1f590f9acc434"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CdXR14U5/zM8zJLW0R6et/ivtDmVixpLfaB5RCwCnc4e4lR/KkgbDisQqepZpug9MDfVU4hOLHl/pwkahsahAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T05:02:21.115638Z","bundle_sha256":"3995675bf95f99f19f543bd22c6309eb17177c43faa109de1e01fae65b5fc8bd"}}