{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VS5G63E6YPD6Y5VSKRL7JYQQWM","short_pith_number":"pith:VS5G63E6","canonical_record":{"source":{"id":"2210.03069","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-06T17:22:40Z","cross_cats_sorted":[],"title_canon_sha256":"6110fac1c6f6219c730034868f20abc6b838a4caf7fed83f80e42890ef70811a","abstract_canon_sha256":"7f08070fc03fd565b24e2649d2d19c51d340de6765f5ea72f0c929deb1334580"},"schema_version":"1.0"},"canonical_sha256":"acba6f6c9ec3c7ec76b25457f4e210b336bea48d45b3c99f8e9593a586eb7d75","source":{"kind":"arxiv","id":"2210.03069","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03069","created_at":"2026-07-05T06:28:14Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03069v4","created_at":"2026-07-05T06:28:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03069","created_at":"2026-07-05T06:28:14Z"},{"alias_kind":"pith_short_12","alias_value":"VS5G63E6YPD6","created_at":"2026-07-05T06:28:14Z"},{"alias_kind":"pith_short_16","alias_value":"VS5G63E6YPD6Y5VS","created_at":"2026-07-05T06:28:14Z"},{"alias_kind":"pith_short_8","alias_value":"VS5G63E6","created_at":"2026-07-05T06:28:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VS5G63E6YPD6Y5VSKRL7JYQQWM","target":"record","payload":{"canonical_record":{"source":{"id":"2210.03069","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-06T17:22:40Z","cross_cats_sorted":[],"title_canon_sha256":"6110fac1c6f6219c730034868f20abc6b838a4caf7fed83f80e42890ef70811a","abstract_canon_sha256":"7f08070fc03fd565b24e2649d2d19c51d340de6765f5ea72f0c929deb1334580"},"schema_version":"1.0"},"canonical_sha256":"acba6f6c9ec3c7ec76b25457f4e210b336bea48d45b3c99f8e9593a586eb7d75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:14.342335Z","signature_b64":"dwH+5ygP1MRAVW4UFPgEhfuvQaFxAeMd4VFtxJGCx8hT2QkR4bualD4gP+M4ZawTfugL5Y9RUW/o4olUv4CgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acba6f6c9ec3c7ec76b25457f4e210b336bea48d45b3c99f8e9593a586eb7d75","last_reissued_at":"2026-07-05T06:28:14.341692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:14.341692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.03069","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:28:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r3wQvGa6bwd7fzQXQhVkp8NvcAgo71oYpmv5d3kXBVEuWo8kYFXndiE88gMUfmotPQ5XC8zmWhPvvz1gRiicAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:25:12.629359Z"},"content_sha256":"75711a41fc6e5b83c2959d8e7d380c91b47fe904208df7cf693325e2918b17fd","schema_version":"1.0","event_id":"sha256:75711a41fc6e5b83c2959d8e7d380c91b47fe904208df7cf693325e2918b17fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VS5G63E6YPD6Y5VSKRL7JYQQWM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PathProx: A Proximal Gradient Algorithm for Weight Decay Regularized Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dimitris Papailiopoulos, Jifan Zhang, Joseph Shenouda, Kangwook Lee, Liu Yang, Robert D. Nowak","submitted_at":"2022-10-06T17:22:40Z","abstract_excerpt":"Weight decay is one of the most widely used forms of regularization in deep learning, and has been shown to improve generalization and robustness. The optimization objective driving weight decay is a sum of losses plus a term proportional to the sum of squared weights. This paper argues that stochastic gradient descent (SGD) may be an inefficient algorithm for this objective. For neural networks with ReLU activations, solutions to the weight decay objective are equivalent to those of a different objective in which the regularization term is instead a sum of products of $\\ell_2$ (not squared) n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03069","kind":"arxiv","version":4},"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/2210.03069/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":"2026-07-05T06:28:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RCVAQkNIzbm/N0UssRzBWAqbKLBiSmIgGSnvCtSfzqn/H/LwuXg0pkEWDSwP1HDTbS6xG4TUNXfJg4/M9pUkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:25:12.629906Z"},"content_sha256":"43edb8e91162a661fb9c4062935bc2930bb96851cb05f76e8950979cad68738b","schema_version":"1.0","event_id":"sha256:43edb8e91162a661fb9c4062935bc2930bb96851cb05f76e8950979cad68738b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VS5G63E6YPD6Y5VSKRL7JYQQWM/bundle.json","state_url":"https://pith.science/pith/VS5G63E6YPD6Y5VSKRL7JYQQWM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VS5G63E6YPD6Y5VSKRL7JYQQWM/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":"2026-08-05T17:25:12Z","links":{"resolver":"https://pith.science/pith/VS5G63E6YPD6Y5VSKRL7JYQQWM","bundle":"https://pith.science/pith/VS5G63E6YPD6Y5VSKRL7JYQQWM/bundle.json","state":"https://pith.science/pith/VS5G63E6YPD6Y5VSKRL7JYQQWM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VS5G63E6YPD6Y5VSKRL7JYQQWM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VS5G63E6YPD6Y5VSKRL7JYQQWM","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":"7f08070fc03fd565b24e2649d2d19c51d340de6765f5ea72f0c929deb1334580","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-06T17:22:40Z","title_canon_sha256":"6110fac1c6f6219c730034868f20abc6b838a4caf7fed83f80e42890ef70811a"},"schema_version":"1.0","source":{"id":"2210.03069","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03069","created_at":"2026-07-05T06:28:14Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03069v4","created_at":"2026-07-05T06:28:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03069","created_at":"2026-07-05T06:28:14Z"},{"alias_kind":"pith_short_12","alias_value":"VS5G63E6YPD6","created_at":"2026-07-05T06:28:14Z"},{"alias_kind":"pith_short_16","alias_value":"VS5G63E6YPD6Y5VS","created_at":"2026-07-05T06:28:14Z"},{"alias_kind":"pith_short_8","alias_value":"VS5G63E6","created_at":"2026-07-05T06:28:14Z"}],"graph_snapshots":[{"event_id":"sha256:43edb8e91162a661fb9c4062935bc2930bb96851cb05f76e8950979cad68738b","target":"graph","created_at":"2026-07-05T06:28:14Z","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/2210.03069/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Weight decay is one of the most widely used forms of regularization in deep learning, and has been shown to improve generalization and robustness. The optimization objective driving weight decay is a sum of losses plus a term proportional to the sum of squared weights. This paper argues that stochastic gradient descent (SGD) may be an inefficient algorithm for this objective. For neural networks with ReLU activations, solutions to the weight decay objective are equivalent to those of a different objective in which the regularization term is instead a sum of products of $\\ell_2$ (not squared) n","authors_text":"Dimitris Papailiopoulos, Jifan Zhang, Joseph Shenouda, Kangwook Lee, Liu Yang, Robert D. Nowak","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-06T17:22:40Z","title":"PathProx: A Proximal Gradient Algorithm for Weight Decay Regularized Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03069","kind":"arxiv","version":4},"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":"sha256:75711a41fc6e5b83c2959d8e7d380c91b47fe904208df7cf693325e2918b17fd","target":"record","created_at":"2026-07-05T06:28:14Z","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":"7f08070fc03fd565b24e2649d2d19c51d340de6765f5ea72f0c929deb1334580","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-06T17:22:40Z","title_canon_sha256":"6110fac1c6f6219c730034868f20abc6b838a4caf7fed83f80e42890ef70811a"},"schema_version":"1.0","source":{"id":"2210.03069","kind":"arxiv","version":4}},"canonical_sha256":"acba6f6c9ec3c7ec76b25457f4e210b336bea48d45b3c99f8e9593a586eb7d75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acba6f6c9ec3c7ec76b25457f4e210b336bea48d45b3c99f8e9593a586eb7d75","first_computed_at":"2026-07-05T06:28:14.341692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:28:14.341692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dwH+5ygP1MRAVW4UFPgEhfuvQaFxAeMd4VFtxJGCx8hT2QkR4bualD4gP+M4ZawTfugL5Y9RUW/o4olUv4CgBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:28:14.342335Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.03069","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75711a41fc6e5b83c2959d8e7d380c91b47fe904208df7cf693325e2918b17fd","sha256:43edb8e91162a661fb9c4062935bc2930bb96851cb05f76e8950979cad68738b"],"state_sha256":"1f469bb41820e0a505028c165e4c67ac4359b07285419c19562dd5b2c23f4087"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rQlVIu+WzhFdsHHiVcLg2SlrTQ86I45kso5hRtUBRFXy9Di/zjVp20+xfxyuIqoynwMtbMOZGE2w3z3CWfF4Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:25:12.633293Z","bundle_sha256":"b4d48f62316f6e94fcda19b7b2aa982860ffbc123eeb9499d558a396808365c5"}}