{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:K3HGYBEOZNQIIWKPVX3RXDLP72","short_pith_number":"pith:K3HGYBEO","canonical_record":{"source":{"id":"2607.23777","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T17:55:40Z","cross_cats_sorted":["cond-mat.dis-nn","cs.AI","math.OC"],"title_canon_sha256":"d21155f6af7731aa46ea4e727795cdf47edad4bf43126393e601240e8b43ee5d","abstract_canon_sha256":"43b5e63d7bbe29f92d67b69fdc3649e72cd0e8a56f2df50a772811d44a6bae53"},"schema_version":"1.0"},"canonical_sha256":"56ce6c048ecb6084594fadf71b8d6ffe92304ad8b0738ed7b8e9adbb308b4df0","source":{"kind":"arxiv","id":"2607.23777","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23777","created_at":"2026-07-28T01:23:10Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23777v1","created_at":"2026-07-28T01:23:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23777","created_at":"2026-07-28T01:23:10Z"},{"alias_kind":"pith_short_12","alias_value":"K3HGYBEOZNQI","created_at":"2026-07-28T01:23:10Z"},{"alias_kind":"pith_short_16","alias_value":"K3HGYBEOZNQIIWKP","created_at":"2026-07-28T01:23:10Z"},{"alias_kind":"pith_short_8","alias_value":"K3HGYBEO","created_at":"2026-07-28T01:23:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:K3HGYBEOZNQIIWKPVX3RXDLP72","target":"record","payload":{"canonical_record":{"source":{"id":"2607.23777","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T17:55:40Z","cross_cats_sorted":["cond-mat.dis-nn","cs.AI","math.OC"],"title_canon_sha256":"d21155f6af7731aa46ea4e727795cdf47edad4bf43126393e601240e8b43ee5d","abstract_canon_sha256":"43b5e63d7bbe29f92d67b69fdc3649e72cd0e8a56f2df50a772811d44a6bae53"},"schema_version":"1.0"},"canonical_sha256":"56ce6c048ecb6084594fadf71b8d6ffe92304ad8b0738ed7b8e9adbb308b4df0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:10.629765Z","signature_b64":"72Lhe8KLqm9ZyBNrKBxByChZ3JLfkdMPJQ7tilgm5E9aAmr+uUtNcHavPD4cfLtzBP3Ys2b1hKOnQ7vVAh5XBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56ce6c048ecb6084594fadf71b8d6ffe92304ad8b0738ed7b8e9adbb308b4df0","last_reissued_at":"2026-07-28T01:23:10.628912Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:10.628912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.23777","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-28T01:23:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4EFbuHygqjQZROtqzE/Eo6R4feUnXXiKVcbKkadwYrEkc1zILoqOB/o4YZijtkbDFq7ULY78d08JG94E8MioBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T11:29:38.103105Z"},"content_sha256":"0a223cf9d8a917fc8c75ffc8545fd19f6b2e5077e219d0e869de1cc188891ab2","schema_version":"1.0","event_id":"sha256:0a223cf9d8a917fc8c75ffc8545fd19f6b2e5077e219d0e869de1cc188891ab2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:K3HGYBEOZNQIIWKPVX3RXDLP72","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scale Weight Decay and Train Better","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Anuj Apte","submitted_at":"2026-07-26T17:55:40Z","abstract_excerpt":"The discovery of scaling laws has motivated training neural networks on ever increasing quantities of data. This is typically done with a constant decoupled weight decay which causes the network weights to shrink steadily over the course of training. Taking inspiration from the Robbins--Monro conditions, we propose to scale weight decay by the fraction of the peak learning rate $\\eta/\\eta_{\\max}$. We prove that this scaled weight decay preserves the asymptotic stationarity guarantees of the corresponding unregularized methods for both stochastic gradient descent and the non-Euclidean spectral "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23777","kind":"arxiv","version":1},"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/2607.23777/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":"2026-07-28T01:23:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hi4idnWGkFq5g0UwEZC5rZ741q4dqC1fuLadqcE83MIHHeKesFX8kAbAbRVAJW3BnlRG7D9dyjgt10tFVnk1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T11:29:38.103658Z"},"content_sha256":"85bb9f4e95fe30e9220fb9327cff0e3e4fdc571936b8dc4ae65768016ce85f6e","schema_version":"1.0","event_id":"sha256:85bb9f4e95fe30e9220fb9327cff0e3e4fdc571936b8dc4ae65768016ce85f6e"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:K3HGYBEOZNQIIWKPVX3RXDLP72","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1038/s41586-025-09422-z) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Daya Guo et al. “DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning”. In: Nature645.8081 (2025), pp. 633–638.issn: 1476-4687.doi:10.1038/s41586- 025- 09422- z.url: http://dx.doi.org/10.1038/s41586-025-09422-z","arxiv_id":"2607.23777","detector":"doi_compliance","evidence":{"ref_index":60,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1038/s41586-","reconstructed_doi":"10.1038/s41586-025-09422-z"},"severity":"advisory","ref_index":60,"audited_at":"2026-07-30T13:01:44.554738Z","event_type":"pith.integrity.v1","detected_doi":"10.1038/s41586-025-09422-z","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"51c0e192252b8820e2230e158cbce06cd1662079513cf328433ac10df6c5cede","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":13913,"payload_sha256":"b7f6a392b51637a7ec91276f301f6980b7f9d6327b9263262fd94a712232b01e","signature_b64":null,"signing_key_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T13:06:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zz2OgtZJRZcUXzz1tvBAlrxCGoC1VxkwFdPJZf3v6+S+lX4RGsRpaM7zGrAxgnGe2bFxTOwt9tJ5EXTyP6z4BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T11:29:38.105875Z"},"content_sha256":"2716b578aa37db3374b203de2ce026ecadfbc7887b6a35c4d0312f7ade57912e","schema_version":"1.0","event_id":"sha256:2716b578aa37db3374b203de2ce026ecadfbc7887b6a35c4d0312f7ade57912e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K3HGYBEOZNQIIWKPVX3RXDLP72/bundle.json","state_url":"https://pith.science/pith/K3HGYBEOZNQIIWKPVX3RXDLP72/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K3HGYBEOZNQIIWKPVX3RXDLP72/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":"2026-08-03T11:29:38Z","links":{"resolver":"https://pith.science/pith/K3HGYBEOZNQIIWKPVX3RXDLP72","bundle":"https://pith.science/pith/K3HGYBEOZNQIIWKPVX3RXDLP72/bundle.json","state":"https://pith.science/pith/K3HGYBEOZNQIIWKPVX3RXDLP72/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K3HGYBEOZNQIIWKPVX3RXDLP72/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:K3HGYBEOZNQIIWKPVX3RXDLP72","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"43b5e63d7bbe29f92d67b69fdc3649e72cd0e8a56f2df50a772811d44a6bae53","cross_cats_sorted":["cond-mat.dis-nn","cs.AI","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T17:55:40Z","title_canon_sha256":"d21155f6af7731aa46ea4e727795cdf47edad4bf43126393e601240e8b43ee5d"},"schema_version":"1.0","source":{"id":"2607.23777","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23777","created_at":"2026-07-28T01:23:10Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23777v1","created_at":"2026-07-28T01:23:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23777","created_at":"2026-07-28T01:23:10Z"},{"alias_kind":"pith_short_12","alias_value":"K3HGYBEOZNQI","created_at":"2026-07-28T01:23:10Z"},{"alias_kind":"pith_short_16","alias_value":"K3HGYBEOZNQIIWKP","created_at":"2026-07-28T01:23:10Z"},{"alias_kind":"pith_short_8","alias_value":"K3HGYBEO","created_at":"2026-07-28T01:23:10Z"}],"graph_snapshots":[{"event_id":"sha256:85bb9f4e95fe30e9220fb9327cff0e3e4fdc571936b8dc4ae65768016ce85f6e","target":"graph","created_at":"2026-07-28T01:23:10Z","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/2607.23777/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The discovery of scaling laws has motivated training neural networks on ever increasing quantities of data. This is typically done with a constant decoupled weight decay which causes the network weights to shrink steadily over the course of training. Taking inspiration from the Robbins--Monro conditions, we propose to scale weight decay by the fraction of the peak learning rate $\\eta/\\eta_{\\max}$. We prove that this scaled weight decay preserves the asymptotic stationarity guarantees of the corresponding unregularized methods for both stochastic gradient descent and the non-Euclidean spectral ","authors_text":"Anuj Apte","cross_cats":["cond-mat.dis-nn","cs.AI","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T17:55:40Z","title":"Scale Weight Decay and Train Better"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23777","kind":"arxiv","version":1},"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":"sha256:0a223cf9d8a917fc8c75ffc8545fd19f6b2e5077e219d0e869de1cc188891ab2","target":"record","created_at":"2026-07-28T01:23:10Z","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":"43b5e63d7bbe29f92d67b69fdc3649e72cd0e8a56f2df50a772811d44a6bae53","cross_cats_sorted":["cond-mat.dis-nn","cs.AI","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T17:55:40Z","title_canon_sha256":"d21155f6af7731aa46ea4e727795cdf47edad4bf43126393e601240e8b43ee5d"},"schema_version":"1.0","source":{"id":"2607.23777","kind":"arxiv","version":1}},"canonical_sha256":"56ce6c048ecb6084594fadf71b8d6ffe92304ad8b0738ed7b8e9adbb308b4df0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56ce6c048ecb6084594fadf71b8d6ffe92304ad8b0738ed7b8e9adbb308b4df0","first_computed_at":"2026-07-28T01:23:10.628912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:10.628912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"72Lhe8KLqm9ZyBNrKBxByChZ3JLfkdMPJQ7tilgm5E9aAmr+uUtNcHavPD4cfLtzBP3Ys2b1hKOnQ7vVAh5XBw==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:10.629765Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23777","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a223cf9d8a917fc8c75ffc8545fd19f6b2e5077e219d0e869de1cc188891ab2","sha256:85bb9f4e95fe30e9220fb9327cff0e3e4fdc571936b8dc4ae65768016ce85f6e","sha256:2716b578aa37db3374b203de2ce026ecadfbc7887b6a35c4d0312f7ade57912e"],"state_sha256":"0b96642ba90fa0422e594cbc3e2c7a473db424ee42612a58840788bab268aa5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dL0C7oowdu9paxjpX6lvW5uG5N4gi81Awq4ACO4n9/ZK5Kall5NZbtfUwGGw48ZznBUcP+CHhQyj77lt/b9nDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T11:29:38.108012Z","bundle_sha256":"c3d96cc80f06aa336ec0d9c14d60f4fd76a4c12fbfe8c67afbaf85e3975ae491"}}