{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FIIRWZ7EWWL7SRPNTY47XVFBFX","short_pith_number":"pith:FIIRWZ7E","canonical_record":{"source":{"id":"2506.02285","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T21:51:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"44be545d3448b67b0ada1d4e688223b7525f3da4d331bde4f6dbfa23a1e1008c","abstract_canon_sha256":"5cf9588528c7dbb96a6ce86851215039ae5eeb461456adad71c63e57936e042d"},"schema_version":"1.0"},"canonical_sha256":"2a111b67e4b597f945ed9e39fbd4a12df5c3b828c153bf02cc75a110080e1516","source":{"kind":"arxiv","id":"2506.02285","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02285","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02285v2","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02285","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_12","alias_value":"FIIRWZ7EWWL7","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_16","alias_value":"FIIRWZ7EWWL7SRPN","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_8","alias_value":"FIIRWZ7E","created_at":"2026-07-05T11:18:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FIIRWZ7EWWL7SRPNTY47XVFBFX","target":"record","payload":{"canonical_record":{"source":{"id":"2506.02285","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T21:51:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"44be545d3448b67b0ada1d4e688223b7525f3da4d331bde4f6dbfa23a1e1008c","abstract_canon_sha256":"5cf9588528c7dbb96a6ce86851215039ae5eeb461456adad71c63e57936e042d"},"schema_version":"1.0"},"canonical_sha256":"2a111b67e4b597f945ed9e39fbd4a12df5c3b828c153bf02cc75a110080e1516","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:43.416001Z","signature_b64":"FRnOmccteZeFg2zZbobA6Du4HTM7Hp3jpBz7WbF8Yl6WSvBHcF4yWxHSmiI8HcZXITV3GxX9l8qXDu6sHgpwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a111b67e4b597f945ed9e39fbd4a12df5c3b828c153bf02cc75a110080e1516","last_reissued_at":"2026-07-05T11:18:43.415559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:43.415559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.02285","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":"2026-07-05T11:18:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kQmaQOAt8CIKojUoteAlCs5YqSOZvAVVj8TJs9lYyN1c7OAV76D1q4FZlitZtceRn4AVj3rsBGFdUu3s/R9KAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:38:50.161694Z"},"content_sha256":"ab822c4c26bad9bfc754d20d277fcf1b5e1d744a09bc537cfa12541079689afd","schema_version":"1.0","event_id":"sha256:ab822c4c26bad9bfc754d20d277fcf1b5e1d744a09bc537cfa12541079689afd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FIIRWZ7EWWL7SRPNTY47XVFBFX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why Gradients Rapidly Increase Near the End of Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aaron Defazio","submitted_at":"2025-06-02T21:51:04Z","abstract_excerpt":"During long-duration Large Language Model (LLM) training runs the gradient norm increases rapidly near the end of training. In this short note, we show that this increase is due to an unintended interaction between weight decay, normalization layers, and the learning rate schedule. We propose a simple correction that fixes this behavior while also resulting in lower loss values throughout training."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02285","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/2506.02285/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":"2026-07-05T11:18:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z7PyQNhTd61hjMuQrG4QLfCGOUWL6fJZk9s916kbRFfK7mimqnlPvAg15H59wLH8fQzPPCuAJe3Fm9LpbSVCDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:38:50.162594Z"},"content_sha256":"4f4eaebe145b0f996e5320394dba355286f2a6bc60767d7c912668189205ef08","schema_version":"1.0","event_id":"sha256:4f4eaebe145b0f996e5320394dba355286f2a6bc60767d7c912668189205ef08"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FIIRWZ7EWWL7SRPNTY47XVFBFX/bundle.json","state_url":"https://pith.science/pith/FIIRWZ7EWWL7SRPNTY47XVFBFX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FIIRWZ7EWWL7SRPNTY47XVFBFX/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":"2026-08-04T07:38:50Z","links":{"resolver":"https://pith.science/pith/FIIRWZ7EWWL7SRPNTY47XVFBFX","bundle":"https://pith.science/pith/FIIRWZ7EWWL7SRPNTY47XVFBFX/bundle.json","state":"https://pith.science/pith/FIIRWZ7EWWL7SRPNTY47XVFBFX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FIIRWZ7EWWL7SRPNTY47XVFBFX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FIIRWZ7EWWL7SRPNTY47XVFBFX","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":"5cf9588528c7dbb96a6ce86851215039ae5eeb461456adad71c63e57936e042d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T21:51:04Z","title_canon_sha256":"44be545d3448b67b0ada1d4e688223b7525f3da4d331bde4f6dbfa23a1e1008c"},"schema_version":"1.0","source":{"id":"2506.02285","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02285","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02285v2","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02285","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_12","alias_value":"FIIRWZ7EWWL7","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_16","alias_value":"FIIRWZ7EWWL7SRPN","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_8","alias_value":"FIIRWZ7E","created_at":"2026-07-05T11:18:43Z"}],"graph_snapshots":[{"event_id":"sha256:4f4eaebe145b0f996e5320394dba355286f2a6bc60767d7c912668189205ef08","target":"graph","created_at":"2026-07-05T11:18:43Z","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/2506.02285/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"During long-duration Large Language Model (LLM) training runs the gradient norm increases rapidly near the end of training. In this short note, we show that this increase is due to an unintended interaction between weight decay, normalization layers, and the learning rate schedule. We propose a simple correction that fixes this behavior while also resulting in lower loss values throughout training.","authors_text":"Aaron Defazio","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T21:51:04Z","title":"Why Gradients Rapidly Increase Near the End of Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02285","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:ab822c4c26bad9bfc754d20d277fcf1b5e1d744a09bc537cfa12541079689afd","target":"record","created_at":"2026-07-05T11:18:43Z","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":"5cf9588528c7dbb96a6ce86851215039ae5eeb461456adad71c63e57936e042d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T21:51:04Z","title_canon_sha256":"44be545d3448b67b0ada1d4e688223b7525f3da4d331bde4f6dbfa23a1e1008c"},"schema_version":"1.0","source":{"id":"2506.02285","kind":"arxiv","version":2}},"canonical_sha256":"2a111b67e4b597f945ed9e39fbd4a12df5c3b828c153bf02cc75a110080e1516","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a111b67e4b597f945ed9e39fbd4a12df5c3b828c153bf02cc75a110080e1516","first_computed_at":"2026-07-05T11:18:43.415559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:43.415559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FRnOmccteZeFg2zZbobA6Du4HTM7Hp3jpBz7WbF8Yl6WSvBHcF4yWxHSmiI8HcZXITV3GxX9l8qXDu6sHgpwCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:43.416001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02285","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab822c4c26bad9bfc754d20d277fcf1b5e1d744a09bc537cfa12541079689afd","sha256:4f4eaebe145b0f996e5320394dba355286f2a6bc60767d7c912668189205ef08"],"state_sha256":"1e32914f7ac09409864efef413237ced44686bc815e3af2f89054f47f0a11860"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u8eNDKbM+nsVJA9Ss092WfBP+H/GpgADGiROKdQ4X+bySJof/izXbJgAM6HiVw5g1AcOfaEXsY3EjOQ9i4TOBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:38:50.169767Z","bundle_sha256":"66cd6f7b05ae7468f3d0340cc8c31317215793cbc5837047cfb041b5e27a369e"}}