{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RHDJK25A7NRYKQQC57Q35JB4UZ","short_pith_number":"pith:RHDJK25A","canonical_record":{"source":{"id":"2501.04697","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-08T18:58:48Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"215cdfb109b560a08ac4d1419136dd6d2c0202d5484f440de0c4124549eebcf8","abstract_canon_sha256":"d280086f7ecbf98b7f830333543a8f8e8516ff8b5f505cfdef45bb978d4372ac"},"schema_version":"1.0"},"canonical_sha256":"89c6956ba0fb63854202efe1bea43ca672380ed53d907e705621b42a22c72a21","source":{"kind":"arxiv","id":"2501.04697","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04697","created_at":"2026-07-05T11:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04697v2","created_at":"2026-07-05T11:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04697","created_at":"2026-07-05T11:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"RHDJK25A7NRY","created_at":"2026-07-05T11:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"RHDJK25A7NRYKQQC","created_at":"2026-07-05T11:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"RHDJK25A","created_at":"2026-07-05T11:04:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RHDJK25A7NRYKQQC57Q35JB4UZ","target":"record","payload":{"canonical_record":{"source":{"id":"2501.04697","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-08T18:58:48Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"215cdfb109b560a08ac4d1419136dd6d2c0202d5484f440de0c4124549eebcf8","abstract_canon_sha256":"d280086f7ecbf98b7f830333543a8f8e8516ff8b5f505cfdef45bb978d4372ac"},"schema_version":"1.0"},"canonical_sha256":"89c6956ba0fb63854202efe1bea43ca672380ed53d907e705621b42a22c72a21","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:43.733850Z","signature_b64":"WCdBXkTBWn2oZmrw7edZ4HLRZBtkTihMTkeykmYW31XWRnOAwb6qHsAA+v7mTDnSthpKJDcaB9Jo31YgpUKEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89c6956ba0fb63854202efe1bea43ca672380ed53d907e705621b42a22c72a21","last_reissued_at":"2026-07-05T11:04:43.733306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:43.733306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.04697","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":"2026-07-05T11:04:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N4pfupxpW5llG55kl4ULiTcv/ScXbCT+SgsoSggfNg1y+moitkvdRdsnUeRtSIft0JhkspMEpYyMgTSmJZCuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:10:52.255075Z"},"content_sha256":"e882bb3e8cd4b9db1104af68bb57ff3d8d788dca43412e77f1dc08ceeac73378","schema_version":"1.0","event_id":"sha256:e882bb3e8cd4b9db1104af68bb57ff3d8d788dca43412e77f1dc08ceeac73378"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RHDJK25A7NRYKQQC57Q35JB4UZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Grokking at the Edge of Numerical Stability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lucas Prieto, Melih Barsbey, Pedro A.M. Mediano, Tolga Birdal","submitted_at":"2025-01-08T18:58:48Z","abstract_excerpt":"Grokking, the sudden generalization that occurs after prolonged overfitting, is a surprising phenomenon challenging our understanding of deep learning. Although significant progress has been made in understanding grokking, the reasons behind the delayed generalization and its dependence on regularization remain unclear. In this work, we argue that without regularization, grokking tasks push models to the edge of numerical stability, introducing floating point errors in the Softmax function, which we refer to as Softmax Collapse (SC). We demonstrate that SC prevents grokking and that mitigating"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04697","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/2501.04697/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":"2026-07-05T11:04:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gsl4wxEa+RKmqbONwtmRMSTJ30xLFVpRqHQIpFtHBUVxwJXoPVqIUMbGjdynU54MuHB5LRud6RhoLs/vy0UjAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:10:52.255587Z"},"content_sha256":"c63eae5d6aaf6621d4d30ce4c70924df28bf7f9a611812f05db8819133f56b51","schema_version":"1.0","event_id":"sha256:c63eae5d6aaf6621d4d30ce4c70924df28bf7f9a611812f05db8819133f56b51"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RHDJK25A7NRYKQQC57Q35JB4UZ/bundle.json","state_url":"https://pith.science/pith/RHDJK25A7NRYKQQC57Q35JB4UZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RHDJK25A7NRYKQQC57Q35JB4UZ/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":"2026-08-05T06:10:52Z","links":{"resolver":"https://pith.science/pith/RHDJK25A7NRYKQQC57Q35JB4UZ","bundle":"https://pith.science/pith/RHDJK25A7NRYKQQC57Q35JB4UZ/bundle.json","state":"https://pith.science/pith/RHDJK25A7NRYKQQC57Q35JB4UZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RHDJK25A7NRYKQQC57Q35JB4UZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RHDJK25A7NRYKQQC57Q35JB4UZ","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":"d280086f7ecbf98b7f830333543a8f8e8516ff8b5f505cfdef45bb978d4372ac","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-08T18:58:48Z","title_canon_sha256":"215cdfb109b560a08ac4d1419136dd6d2c0202d5484f440de0c4124549eebcf8"},"schema_version":"1.0","source":{"id":"2501.04697","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04697","created_at":"2026-07-05T11:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04697v2","created_at":"2026-07-05T11:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04697","created_at":"2026-07-05T11:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"RHDJK25A7NRY","created_at":"2026-07-05T11:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"RHDJK25A7NRYKQQC","created_at":"2026-07-05T11:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"RHDJK25A","created_at":"2026-07-05T11:04:43Z"}],"graph_snapshots":[{"event_id":"sha256:c63eae5d6aaf6621d4d30ce4c70924df28bf7f9a611812f05db8819133f56b51","target":"graph","created_at":"2026-07-05T11:04:43Z","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/2501.04697/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Grokking, the sudden generalization that occurs after prolonged overfitting, is a surprising phenomenon challenging our understanding of deep learning. Although significant progress has been made in understanding grokking, the reasons behind the delayed generalization and its dependence on regularization remain unclear. In this work, we argue that without regularization, grokking tasks push models to the edge of numerical stability, introducing floating point errors in the Softmax function, which we refer to as Softmax Collapse (SC). We demonstrate that SC prevents grokking and that mitigating","authors_text":"Lucas Prieto, Melih Barsbey, Pedro A.M. Mediano, Tolga Birdal","cross_cats":["cs.AI","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-08T18:58:48Z","title":"Grokking at the Edge of Numerical Stability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04697","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:e882bb3e8cd4b9db1104af68bb57ff3d8d788dca43412e77f1dc08ceeac73378","target":"record","created_at":"2026-07-05T11:04:43Z","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":"d280086f7ecbf98b7f830333543a8f8e8516ff8b5f505cfdef45bb978d4372ac","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-08T18:58:48Z","title_canon_sha256":"215cdfb109b560a08ac4d1419136dd6d2c0202d5484f440de0c4124549eebcf8"},"schema_version":"1.0","source":{"id":"2501.04697","kind":"arxiv","version":2}},"canonical_sha256":"89c6956ba0fb63854202efe1bea43ca672380ed53d907e705621b42a22c72a21","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89c6956ba0fb63854202efe1bea43ca672380ed53d907e705621b42a22c72a21","first_computed_at":"2026-07-05T11:04:43.733306Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:43.733306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WCdBXkTBWn2oZmrw7edZ4HLRZBtkTihMTkeykmYW31XWRnOAwb6qHsAA+v7mTDnSthpKJDcaB9Jo31YgpUKEBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:43.733850Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04697","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e882bb3e8cd4b9db1104af68bb57ff3d8d788dca43412e77f1dc08ceeac73378","sha256:c63eae5d6aaf6621d4d30ce4c70924df28bf7f9a611812f05db8819133f56b51"],"state_sha256":"b8470fd7d38f65ab5bdce58ddd294b6d18e73b81177f140c83d724a6711e8e74"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LHAgVcEWLB+cs0aESm+nhCmlKIysMvL115KTd4WW5tT0gKkY6sbtPCg4vsZabQ/Uy0JIy0PVFDCUDBPY4aUXCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:10:52.260838Z","bundle_sha256":"78b7faf78cbdc1f6d8a85ce298e62f1f4ff11771481b1832f13d891f48346412"}}