{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IVYZGKYWW2PO22UQ5UHO57GQEX","short_pith_number":"pith:IVYZGKYW","canonical_record":{"source":{"id":"2504.16041","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T17:08:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae322101a8019ffef09426a74d92e430abe7ed04bdc0fc459dbec8915b73b729","abstract_canon_sha256":"f83014f1f2f7e5aa47b4b529587f67b05774c4f4cf8539c4d50afb3fa4786cae"},"schema_version":"1.0"},"canonical_sha256":"4571932b16b69eed6a90ed0eeefcd025c915962ad37cc62022aea118444af93a","source":{"kind":"arxiv","id":"2504.16041","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16041","created_at":"2026-07-05T10:52:34Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16041v1","created_at":"2026-07-05T10:52:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16041","created_at":"2026-07-05T10:52:34Z"},{"alias_kind":"pith_short_12","alias_value":"IVYZGKYWW2PO","created_at":"2026-07-05T10:52:34Z"},{"alias_kind":"pith_short_16","alias_value":"IVYZGKYWW2PO22UQ","created_at":"2026-07-05T10:52:34Z"},{"alias_kind":"pith_short_8","alias_value":"IVYZGKYW","created_at":"2026-07-05T10:52:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IVYZGKYWW2PO22UQ5UHO57GQEX","target":"record","payload":{"canonical_record":{"source":{"id":"2504.16041","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T17:08:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ae322101a8019ffef09426a74d92e430abe7ed04bdc0fc459dbec8915b73b729","abstract_canon_sha256":"f83014f1f2f7e5aa47b4b529587f67b05774c4f4cf8539c4d50afb3fa4786cae"},"schema_version":"1.0"},"canonical_sha256":"4571932b16b69eed6a90ed0eeefcd025c915962ad37cc62022aea118444af93a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:34.333722Z","signature_b64":"fzwXDM6Pr/EJ3JmZ5RPZtz36VWmhvAazuGRhkIvAdgeea5ZIT+vrpkkHhPKWTqkHZnHaw49XuUxiHxQ7wuf/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4571932b16b69eed6a90ed0eeefcd025c915962ad37cc62022aea118444af93a","last_reissued_at":"2026-07-05T10:52:34.333185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:34.333185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.16041","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":"2026-07-05T10:52:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t5SWd9sCBfvBZZIbKqrHUrGJeIzQjbzQTpU8wZZRelYxZ/awMk9CbsLzUc2QBfTqxB8IjQYWPUIkyb3LJLJHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:10:14.716602Z"},"content_sha256":"093c54e2324d7dad9b225ebaab2f683d5e8e945f6925cfb2d4c04cab63a788e8","schema_version":"1.0","event_id":"sha256:093c54e2324d7dad9b225ebaab2f683d5e8e945f6925cfb2d4c04cab63a788e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IVYZGKYWW2PO22UQ5UHO57GQEX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Muon Optimizer Accelerates Grokking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amund Tveit, Arve Skogvold, Bj{\\o}rn Remseth","submitted_at":"2025-04-22T17:08:09Z","abstract_excerpt":"This paper investigates the impact of different optimizers on the grokking phenomenon, where models exhibit delayed generalization. We conducted experiments across seven numerical tasks (primarily modular arithmetic) using a modern Transformer architecture. The experimental configuration systematically varied the optimizer (Muon vs. AdamW) and the softmax activation function (standard softmax, stablemax, and sparsemax) to assess their combined effect on learning dynamics. Our empirical evaluation reveals that the Muon optimizer, characterized by its use of spectral norm constraints and second-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16041","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/2504.16041/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":"2026-07-05T10:52:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GVlwGNEBau3qCEtFoRS0Vj19F8rwcGJQEjJIM7mIywFE9xN3DBfb39juzRJ7SiMuF1O97HsKHuermNgZS0yUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:10:14.717097Z"},"content_sha256":"e2369ceda77ab28bd742d3333f340bdbaa85d893c4ada30372ba91e19cf41d63","schema_version":"1.0","event_id":"sha256:e2369ceda77ab28bd742d3333f340bdbaa85d893c4ada30372ba91e19cf41d63"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IVYZGKYWW2PO22UQ5UHO57GQEX/bundle.json","state_url":"https://pith.science/pith/IVYZGKYWW2PO22UQ5UHO57GQEX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IVYZGKYWW2PO22UQ5UHO57GQEX/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":"2026-08-10T03:10:14Z","links":{"resolver":"https://pith.science/pith/IVYZGKYWW2PO22UQ5UHO57GQEX","bundle":"https://pith.science/pith/IVYZGKYWW2PO22UQ5UHO57GQEX/bundle.json","state":"https://pith.science/pith/IVYZGKYWW2PO22UQ5UHO57GQEX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IVYZGKYWW2PO22UQ5UHO57GQEX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IVYZGKYWW2PO22UQ5UHO57GQEX","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":"f83014f1f2f7e5aa47b4b529587f67b05774c4f4cf8539c4d50afb3fa4786cae","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T17:08:09Z","title_canon_sha256":"ae322101a8019ffef09426a74d92e430abe7ed04bdc0fc459dbec8915b73b729"},"schema_version":"1.0","source":{"id":"2504.16041","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16041","created_at":"2026-07-05T10:52:34Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16041v1","created_at":"2026-07-05T10:52:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16041","created_at":"2026-07-05T10:52:34Z"},{"alias_kind":"pith_short_12","alias_value":"IVYZGKYWW2PO","created_at":"2026-07-05T10:52:34Z"},{"alias_kind":"pith_short_16","alias_value":"IVYZGKYWW2PO22UQ","created_at":"2026-07-05T10:52:34Z"},{"alias_kind":"pith_short_8","alias_value":"IVYZGKYW","created_at":"2026-07-05T10:52:34Z"}],"graph_snapshots":[{"event_id":"sha256:e2369ceda77ab28bd742d3333f340bdbaa85d893c4ada30372ba91e19cf41d63","target":"graph","created_at":"2026-07-05T10:52:34Z","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/2504.16041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates the impact of different optimizers on the grokking phenomenon, where models exhibit delayed generalization. We conducted experiments across seven numerical tasks (primarily modular arithmetic) using a modern Transformer architecture. The experimental configuration systematically varied the optimizer (Muon vs. AdamW) and the softmax activation function (standard softmax, stablemax, and sparsemax) to assess their combined effect on learning dynamics. Our empirical evaluation reveals that the Muon optimizer, characterized by its use of spectral norm constraints and second-","authors_text":"Amund Tveit, Arve Skogvold, Bj{\\o}rn Remseth","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T17:08:09Z","title":"Muon Optimizer Accelerates Grokking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16041","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":"sha256:093c54e2324d7dad9b225ebaab2f683d5e8e945f6925cfb2d4c04cab63a788e8","target":"record","created_at":"2026-07-05T10:52:34Z","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":"f83014f1f2f7e5aa47b4b529587f67b05774c4f4cf8539c4d50afb3fa4786cae","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T17:08:09Z","title_canon_sha256":"ae322101a8019ffef09426a74d92e430abe7ed04bdc0fc459dbec8915b73b729"},"schema_version":"1.0","source":{"id":"2504.16041","kind":"arxiv","version":1}},"canonical_sha256":"4571932b16b69eed6a90ed0eeefcd025c915962ad37cc62022aea118444af93a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4571932b16b69eed6a90ed0eeefcd025c915962ad37cc62022aea118444af93a","first_computed_at":"2026-07-05T10:52:34.333185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:34.333185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fzwXDM6Pr/EJ3JmZ5RPZtz36VWmhvAazuGRhkIvAdgeea5ZIT+vrpkkHhPKWTqkHZnHaw49XuUxiHxQ7wuf/Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:34.333722Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.16041","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:093c54e2324d7dad9b225ebaab2f683d5e8e945f6925cfb2d4c04cab63a788e8","sha256:e2369ceda77ab28bd742d3333f340bdbaa85d893c4ada30372ba91e19cf41d63"],"state_sha256":"13c8060a591dc235999cc21d4faf255a5d9ae7f052759c6d05111dd6bfe01c3c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KjVVU0jEcNhNJ0qQrSUxhf2PrsDXW7Q5FpwvgKACgwFKuqQM2r+9JACcgj9VC2t7h2nXRlbLBY7ec+65Re7nDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T03:10:14.721468Z","bundle_sha256":"a162b93bcc9b1f8d09e34834e23296c3eedee6a618f2e882c778af8a4e704de8"}}