{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LQ7N56XB2BRO5DHX7HIRVPZUWQ","short_pith_number":"pith:LQ7N56XB","canonical_record":{"source":{"id":"2505.15624","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T15:12:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"cca2fe4e23998256ca780937206301c44c911a5fb64b19cf357a4cdfcf38f4ae","abstract_canon_sha256":"9ea0f87f36e70d673cbed8b35c1486fbcb4945b45aceca54394faa2ba9094965"},"schema_version":"1.0"},"canonical_sha256":"5c3edefae1d062ee8cf7f9d11abf34b42e570a7a8642e1006767809352d0f77b","source":{"kind":"arxiv","id":"2505.15624","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15624","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15624v1","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15624","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"pith_short_12","alias_value":"LQ7N56XB2BRO","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"pith_short_16","alias_value":"LQ7N56XB2BRO5DHX","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"pith_short_8","alias_value":"LQ7N56XB","created_at":"2026-07-05T11:06:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LQ7N56XB2BRO5DHX7HIRVPZUWQ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.15624","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T15:12:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"cca2fe4e23998256ca780937206301c44c911a5fb64b19cf357a4cdfcf38f4ae","abstract_canon_sha256":"9ea0f87f36e70d673cbed8b35c1486fbcb4945b45aceca54394faa2ba9094965"},"schema_version":"1.0"},"canonical_sha256":"5c3edefae1d062ee8cf7f9d11abf34b42e570a7a8642e1006767809352d0f77b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:48.623510Z","signature_b64":"lJ6eGlHgNkhdFGFuA5caytqyzfsODq1HiNGxghL36ffAnqRSh/9qosWrdx6J3YotogDBKd1BzbkbCgmC+YeKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c3edefae1d062ee8cf7f9d11abf34b42e570a7a8642e1006767809352d0f77b","last_reissued_at":"2026-07-05T11:06:48.622887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:48.622887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.15624","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":"2026-07-05T11:06:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0ndXot0he6hztl4sAk6TvoEpKXC4yliAz5PBWIwk1wXIKrdQQaFABfdm91Wmj66hifKKjsmQbA9pWFNSJnTKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T12:10:56.532088Z"},"content_sha256":"36914be128de3be89bb7240b2ae5383c7f0579fd521b3f62ab6172729fa2257d","schema_version":"1.0","event_id":"sha256:36914be128de3be89bb7240b2ae5383c7f0579fd521b3f62ab6172729fa2257d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LQ7N56XB2BRO5DHX7HIRVPZUWQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mechanistic Insights into Grokking from the Embedding Layer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Hilal AlQuabeh, H.V.AlquBoj, Kentaro Inui, Munachiso Nwadike, Velibor Bojkovic","submitted_at":"2025-05-21T15:12:34Z","abstract_excerpt":"Grokking, a delayed generalization in neural networks after perfect training performance, has been observed in Transformers and MLPs, but the components driving it remain underexplored. We show that embeddings are central to grokking: introducing them into MLPs induces delayed generalization in modular arithmetic tasks, whereas MLPs without embeddings can generalize immediately. Our analysis identifies two key mechanisms: (1) Embedding update dynamics, where rare tokens stagnate due to sparse gradient updates and weight decay, and (2) Bilinear coupling, where the interaction between embeddings"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15624","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/2505.15624/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":"2026-07-05T11:06:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wtx79UcMvgOdaCMlfMhyhYpZSBbBeNPlgJFpSj40FsIm5HQK4RpQdJt9NesZ9RR4aj3EUEyYuj4GVm4xW64qDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T12:10:56.532609Z"},"content_sha256":"245bcde9939600cb8982625382b8bc47bdb78cc176d0f66b13f15eaec4021047","schema_version":"1.0","event_id":"sha256:245bcde9939600cb8982625382b8bc47bdb78cc176d0f66b13f15eaec4021047"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LQ7N56XB2BRO5DHX7HIRVPZUWQ/bundle.json","state_url":"https://pith.science/pith/LQ7N56XB2BRO5DHX7HIRVPZUWQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LQ7N56XB2BRO5DHX7HIRVPZUWQ/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":"2026-08-15T12:10:56Z","links":{"resolver":"https://pith.science/pith/LQ7N56XB2BRO5DHX7HIRVPZUWQ","bundle":"https://pith.science/pith/LQ7N56XB2BRO5DHX7HIRVPZUWQ/bundle.json","state":"https://pith.science/pith/LQ7N56XB2BRO5DHX7HIRVPZUWQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LQ7N56XB2BRO5DHX7HIRVPZUWQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LQ7N56XB2BRO5DHX7HIRVPZUWQ","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":"9ea0f87f36e70d673cbed8b35c1486fbcb4945b45aceca54394faa2ba9094965","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T15:12:34Z","title_canon_sha256":"cca2fe4e23998256ca780937206301c44c911a5fb64b19cf357a4cdfcf38f4ae"},"schema_version":"1.0","source":{"id":"2505.15624","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15624","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15624v1","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15624","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"pith_short_12","alias_value":"LQ7N56XB2BRO","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"pith_short_16","alias_value":"LQ7N56XB2BRO5DHX","created_at":"2026-07-05T11:06:48Z"},{"alias_kind":"pith_short_8","alias_value":"LQ7N56XB","created_at":"2026-07-05T11:06:48Z"}],"graph_snapshots":[{"event_id":"sha256:245bcde9939600cb8982625382b8bc47bdb78cc176d0f66b13f15eaec4021047","target":"graph","created_at":"2026-07-05T11:06:48Z","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/2505.15624/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Grokking, a delayed generalization in neural networks after perfect training performance, has been observed in Transformers and MLPs, but the components driving it remain underexplored. We show that embeddings are central to grokking: introducing them into MLPs induces delayed generalization in modular arithmetic tasks, whereas MLPs without embeddings can generalize immediately. Our analysis identifies two key mechanisms: (1) Embedding update dynamics, where rare tokens stagnate due to sparse gradient updates and weight decay, and (2) Bilinear coupling, where the interaction between embeddings","authors_text":"Hilal AlQuabeh, H.V.AlquBoj, Kentaro Inui, Munachiso Nwadike, Velibor Bojkovic","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T15:12:34Z","title":"Mechanistic Insights into Grokking from the Embedding Layer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15624","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":"sha256:36914be128de3be89bb7240b2ae5383c7f0579fd521b3f62ab6172729fa2257d","target":"record","created_at":"2026-07-05T11:06:48Z","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":"9ea0f87f36e70d673cbed8b35c1486fbcb4945b45aceca54394faa2ba9094965","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T15:12:34Z","title_canon_sha256":"cca2fe4e23998256ca780937206301c44c911a5fb64b19cf357a4cdfcf38f4ae"},"schema_version":"1.0","source":{"id":"2505.15624","kind":"arxiv","version":1}},"canonical_sha256":"5c3edefae1d062ee8cf7f9d11abf34b42e570a7a8642e1006767809352d0f77b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c3edefae1d062ee8cf7f9d11abf34b42e570a7a8642e1006767809352d0f77b","first_computed_at":"2026-07-05T11:06:48.622887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:48.622887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lJ6eGlHgNkhdFGFuA5caytqyzfsODq1HiNGxghL36ffAnqRSh/9qosWrdx6J3YotogDBKd1BzbkbCgmC+YeKDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:48.623510Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15624","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36914be128de3be89bb7240b2ae5383c7f0579fd521b3f62ab6172729fa2257d","sha256:245bcde9939600cb8982625382b8bc47bdb78cc176d0f66b13f15eaec4021047"],"state_sha256":"ac78f43fa08071faaa9720e1284bdf36b65140206bd0b529b9d5bc0edb143567"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YP7KsBzaYTLGhL9l1l7d4yKcHuO23U2ZfGOQZDA9rHQEGOK29zc2yhizsu08h6Zg4VDNUglJXTvETfV23zi3Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T12:10:56.535843Z","bundle_sha256":"36e4d20830d1401e7d19bcd41c9765ea1789cc2cbd080500a505c0dba1b057fe"}}