{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5CX2PMOIDW63ZMBJWFAESW7CMN","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":"ca296c1d3879ddcb7bee33ef475076974be11b627d7ef088e3772cbf6ecff4de","cross_cats_sorted":["cond-mat.dis-nn","hep-th","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T17:59:36Z","title_canon_sha256":"1080b689fe2dc7ca4201f0c673c361b73afc210ed890719ba484833bbe163bc8"},"schema_version":"1.0","source":{"id":"2406.02550","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02550","created_at":"2026-07-05T09:30:16Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02550v2","created_at":"2026-07-05T09:30:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02550","created_at":"2026-07-05T09:30:16Z"},{"alias_kind":"pith_short_12","alias_value":"5CX2PMOIDW63","created_at":"2026-07-05T09:30:16Z"},{"alias_kind":"pith_short_16","alias_value":"5CX2PMOIDW63ZMBJ","created_at":"2026-07-05T09:30:16Z"},{"alias_kind":"pith_short_8","alias_value":"5CX2PMOI","created_at":"2026-07-05T09:30:16Z"}],"graph_snapshots":[{"event_id":"sha256:e895cea6ce9ddfb732b07f2bcc3f4cf94360f6e67a62266386309994d7d724d8","target":"graph","created_at":"2026-07-05T09:30:16Z","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/2406.02550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models can solve tasks that were not present in the training set. This capability is believed to be due to in-context learning and skill composition. In this work, we study the emergence of in-context learning and skill composition in a collection of modular arithmetic tasks. Specifically, we consider a finite collection of linear modular functions $z = a \\, x + b \\, y \\;\\mathrm{mod}\\; p$ labeled by the vector $(a, b) \\in \\mathbb{Z}_p^2$. We use some of these tasks for pre-training and the rest for out-of-distribution testing. We empirically show that a GPT-style transformer exh","authors_text":"Andrey Gromov, Aritra Das, Darshil Doshi, Tianyu He","cross_cats":["cond-mat.dis-nn","hep-th","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T17:59:36Z","title":"Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02550","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":"sha256:12a05c52e8f9ed5dacf83cc5c4d98d0e9ba55f9cdb9bae118ddf72fbf26ea60e","target":"record","created_at":"2026-07-05T09:30:16Z","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":"ca296c1d3879ddcb7bee33ef475076974be11b627d7ef088e3772cbf6ecff4de","cross_cats_sorted":["cond-mat.dis-nn","hep-th","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T17:59:36Z","title_canon_sha256":"1080b689fe2dc7ca4201f0c673c361b73afc210ed890719ba484833bbe163bc8"},"schema_version":"1.0","source":{"id":"2406.02550","kind":"arxiv","version":2}},"canonical_sha256":"e8afa7b1c81dbdbcb029b140495be2635f51c109283d37a384a093559f3c6122","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8afa7b1c81dbdbcb029b140495be2635f51c109283d37a384a093559f3c6122","first_computed_at":"2026-07-05T09:30:16.014336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:16.014336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WQfGiOcxmgXuwt9Zy7U23sPUz4MQzaQBsHRWoC9hIeIYHTahQT2u7AufnszQQZW/14mDpEII8H01RW9N4AcZCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:16.014848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02550","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12a05c52e8f9ed5dacf83cc5c4d98d0e9ba55f9cdb9bae118ddf72fbf26ea60e","sha256:e895cea6ce9ddfb732b07f2bcc3f4cf94360f6e67a62266386309994d7d724d8"],"state_sha256":"c9919779033a7e9d6e479c386b1ede4a190a104ae26e3349d38ac093363d3d4c"}