{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XOVYN75UABKBJNOWDJATDJAXTB","short_pith_number":"pith:XOVYN75U","schema_version":"1.0","canonical_sha256":"bbab86ffb4005414b5d61a4131a417986ef9e5ed51dbf8c8b50b36fbcba47293","source":{"kind":"arxiv","id":"2410.12783","version":1},"attestation_state":"computed","paper":{"title":"Context-Scaling versus Task-Scaling in In-Context Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adityanarayanan Radhakrishnan, Amirhesam Abedsoltan, Jingfeng Wu, Mikhail Belkin","submitted_at":"2024-10-16T17:58:08Z","abstract_excerpt":"Transformers exhibit In-Context Learning (ICL), where these models solve new tasks by using examples in the prompt without additional training. In our work, we identify and analyze two key components of ICL: (1) context-scaling, where model performance improves as the number of in-context examples increases and (2) task-scaling, where model performance improves as the number of pre-training tasks increases. While transformers are capable of both context-scaling and task-scaling, we empirically show that standard Multi-Layer Perceptrons (MLPs) with vectorized input are only capable of task-scal"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.12783","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-16T17:58:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a651ecfca9c505475e348bd9d25ab363cd423517416f583260e71510c2a2fa57","abstract_canon_sha256":"075c32c9150dbc0fc64e9cd5d43400be1039de0f231b9794f7b3d9e2b7206f24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:33.868397Z","signature_b64":"RQGJn2laNs/JL/5a8Mz37PG2+igiuMn/9s6uz63bd8XcrcNJxE2HP9IO6+2bMcw8bWo1PKZSVH8RY9yXxDXGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbab86ffb4005414b5d61a4131a417986ef9e5ed51dbf8c8b50b36fbcba47293","last_reissued_at":"2026-07-05T09:21:33.867913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:33.867913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-Scaling versus Task-Scaling in In-Context Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adityanarayanan Radhakrishnan, Amirhesam Abedsoltan, Jingfeng Wu, Mikhail Belkin","submitted_at":"2024-10-16T17:58:08Z","abstract_excerpt":"Transformers exhibit In-Context Learning (ICL), where these models solve new tasks by using examples in the prompt without additional training. In our work, we identify and analyze two key components of ICL: (1) context-scaling, where model performance improves as the number of in-context examples increases and (2) task-scaling, where model performance improves as the number of pre-training tasks increases. While transformers are capable of both context-scaling and task-scaling, we empirically show that standard Multi-Layer Perceptrons (MLPs) with vectorized input are only capable of task-scal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12783","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/2410.12783/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.12783","created_at":"2026-07-05T09:21:33.867968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12783v1","created_at":"2026-07-05T09:21:33.867968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12783","created_at":"2026-07-05T09:21:33.867968+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOVYN75UABKB","created_at":"2026-07-05T09:21:33.867968+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOVYN75UABKBJNOW","created_at":"2026-07-05T09:21:33.867968+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOVYN75U","created_at":"2026-07-05T09:21:33.867968+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOVYN75UABKBJNOWDJATDJAXTB","json":"https://pith.science/pith/XOVYN75UABKBJNOWDJATDJAXTB.json","graph_json":"https://pith.science/api/pith-number/XOVYN75UABKBJNOWDJATDJAXTB/graph.json","events_json":"https://pith.science/api/pith-number/XOVYN75UABKBJNOWDJATDJAXTB/events.json","paper":"https://pith.science/paper/XOVYN75U"},"agent_actions":{"view_html":"https://pith.science/pith/XOVYN75UABKBJNOWDJATDJAXTB","download_json":"https://pith.science/pith/XOVYN75UABKBJNOWDJATDJAXTB.json","view_paper":"https://pith.science/paper/XOVYN75U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12783&json=true","fetch_graph":"https://pith.science/api/pith-number/XOVYN75UABKBJNOWDJATDJAXTB/graph.json","fetch_events":"https://pith.science/api/pith-number/XOVYN75UABKBJNOWDJATDJAXTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOVYN75UABKBJNOWDJATDJAXTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOVYN75UABKBJNOWDJATDJAXTB/action/storage_attestation","attest_author":"https://pith.science/pith/XOVYN75UABKBJNOWDJATDJAXTB/action/author_attestation","sign_citation":"https://pith.science/pith/XOVYN75UABKBJNOWDJATDJAXTB/action/citation_signature","submit_replication":"https://pith.science/pith/XOVYN75UABKBJNOWDJATDJAXTB/action/replication_record"}},"created_at":"2026-07-05T09:21:33.867968+00:00","updated_at":"2026-07-05T09:21:33.867968+00:00"}