{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SNAI4SLS5RXKHB4ZMO742PVRXI","short_pith_number":"pith:SNAI4SLS","canonical_record":{"source":{"id":"2605.29548","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T08:02:11Z","cross_cats_sorted":[],"title_canon_sha256":"91c571c5681f8728f7aa7c2a45f897708147783398d3462abde2101ca01cfc34","abstract_canon_sha256":"166fbce3226d023d0621cdd479f4b3001e7feadec71cb130f37ca57cc7d470fa"},"schema_version":"1.0"},"canonical_sha256":"93408e4972ec6ea3879963bfcd3eb1ba3bf9827a4f5c4b1aa837a4d076a852d6","source":{"kind":"arxiv","id":"2605.29548","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29548","created_at":"2026-05-29T01:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29548v1","created_at":"2026-05-29T01:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29548","created_at":"2026-05-29T01:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"SNAI4SLS5RXK","created_at":"2026-05-29T01:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"SNAI4SLS5RXKHB4Z","created_at":"2026-05-29T01:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"SNAI4SLS","created_at":"2026-05-29T01:05:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SNAI4SLS5RXKHB4ZMO742PVRXI","target":"record","payload":{"canonical_record":{"source":{"id":"2605.29548","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T08:02:11Z","cross_cats_sorted":[],"title_canon_sha256":"91c571c5681f8728f7aa7c2a45f897708147783398d3462abde2101ca01cfc34","abstract_canon_sha256":"166fbce3226d023d0621cdd479f4b3001e7feadec71cb130f37ca57cc7d470fa"},"schema_version":"1.0"},"canonical_sha256":"93408e4972ec6ea3879963bfcd3eb1ba3bf9827a4f5c4b1aa837a4d076a852d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:46.534791Z","signature_b64":"zEUn/5V5rkyCBbI/gWzl56GCzo1f/9ULKpO35OvYIF4TfJ1ztf4+/GCkBnw4Pb/U3sx0z0HiIqCJmCbN1oHuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93408e4972ec6ea3879963bfcd3eb1ba3bf9827a4f5c4b1aa837a4d076a852d6","last_reissued_at":"2026-05-29T01:05:46.533942Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:46.533942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.29548","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":"2026-05-29T01:05:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y8Q5ffLVgmymPoxo0QvY0/UwXkCxfpxQxFul4qz+fs8yeXUV8mM84x1RanIJZTVNyqTweJcXFacDVdcTo3/NAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T01:20:32.064005Z"},"content_sha256":"48ab22e932c8354c2d0d157ff8d7b90e6e4120638967143ab3e00fa2af9efe33","schema_version":"1.0","event_id":"sha256:48ab22e932c8354c2d0d157ff8d7b90e6e4120638967143ab3e00fa2af9efe33"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SNAI4SLS5RXKHB4ZMO742PVRXI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Kyle Lampinen, Christopher Potts, Daniel Wurgaft, David Alvarez-Melis, Ekdeep Singh Lubana, Jing Huang, Laura Ruis, Naomi Saphra, Rachit Bansal","submitted_at":"2026-05-28T08:02:11Z","abstract_excerpt":"Larger models learn tasks smaller models do not. What drives this phenomenon? We develop a simple phenomenological argument that power-law scaling already suggests that a larger model will be able to learn a part of the data distribution that a smaller model fails to learn, even with infinite training data. To validate this claim and identify its causes, we study the effects of model scaling on a synthetic setup consisting of a mixture of tasks that show monotonic scaling curves. The results point to a data-induced competition over resources (neurons). Specifically, smaller models allocate the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29548","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/2605.29548/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":"2026-05-29T01:05:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CqJILEbx2n0GKNri0qkJ+dnJ9mRnGflfuZXxJaVoYzjdnxr8el7k4QBjZh98ImDFVYhhrZFEotzdyDW+a35PCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T01:20:32.064823Z"},"content_sha256":"a3efd76e8434e9f18f0497670c643be589745d7c78cec6951e39bf65b530db2f","schema_version":"1.0","event_id":"sha256:a3efd76e8434e9f18f0497670c643be589745d7c78cec6951e39bf65b530db2f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SNAI4SLS5RXKHB4ZMO742PVRXI/bundle.json","state_url":"https://pith.science/pith/SNAI4SLS5RXKHB4ZMO742PVRXI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SNAI4SLS5RXKHB4ZMO742PVRXI/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":"2026-05-30T01:20:32Z","links":{"resolver":"https://pith.science/pith/SNAI4SLS5RXKHB4ZMO742PVRXI","bundle":"https://pith.science/pith/SNAI4SLS5RXKHB4ZMO742PVRXI/bundle.json","state":"https://pith.science/pith/SNAI4SLS5RXKHB4ZMO742PVRXI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SNAI4SLS5RXKHB4ZMO742PVRXI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SNAI4SLS5RXKHB4ZMO742PVRXI","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":"166fbce3226d023d0621cdd479f4b3001e7feadec71cb130f37ca57cc7d470fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T08:02:11Z","title_canon_sha256":"91c571c5681f8728f7aa7c2a45f897708147783398d3462abde2101ca01cfc34"},"schema_version":"1.0","source":{"id":"2605.29548","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29548","created_at":"2026-05-29T01:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29548v1","created_at":"2026-05-29T01:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29548","created_at":"2026-05-29T01:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"SNAI4SLS5RXK","created_at":"2026-05-29T01:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"SNAI4SLS5RXKHB4Z","created_at":"2026-05-29T01:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"SNAI4SLS","created_at":"2026-05-29T01:05:46Z"}],"graph_snapshots":[{"event_id":"sha256:a3efd76e8434e9f18f0497670c643be589745d7c78cec6951e39bf65b530db2f","target":"graph","created_at":"2026-05-29T01:05:46Z","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/2605.29548/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Larger models learn tasks smaller models do not. What drives this phenomenon? We develop a simple phenomenological argument that power-law scaling already suggests that a larger model will be able to learn a part of the data distribution that a smaller model fails to learn, even with infinite training data. To validate this claim and identify its causes, we study the effects of model scaling on a synthetic setup consisting of a mixture of tasks that show monotonic scaling curves. The results point to a data-induced competition over resources (neurons). Specifically, smaller models allocate the","authors_text":"Andrew Kyle Lampinen, Christopher Potts, Daniel Wurgaft, David Alvarez-Melis, Ekdeep Singh Lubana, Jing Huang, Laura Ruis, Naomi Saphra, Rachit Bansal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T08:02:11Z","title":"Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29548","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":"sha256:48ab22e932c8354c2d0d157ff8d7b90e6e4120638967143ab3e00fa2af9efe33","target":"record","created_at":"2026-05-29T01:05:46Z","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":"166fbce3226d023d0621cdd479f4b3001e7feadec71cb130f37ca57cc7d470fa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T08:02:11Z","title_canon_sha256":"91c571c5681f8728f7aa7c2a45f897708147783398d3462abde2101ca01cfc34"},"schema_version":"1.0","source":{"id":"2605.29548","kind":"arxiv","version":1}},"canonical_sha256":"93408e4972ec6ea3879963bfcd3eb1ba3bf9827a4f5c4b1aa837a4d076a852d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93408e4972ec6ea3879963bfcd3eb1ba3bf9827a4f5c4b1aa837a4d076a852d6","first_computed_at":"2026-05-29T01:05:46.533942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:46.533942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zEUn/5V5rkyCBbI/gWzl56GCzo1f/9ULKpO35OvYIF4TfJ1ztf4+/GCkBnw4Pb/U3sx0z0HiIqCJmCbN1oHuCw==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:46.534791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29548","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48ab22e932c8354c2d0d157ff8d7b90e6e4120638967143ab3e00fa2af9efe33","sha256:a3efd76e8434e9f18f0497670c643be589745d7c78cec6951e39bf65b530db2f"],"state_sha256":"0944c7f922156d58e196e23885a40503692590d08b911fb6f06e704735d0b4db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KZJS1SmJX+y8Zt6UAZrRdeW43upG3DDAkI0YubYTg/F9ldpn1p5+d5W/yD/CEJGftIeA7u87WIYUFiBkycNWAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T01:20:32.069596Z","bundle_sha256":"fed856c1c72bf0f06bf48915bbcd9544a41856cb5c03482ee1178f676b7b73e7"}}