{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JK37LOJKXCOFUX6HXQYACHN4HE","short_pith_number":"pith:JK37LOJK","canonical_record":{"source":{"id":"2410.21698","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-29T03:27:56Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"88e431ad16e2a11bc53cafa7621c59a3f82c9fc7b434643a913727d94f0b4d92","abstract_canon_sha256":"8395c8fc76d53666c3fcb41d745982b45a6c84c3b9004859dca50c05d2a87f97"},"schema_version":"1.0"},"canonical_sha256":"4ab7f5b92ab89c5a5fc7bc30011dbc3902668c57cc139eec1909de36063d9988","source":{"kind":"arxiv","id":"2410.21698","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21698","created_at":"2026-07-05T09:27:31Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21698v1","created_at":"2026-07-05T09:27:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21698","created_at":"2026-07-05T09:27:31Z"},{"alias_kind":"pith_short_12","alias_value":"JK37LOJKXCOF","created_at":"2026-07-05T09:27:31Z"},{"alias_kind":"pith_short_16","alias_value":"JK37LOJKXCOFUX6H","created_at":"2026-07-05T09:27:31Z"},{"alias_kind":"pith_short_8","alias_value":"JK37LOJK","created_at":"2026-07-05T09:27:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JK37LOJKXCOFUX6HXQYACHN4HE","target":"record","payload":{"canonical_record":{"source":{"id":"2410.21698","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-29T03:27:56Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"88e431ad16e2a11bc53cafa7621c59a3f82c9fc7b434643a913727d94f0b4d92","abstract_canon_sha256":"8395c8fc76d53666c3fcb41d745982b45a6c84c3b9004859dca50c05d2a87f97"},"schema_version":"1.0"},"canonical_sha256":"4ab7f5b92ab89c5a5fc7bc30011dbc3902668c57cc139eec1909de36063d9988","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:31.918166Z","signature_b64":"ysYNOeteV5Eox/T05B3+qTnGzHzSfjWle3nC6FqqcW+Tsdw2ZZF0Q26SKw2LdhryC/1AWBLrXaOGVeW2OJohDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ab7f5b92ab89c5a5fc7bc30011dbc3902668c57cc139eec1909de36063d9988","last_reissued_at":"2026-07-05T09:27:31.917558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:31.917558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.21698","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":"2026-07-05T09:27:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4HutYwkfMiuiu+Le4ACinshRiOfDSdJPGEtx9zJyj3fD8uRdIbVDQJ9B22cMY3g6aDbo9SVO+dWEhMc9IBuQCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:07:45.981871Z"},"content_sha256":"6b52745b194a1e8999d1f655dac726ade359986ea07497db146a36fff023e31d","schema_version":"1.0","event_id":"sha256:6b52745b194a1e8999d1f655dac726ade359986ea07497db146a36fff023e31d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JK37LOJKXCOFUX6HXQYACHN4HE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Role of Depth and Looping for In-Context Learning with Task Diversity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Khashayar Gatmiry, Nikunj Saunshi, Sanjiv Kumar, Sashank J. Reddi, Stefanie Jegelka","submitted_at":"2024-10-29T03:27:56Z","abstract_excerpt":"The intriguing in-context learning (ICL) abilities of deep Transformer models have lately garnered significant attention. By studying in-context linear regression on unimodal Gaussian data, recent empirical and theoretical works have argued that ICL emerges from Transformers' abilities to simulate learning algorithms like gradient descent. However, these works fail to capture the remarkable ability of Transformers to learn multiple tasks in context. To this end, we study in-context learning for linear regression with diverse tasks, characterized by data covariance matrices with condition numbe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21698","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/2410.21698/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":"2026-07-05T09:27:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y9yqq/iK4B71G3Hx4pq+J381KtSKMS8kNKP/XNBFW/ONDKyq53QrzFkWOWqqFX+ZRGONYek1/AdCwCPojQ6SBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T17:07:45.982477Z"},"content_sha256":"d743ba7da6b09fd89b15104e7c3c0e5fdad043db8d72120f8f835f05cdc89a62","schema_version":"1.0","event_id":"sha256:d743ba7da6b09fd89b15104e7c3c0e5fdad043db8d72120f8f835f05cdc89a62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JK37LOJKXCOFUX6HXQYACHN4HE/bundle.json","state_url":"https://pith.science/pith/JK37LOJKXCOFUX6HXQYACHN4HE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JK37LOJKXCOFUX6HXQYACHN4HE/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":"2026-08-11T17:07:45Z","links":{"resolver":"https://pith.science/pith/JK37LOJKXCOFUX6HXQYACHN4HE","bundle":"https://pith.science/pith/JK37LOJKXCOFUX6HXQYACHN4HE/bundle.json","state":"https://pith.science/pith/JK37LOJKXCOFUX6HXQYACHN4HE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JK37LOJKXCOFUX6HXQYACHN4HE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JK37LOJKXCOFUX6HXQYACHN4HE","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":"8395c8fc76d53666c3fcb41d745982b45a6c84c3b9004859dca50c05d2a87f97","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-29T03:27:56Z","title_canon_sha256":"88e431ad16e2a11bc53cafa7621c59a3f82c9fc7b434643a913727d94f0b4d92"},"schema_version":"1.0","source":{"id":"2410.21698","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21698","created_at":"2026-07-05T09:27:31Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21698v1","created_at":"2026-07-05T09:27:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21698","created_at":"2026-07-05T09:27:31Z"},{"alias_kind":"pith_short_12","alias_value":"JK37LOJKXCOF","created_at":"2026-07-05T09:27:31Z"},{"alias_kind":"pith_short_16","alias_value":"JK37LOJKXCOFUX6H","created_at":"2026-07-05T09:27:31Z"},{"alias_kind":"pith_short_8","alias_value":"JK37LOJK","created_at":"2026-07-05T09:27:31Z"}],"graph_snapshots":[{"event_id":"sha256:d743ba7da6b09fd89b15104e7c3c0e5fdad043db8d72120f8f835f05cdc89a62","target":"graph","created_at":"2026-07-05T09:27:31Z","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/2410.21698/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The intriguing in-context learning (ICL) abilities of deep Transformer models have lately garnered significant attention. By studying in-context linear regression on unimodal Gaussian data, recent empirical and theoretical works have argued that ICL emerges from Transformers' abilities to simulate learning algorithms like gradient descent. However, these works fail to capture the remarkable ability of Transformers to learn multiple tasks in context. To this end, we study in-context learning for linear regression with diverse tasks, characterized by data covariance matrices with condition numbe","authors_text":"Khashayar Gatmiry, Nikunj Saunshi, Sanjiv Kumar, Sashank J. Reddi, Stefanie Jegelka","cross_cats":["math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-29T03:27:56Z","title":"On the Role of Depth and Looping for In-Context Learning with Task Diversity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21698","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":"sha256:6b52745b194a1e8999d1f655dac726ade359986ea07497db146a36fff023e31d","target":"record","created_at":"2026-07-05T09:27:31Z","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":"8395c8fc76d53666c3fcb41d745982b45a6c84c3b9004859dca50c05d2a87f97","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-29T03:27:56Z","title_canon_sha256":"88e431ad16e2a11bc53cafa7621c59a3f82c9fc7b434643a913727d94f0b4d92"},"schema_version":"1.0","source":{"id":"2410.21698","kind":"arxiv","version":1}},"canonical_sha256":"4ab7f5b92ab89c5a5fc7bc30011dbc3902668c57cc139eec1909de36063d9988","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ab7f5b92ab89c5a5fc7bc30011dbc3902668c57cc139eec1909de36063d9988","first_computed_at":"2026-07-05T09:27:31.917558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:31.917558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ysYNOeteV5Eox/T05B3+qTnGzHzSfjWle3nC6FqqcW+Tsdw2ZZF0Q26SKw2LdhryC/1AWBLrXaOGVeW2OJohDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:31.918166Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.21698","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b52745b194a1e8999d1f655dac726ade359986ea07497db146a36fff023e31d","sha256:d743ba7da6b09fd89b15104e7c3c0e5fdad043db8d72120f8f835f05cdc89a62"],"state_sha256":"8af5130cde92b20972d170b9bddc84b6c253c474a573763e3cde4b7486e6d0f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lvUsQ/fGKMxhNZA+Kpuq13WX+nX3LQO3eJIPlURitC4lv2vR464FTX4cMgfhJqz1h68S2anXvi3umHfVuazYBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T17:07:45.990067Z","bundle_sha256":"d3f753f18ff6d04503d684b3395e7c1b822063fb6ba63e5062e7599d81e5278d"}}