{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:T55M4OFHVXXSJBWL4UF7JTWGOM","short_pith_number":"pith:T55M4OFH","canonical_record":{"source":{"id":"2408.10147","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T16:47:46Z","cross_cats_sorted":["cs.CL","cs.IT","math.IT","math.OC","stat.ML"],"title_canon_sha256":"09a4ce0abc2cf158fd9d8f87980ee3840049f5305a041df66074a5d21367d5cb","abstract_canon_sha256":"50e202b55586e383c2bbf7086c5e258d9454cf259e44f6475cebd617daaeb501"},"schema_version":"1.0"},"canonical_sha256":"9f7ace38a7adef2486cbe50bf4cec673029de4b69a9f00fcb1e8719d79e3d229","source":{"kind":"arxiv","id":"2408.10147","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10147","created_at":"2026-07-05T09:11:48Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10147v2","created_at":"2026-07-05T09:11:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10147","created_at":"2026-07-05T09:11:48Z"},{"alias_kind":"pith_short_12","alias_value":"T55M4OFHVXXS","created_at":"2026-07-05T09:11:48Z"},{"alias_kind":"pith_short_16","alias_value":"T55M4OFHVXXSJBWL","created_at":"2026-07-05T09:11:48Z"},{"alias_kind":"pith_short_8","alias_value":"T55M4OFH","created_at":"2026-07-05T09:11:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:T55M4OFHVXXSJBWL4UF7JTWGOM","target":"record","payload":{"canonical_record":{"source":{"id":"2408.10147","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T16:47:46Z","cross_cats_sorted":["cs.CL","cs.IT","math.IT","math.OC","stat.ML"],"title_canon_sha256":"09a4ce0abc2cf158fd9d8f87980ee3840049f5305a041df66074a5d21367d5cb","abstract_canon_sha256":"50e202b55586e383c2bbf7086c5e258d9454cf259e44f6475cebd617daaeb501"},"schema_version":"1.0"},"canonical_sha256":"9f7ace38a7adef2486cbe50bf4cec673029de4b69a9f00fcb1e8719d79e3d229","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:48.042807Z","signature_b64":"NXxQ0pjgmdutjFD5NpRvG/x0tzD1WWnJfrCQHFT0Bl3fVf/9WfKkiWUvcYtCIZQtqC8CPH0ORDd5E4U0HQMXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f7ace38a7adef2486cbe50bf4cec673029de4b69a9f00fcb1e8719d79e3d229","last_reissued_at":"2026-07-05T09:11:48.042321Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:48.042321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.10147","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:11:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9ueP1tT+3x0Wf2JArALA45urxu+4bleEJGCg3pqNVvjobWB5Sh3bDJe+yFhmQtM/uA7q/WbVRrq8y6qWlHVACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:49:22.067079Z"},"content_sha256":"16bb8facd2a9ed2cc58130ec4b004dc5f37b82e01f3a7c340f8a5fbffe7ea7fb","schema_version":"1.0","event_id":"sha256:16bb8facd2a9ed2cc58130ec4b004dc5f37b82e01f3a7c340f8a5fbffe7ea7fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:T55M4OFHVXXSJBWL4UF7JTWGOM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"In-Context Learning with Representations: Contextual Generalization of Trained Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IT","math.IT","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Tong Yang, Yingbin Liang, Yuejie Chi, Yu Huang","submitted_at":"2024-08-19T16:47:46Z","abstract_excerpt":"In-context learning (ICL) refers to a remarkable capability of pretrained large language models, which can learn a new task given a few examples during inference. However, theoretical understanding of ICL is largely under-explored, particularly whether transformers can be trained to generalize to unseen examples in a prompt, which will require the model to acquire contextual knowledge of the prompt for generalization. This paper investigates the training dynamics of transformers by gradient descent through the lens of non-linear regression tasks. The contextual generalization here can be attai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10147","kind":"arxiv","version":2},"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/2408.10147/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":"2026-07-05T09:11:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ydPo1MIgccJ4bqnCtDHAXXWQT2o5QHaEYeBMEeWsrnorNDY0ViT3opDLIG/Htt8IYcXf+PMUJ0lRFqwhEZ7kCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:49:22.067683Z"},"content_sha256":"4d3805d2646681e8b7aacb5d5256e4d431fb63e29b0fa6d49ae17da6e59dc141","schema_version":"1.0","event_id":"sha256:4d3805d2646681e8b7aacb5d5256e4d431fb63e29b0fa6d49ae17da6e59dc141"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T55M4OFHVXXSJBWL4UF7JTWGOM/bundle.json","state_url":"https://pith.science/pith/T55M4OFHVXXSJBWL4UF7JTWGOM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T55M4OFHVXXSJBWL4UF7JTWGOM/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":"2026-08-10T18:49:22Z","links":{"resolver":"https://pith.science/pith/T55M4OFHVXXSJBWL4UF7JTWGOM","bundle":"https://pith.science/pith/T55M4OFHVXXSJBWL4UF7JTWGOM/bundle.json","state":"https://pith.science/pith/T55M4OFHVXXSJBWL4UF7JTWGOM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T55M4OFHVXXSJBWL4UF7JTWGOM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T55M4OFHVXXSJBWL4UF7JTWGOM","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":"50e202b55586e383c2bbf7086c5e258d9454cf259e44f6475cebd617daaeb501","cross_cats_sorted":["cs.CL","cs.IT","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T16:47:46Z","title_canon_sha256":"09a4ce0abc2cf158fd9d8f87980ee3840049f5305a041df66074a5d21367d5cb"},"schema_version":"1.0","source":{"id":"2408.10147","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10147","created_at":"2026-07-05T09:11:48Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10147v2","created_at":"2026-07-05T09:11:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10147","created_at":"2026-07-05T09:11:48Z"},{"alias_kind":"pith_short_12","alias_value":"T55M4OFHVXXS","created_at":"2026-07-05T09:11:48Z"},{"alias_kind":"pith_short_16","alias_value":"T55M4OFHVXXSJBWL","created_at":"2026-07-05T09:11:48Z"},{"alias_kind":"pith_short_8","alias_value":"T55M4OFH","created_at":"2026-07-05T09:11:48Z"}],"graph_snapshots":[{"event_id":"sha256:4d3805d2646681e8b7aacb5d5256e4d431fb63e29b0fa6d49ae17da6e59dc141","target":"graph","created_at":"2026-07-05T09:11:48Z","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/2408.10147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In-context learning (ICL) refers to a remarkable capability of pretrained large language models, which can learn a new task given a few examples during inference. However, theoretical understanding of ICL is largely under-explored, particularly whether transformers can be trained to generalize to unseen examples in a prompt, which will require the model to acquire contextual knowledge of the prompt for generalization. This paper investigates the training dynamics of transformers by gradient descent through the lens of non-linear regression tasks. The contextual generalization here can be attai","authors_text":"Tong Yang, Yingbin Liang, Yuejie Chi, Yu Huang","cross_cats":["cs.CL","cs.IT","math.IT","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T16:47:46Z","title":"In-Context Learning with Representations: Contextual Generalization of Trained Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10147","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":"sha256:16bb8facd2a9ed2cc58130ec4b004dc5f37b82e01f3a7c340f8a5fbffe7ea7fb","target":"record","created_at":"2026-07-05T09:11:48Z","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":"50e202b55586e383c2bbf7086c5e258d9454cf259e44f6475cebd617daaeb501","cross_cats_sorted":["cs.CL","cs.IT","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-19T16:47:46Z","title_canon_sha256":"09a4ce0abc2cf158fd9d8f87980ee3840049f5305a041df66074a5d21367d5cb"},"schema_version":"1.0","source":{"id":"2408.10147","kind":"arxiv","version":2}},"canonical_sha256":"9f7ace38a7adef2486cbe50bf4cec673029de4b69a9f00fcb1e8719d79e3d229","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f7ace38a7adef2486cbe50bf4cec673029de4b69a9f00fcb1e8719d79e3d229","first_computed_at":"2026-07-05T09:11:48.042321Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:11:48.042321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NXxQ0pjgmdutjFD5NpRvG/x0tzD1WWnJfrCQHFT0Bl3fVf/9WfKkiWUvcYtCIZQtqC8CPH0ORDd5E4U0HQMXBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:11:48.042807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10147","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16bb8facd2a9ed2cc58130ec4b004dc5f37b82e01f3a7c340f8a5fbffe7ea7fb","sha256:4d3805d2646681e8b7aacb5d5256e4d431fb63e29b0fa6d49ae17da6e59dc141"],"state_sha256":"fa4994be839c6613c2c23d8b7a85082638fa0c14448dd4a6662554741816b761"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QgeW5qkyaU2IaOuFIWoi7NxWhh1SzKWkGw/s4MbWGgvww9okBo/50TS28W5Wxwti3YC+yQ2kbaMLohdEdQn9AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:49:22.071926Z","bundle_sha256":"441b48d2e0ecf606ff723f4690087ae5b8c85a92d6cc12a4199b2312f39251f7"}}