{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZUBCXTJFLJZPN24ERRBDC3YWZZ","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":"4980a5da7803f64b34fb1846338acb7626898b4701be5f05ea96bc0ac82627c3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T20:40:48Z","title_canon_sha256":"a6424b9db8cecb69994698f964590bcecba31ec028d920b5c0ec624f3fb12f24"},"schema_version":"1.0","source":{"id":"2402.12530","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12530","created_at":"2026-07-05T07:47:12Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12530v1","created_at":"2026-07-05T07:47:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12530","created_at":"2026-07-05T07:47:12Z"},{"alias_kind":"pith_short_12","alias_value":"ZUBCXTJFLJZP","created_at":"2026-07-05T07:47:12Z"},{"alias_kind":"pith_short_16","alias_value":"ZUBCXTJFLJZPN24E","created_at":"2026-07-05T07:47:12Z"},{"alias_kind":"pith_short_8","alias_value":"ZUBCXTJF","created_at":"2026-07-05T07:47:12Z"}],"graph_snapshots":[{"event_id":"sha256:92787c7d829e06ba9f7f558f7fa0e572a17ca2460cad5811156e3d815f1025a7","target":"graph","created_at":"2026-07-05T07:47:12Z","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/2402.12530/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained language models (LMs) are capable of in-context learning (ICL): they can adapt to a task with only a few examples given in the prompt without any parameter update. However, it is unclear where this capability comes from as there is a stark distribution shift between pre-training text and ICL prompts. In this work, we study what patterns of the pre-training data contribute to ICL. We find that LMs' ICL ability depends on $\\textit{parallel structures}$ in the pre-training data -- pairs of phrases following similar templates in the same context window. Specifically, we detect parallel","authors_text":"Chen Zhao, He He, Kathleen McKeown, Yanda Chen, Zhou Yu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T20:40:48Z","title":"Parallel Structures in Pre-training Data Yield In-Context Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12530","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":"sha256:7aa7808628c547a90dd2d6dc0c17bb8caa214abbfad2022049c0ea60a01344ff","target":"record","created_at":"2026-07-05T07:47:12Z","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":"4980a5da7803f64b34fb1846338acb7626898b4701be5f05ea96bc0ac82627c3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T20:40:48Z","title_canon_sha256":"a6424b9db8cecb69994698f964590bcecba31ec028d920b5c0ec624f3fb12f24"},"schema_version":"1.0","source":{"id":"2402.12530","kind":"arxiv","version":1}},"canonical_sha256":"cd022bcd255a72f6eb848c42316f16ce5e002219f6aefbd6f73c2a2d79b10476","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd022bcd255a72f6eb848c42316f16ce5e002219f6aefbd6f73c2a2d79b10476","first_computed_at":"2026-07-05T07:47:12.653902Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:12.653902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WEg+/M54ULw0UPO5V8fKQbRehnmLk5QZll0z8dNJ/uE/bjiS+ca0av6Z1NDgI/k+UwC9kYP2Qkk1ioX6LcpgDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:12.654311Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12530","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7aa7808628c547a90dd2d6dc0c17bb8caa214abbfad2022049c0ea60a01344ff","sha256:92787c7d829e06ba9f7f558f7fa0e572a17ca2460cad5811156e3d815f1025a7"],"state_sha256":"bcee5a89033bb47db04e1fdcbca098681424f60931c17d935b4e0773ea135a95"}