{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:M7JED7IX4VETGUHMA2AN4A5WKQ","short_pith_number":"pith:M7JED7IX","canonical_record":{"source":{"id":"2303.07971","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-14T15:24:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c63a22c3ebdcf663cc4be5ed3010f6d1c1f721905bf0aa4e80e8499f86048e42","abstract_canon_sha256":"163f09cbf029116339b548d1ee2ac3d89447c5b5742c8166625a7d361f129549"},"schema_version":"1.0"},"canonical_sha256":"67d241fd17e5493350ec0680de03b654231ad6c4617f6e4e5f6071b6330d625c","source":{"kind":"arxiv","id":"2303.07971","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.07971","created_at":"2026-07-05T05:51:13Z"},{"alias_kind":"arxiv_version","alias_value":"2303.07971v1","created_at":"2026-07-05T05:51:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07971","created_at":"2026-07-05T05:51:13Z"},{"alias_kind":"pith_short_12","alias_value":"M7JED7IX4VET","created_at":"2026-07-05T05:51:13Z"},{"alias_kind":"pith_short_16","alias_value":"M7JED7IX4VETGUHM","created_at":"2026-07-05T05:51:13Z"},{"alias_kind":"pith_short_8","alias_value":"M7JED7IX","created_at":"2026-07-05T05:51:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:M7JED7IX4VETGUHMA2AN4A5WKQ","target":"record","payload":{"canonical_record":{"source":{"id":"2303.07971","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-14T15:24:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c63a22c3ebdcf663cc4be5ed3010f6d1c1f721905bf0aa4e80e8499f86048e42","abstract_canon_sha256":"163f09cbf029116339b548d1ee2ac3d89447c5b5742c8166625a7d361f129549"},"schema_version":"1.0"},"canonical_sha256":"67d241fd17e5493350ec0680de03b654231ad6c4617f6e4e5f6071b6330d625c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:13.547657Z","signature_b64":"2VssRosZ+IhWuKXxbUH4x7AbwUxosMwspYioC5yn4tQHBJPavi4p2YmHmeSuyMvPwK1nm20B2BtcaDQTZ64pAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67d241fd17e5493350ec0680de03b654231ad6c4617f6e4e5f6071b6330d625c","last_reissued_at":"2026-07-05T05:51:13.547125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:13.547125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.07971","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":"2026-07-05T05:51:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sGttY6pH1hyz2PRU+Pw4th6BLW1WK1VFU9WCpMdfvwqF8UgcmP/14cw4d30ZWeFI79oGiW9NobqWBz9+eHaYDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:28:45.591531Z"},"content_sha256":"ca3e78be6473e592ddf281236c9c4d1e87a965be27c8bf12cb54415578615045","schema_version":"1.0","event_id":"sha256:ca3e78be6473e592ddf281236c9c4d1e87a965be27c8bf12cb54415578615045"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:M7JED7IX4VETGUHMA2AN4A5WKQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Theory of Emergent In-Context Learning as Implicit Structure Induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Michael Hahn, Navin Goyal","submitted_at":"2023-03-14T15:24:05Z","abstract_excerpt":"Scaling large language models (LLMs) leads to an emergent capacity to learn in-context from example demonstrations. Despite progress, theoretical understanding of this phenomenon remains limited. We argue that in-context learning relies on recombination of compositional operations found in natural language data. We derive an information-theoretic bound showing how in-context learning abilities arise from generic next-token prediction when the pretraining distribution has sufficient amounts of compositional structure, under linguistically motivated assumptions. A second bound provides a theoret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07971","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/2303.07971/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":"2026-07-05T05:51:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u0erq1fIxXOH7fQG3sL6wH2rsA41u75qlGT/nkO5a9Tf0/ViJZP4lQxBzilTrlTY5scjKmF1mN4PDnLd5YpCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:28:45.592057Z"},"content_sha256":"aaf4faf18b6ff94ad18d2bf11250e9713ab7915b209ea1c35f5be8f5b9a6efed","schema_version":"1.0","event_id":"sha256:aaf4faf18b6ff94ad18d2bf11250e9713ab7915b209ea1c35f5be8f5b9a6efed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M7JED7IX4VETGUHMA2AN4A5WKQ/bundle.json","state_url":"https://pith.science/pith/M7JED7IX4VETGUHMA2AN4A5WKQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M7JED7IX4VETGUHMA2AN4A5WKQ/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":"2026-08-07T01:28:45Z","links":{"resolver":"https://pith.science/pith/M7JED7IX4VETGUHMA2AN4A5WKQ","bundle":"https://pith.science/pith/M7JED7IX4VETGUHMA2AN4A5WKQ/bundle.json","state":"https://pith.science/pith/M7JED7IX4VETGUHMA2AN4A5WKQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M7JED7IX4VETGUHMA2AN4A5WKQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:M7JED7IX4VETGUHMA2AN4A5WKQ","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":"163f09cbf029116339b548d1ee2ac3d89447c5b5742c8166625a7d361f129549","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-14T15:24:05Z","title_canon_sha256":"c63a22c3ebdcf663cc4be5ed3010f6d1c1f721905bf0aa4e80e8499f86048e42"},"schema_version":"1.0","source":{"id":"2303.07971","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.07971","created_at":"2026-07-05T05:51:13Z"},{"alias_kind":"arxiv_version","alias_value":"2303.07971v1","created_at":"2026-07-05T05:51:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07971","created_at":"2026-07-05T05:51:13Z"},{"alias_kind":"pith_short_12","alias_value":"M7JED7IX4VET","created_at":"2026-07-05T05:51:13Z"},{"alias_kind":"pith_short_16","alias_value":"M7JED7IX4VETGUHM","created_at":"2026-07-05T05:51:13Z"},{"alias_kind":"pith_short_8","alias_value":"M7JED7IX","created_at":"2026-07-05T05:51:13Z"}],"graph_snapshots":[{"event_id":"sha256:aaf4faf18b6ff94ad18d2bf11250e9713ab7915b209ea1c35f5be8f5b9a6efed","target":"graph","created_at":"2026-07-05T05:51:13Z","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/2303.07971/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling large language models (LLMs) leads to an emergent capacity to learn in-context from example demonstrations. Despite progress, theoretical understanding of this phenomenon remains limited. We argue that in-context learning relies on recombination of compositional operations found in natural language data. We derive an information-theoretic bound showing how in-context learning abilities arise from generic next-token prediction when the pretraining distribution has sufficient amounts of compositional structure, under linguistically motivated assumptions. A second bound provides a theoret","authors_text":"Michael Hahn, Navin Goyal","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-14T15:24:05Z","title":"A Theory of Emergent In-Context Learning as Implicit Structure Induction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07971","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:ca3e78be6473e592ddf281236c9c4d1e87a965be27c8bf12cb54415578615045","target":"record","created_at":"2026-07-05T05:51:13Z","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":"163f09cbf029116339b548d1ee2ac3d89447c5b5742c8166625a7d361f129549","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-14T15:24:05Z","title_canon_sha256":"c63a22c3ebdcf663cc4be5ed3010f6d1c1f721905bf0aa4e80e8499f86048e42"},"schema_version":"1.0","source":{"id":"2303.07971","kind":"arxiv","version":1}},"canonical_sha256":"67d241fd17e5493350ec0680de03b654231ad6c4617f6e4e5f6071b6330d625c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67d241fd17e5493350ec0680de03b654231ad6c4617f6e4e5f6071b6330d625c","first_computed_at":"2026-07-05T05:51:13.547125Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:51:13.547125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2VssRosZ+IhWuKXxbUH4x7AbwUxosMwspYioC5yn4tQHBJPavi4p2YmHmeSuyMvPwK1nm20B2BtcaDQTZ64pAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:51:13.547657Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.07971","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca3e78be6473e592ddf281236c9c4d1e87a965be27c8bf12cb54415578615045","sha256:aaf4faf18b6ff94ad18d2bf11250e9713ab7915b209ea1c35f5be8f5b9a6efed"],"state_sha256":"ce9e9e728266d9e6145bd39f263d96fc5feb25132cf869069ee887ecb6860896"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XnB9svlO02FdOPDrc7+V05CRxf4tFALo0Iou+0/FWq+ONKYkG0ZWBg5x2h8sBd1sMjxkPLoB0gb5fV8+AFbiCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:28:45.598176Z","bundle_sha256":"82df47b27ac3c398caad15e608fec2887499ed6fad63970eff29c686e9a73629"}}