{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BKVPYDMBARKNTNKKREA6FZCWV5","short_pith_number":"pith:BKVPYDMB","canonical_record":{"source":{"id":"2307.15936","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-29T09:22:54Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"e363eb8c2fd8d0c7abea2cd4eaf2ab1a15b202156ad746f8ca935f4751123585","abstract_canon_sha256":"fab594f2c5557405b2d9654fecab1c8afd0c3e94f3c3f39990a2c1931161fea4"},"schema_version":"1.0"},"canonical_sha256":"0aaafc0d810454d9b54a8901e2e456af498d89440f2263dacf5d03df38d7bd56","source":{"kind":"arxiv","id":"2307.15936","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.15936","created_at":"2026-07-05T07:09:00Z"},{"alias_kind":"arxiv_version","alias_value":"2307.15936v2","created_at":"2026-07-05T07:09:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15936","created_at":"2026-07-05T07:09:00Z"},{"alias_kind":"pith_short_12","alias_value":"BKVPYDMBARKN","created_at":"2026-07-05T07:09:00Z"},{"alias_kind":"pith_short_16","alias_value":"BKVPYDMBARKNTNKK","created_at":"2026-07-05T07:09:00Z"},{"alias_kind":"pith_short_8","alias_value":"BKVPYDMB","created_at":"2026-07-05T07:09:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BKVPYDMBARKNTNKKREA6FZCWV5","target":"record","payload":{"canonical_record":{"source":{"id":"2307.15936","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-29T09:22:54Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"e363eb8c2fd8d0c7abea2cd4eaf2ab1a15b202156ad746f8ca935f4751123585","abstract_canon_sha256":"fab594f2c5557405b2d9654fecab1c8afd0c3e94f3c3f39990a2c1931161fea4"},"schema_version":"1.0"},"canonical_sha256":"0aaafc0d810454d9b54a8901e2e456af498d89440f2263dacf5d03df38d7bd56","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:00.353781Z","signature_b64":"XppgT6N/Lk3zq2hl6m6Ar0+t4J/cC/evty2G7pyF+Ody/2FycMTtAUje3oCtae2t1/B8U2baQqN9AallNsL+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0aaafc0d810454d9b54a8901e2e456af498d89440f2263dacf5d03df38d7bd56","last_reissued_at":"2026-07-05T07:09:00.353326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:00.353326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.15936","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":"2026-07-05T07:09:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MlpfwVNZfJ9uVn3aPIousQ9jHfKTHVaOGmia79C9NHfeLcTk3tKCZGzjRwdAqhri2rzmKwGwi+Vp+UUOHV19Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:28:16.233590Z"},"content_sha256":"9ff0faebbb625baedfef40354e4e46bb06b04d347380938b5f7b376f169d71bc","schema_version":"1.0","event_id":"sha256:9ff0faebbb625baedfef40354e4e46bb06b04d347380938b5f7b376f169d71bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BKVPYDMBARKNTNKKREA6FZCWV5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Theory for Emergence of Complex Skills in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anirudh Goyal, Sanjeev Arora","submitted_at":"2023-07-29T09:22:54Z","abstract_excerpt":"A major driver of AI products today is the fact that new skills emerge in language models when their parameter set and training corpora are scaled up. This phenomenon is poorly understood, and a mechanistic explanation via mathematical analysis of gradient-based training seems difficult. The current paper takes a different approach, analysing emergence using the famous (and empirical) Scaling Laws of LLMs and a simple statistical framework. Contributions include: (a) A statistical framework that relates cross-entropy loss of LLMs to competence on the basic skills that underlie language tasks. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15936","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/2307.15936/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":"2026-07-05T07:09:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8EVJkogtcJ9nflBZ1PYxlovmU9ewpRxTKXFsY4SE8xD9fEY3cXLNQsHM1+aZt05zH1tgh3sEUGSAL2Z5/GTbAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:28:16.234370Z"},"content_sha256":"f790c16dcdf469c19072f1eaa4ef6787cd8b40764356dd189ea251b12e93434c","schema_version":"1.0","event_id":"sha256:f790c16dcdf469c19072f1eaa4ef6787cd8b40764356dd189ea251b12e93434c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BKVPYDMBARKNTNKKREA6FZCWV5/bundle.json","state_url":"https://pith.science/pith/BKVPYDMBARKNTNKKREA6FZCWV5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BKVPYDMBARKNTNKKREA6FZCWV5/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":"2026-08-10T00:28:16Z","links":{"resolver":"https://pith.science/pith/BKVPYDMBARKNTNKKREA6FZCWV5","bundle":"https://pith.science/pith/BKVPYDMBARKNTNKKREA6FZCWV5/bundle.json","state":"https://pith.science/pith/BKVPYDMBARKNTNKKREA6FZCWV5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BKVPYDMBARKNTNKKREA6FZCWV5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BKVPYDMBARKNTNKKREA6FZCWV5","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":"fab594f2c5557405b2d9654fecab1c8afd0c3e94f3c3f39990a2c1931161fea4","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-29T09:22:54Z","title_canon_sha256":"e363eb8c2fd8d0c7abea2cd4eaf2ab1a15b202156ad746f8ca935f4751123585"},"schema_version":"1.0","source":{"id":"2307.15936","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.15936","created_at":"2026-07-05T07:09:00Z"},{"alias_kind":"arxiv_version","alias_value":"2307.15936v2","created_at":"2026-07-05T07:09:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15936","created_at":"2026-07-05T07:09:00Z"},{"alias_kind":"pith_short_12","alias_value":"BKVPYDMBARKN","created_at":"2026-07-05T07:09:00Z"},{"alias_kind":"pith_short_16","alias_value":"BKVPYDMBARKNTNKK","created_at":"2026-07-05T07:09:00Z"},{"alias_kind":"pith_short_8","alias_value":"BKVPYDMB","created_at":"2026-07-05T07:09:00Z"}],"graph_snapshots":[{"event_id":"sha256:f790c16dcdf469c19072f1eaa4ef6787cd8b40764356dd189ea251b12e93434c","target":"graph","created_at":"2026-07-05T07:09:00Z","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/2307.15936/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A major driver of AI products today is the fact that new skills emerge in language models when their parameter set and training corpora are scaled up. This phenomenon is poorly understood, and a mechanistic explanation via mathematical analysis of gradient-based training seems difficult. The current paper takes a different approach, analysing emergence using the famous (and empirical) Scaling Laws of LLMs and a simple statistical framework. Contributions include: (a) A statistical framework that relates cross-entropy loss of LLMs to competence on the basic skills that underlie language tasks. ","authors_text":"Anirudh Goyal, Sanjeev Arora","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-29T09:22:54Z","title":"A Theory for Emergence of Complex Skills in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15936","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":"sha256:9ff0faebbb625baedfef40354e4e46bb06b04d347380938b5f7b376f169d71bc","target":"record","created_at":"2026-07-05T07:09:00Z","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":"fab594f2c5557405b2d9654fecab1c8afd0c3e94f3c3f39990a2c1931161fea4","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-29T09:22:54Z","title_canon_sha256":"e363eb8c2fd8d0c7abea2cd4eaf2ab1a15b202156ad746f8ca935f4751123585"},"schema_version":"1.0","source":{"id":"2307.15936","kind":"arxiv","version":2}},"canonical_sha256":"0aaafc0d810454d9b54a8901e2e456af498d89440f2263dacf5d03df38d7bd56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0aaafc0d810454d9b54a8901e2e456af498d89440f2263dacf5d03df38d7bd56","first_computed_at":"2026-07-05T07:09:00.353326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:09:00.353326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XppgT6N/Lk3zq2hl6m6Ar0+t4J/cC/evty2G7pyF+Ody/2FycMTtAUje3oCtae2t1/B8U2baQqN9AallNsL+Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:09:00.353781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.15936","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ff0faebbb625baedfef40354e4e46bb06b04d347380938b5f7b376f169d71bc","sha256:f790c16dcdf469c19072f1eaa4ef6787cd8b40764356dd189ea251b12e93434c"],"state_sha256":"1866c7d534931ee396e7b294c366b22ba0352d1b5975d8b704dbdd6adfbe679e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aeJCZmtKU29h4WdAJG7Pwb5+y8tzbW0EgTKE2tgTdwEu42a1yWGNv1crLqH696TBjcIVeOfeywcbsy/C1MpGAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T00:28:16.239925Z","bundle_sha256":"ffe1b08f1a4c57736282cdb429c1f0ac17d41c7c8a64ad929ad4c21ae326ccf1"}}