{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QE6QO4FGJTAICJUIBD4UKTURFP","short_pith_number":"pith:QE6QO4FG","schema_version":"1.0","canonical_sha256":"813d0770a64cc081268808f9454e912bc470d789ab47040319c70f2432b63426","source":{"kind":"arxiv","id":"2304.09960","version":3},"attestation_state":"computed","paper":{"title":"A Latent Space Theory for Emergent Abilities in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hui Jiang","submitted_at":"2023-04-19T20:45:01Z","abstract_excerpt":"Languages are not created randomly but rather to communicate information. There is a strong association between languages and their underlying meanings, resulting in a sparse joint distribution that is heavily peaked according to their correlations. Moreover, these peak values happen to match with the marginal distribution of languages due to the sparsity. With the advent of LLMs trained on big data and large models, we can now precisely assess the marginal distribution of languages, providing a convenient means of exploring the sparse structures in the joint distribution for effective inferen"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2304.09960","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-19T20:45:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2a687c4943f6c7a092bcd8c20238ada84baa6c1cef2bac70b1c678fd30cc95e2","abstract_canon_sha256":"8b322ef687566043725c436b2353f62e9e06dbbb9efd740d01c12a64499410b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:28.886091Z","signature_b64":"JvH7HisbRcxSQdf9HQmMNfv61eWKsfRTklh3uvw1iVg79drCxH2e6R9a3sSsVFgyAGI/n02VLwWTYuo6nux9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"813d0770a64cc081268808f9454e912bc470d789ab47040319c70f2432b63426","last_reissued_at":"2026-07-05T06:50:28.885732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:28.885732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Latent Space Theory for Emergent Abilities in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hui Jiang","submitted_at":"2023-04-19T20:45:01Z","abstract_excerpt":"Languages are not created randomly but rather to communicate information. There is a strong association between languages and their underlying meanings, resulting in a sparse joint distribution that is heavily peaked according to their correlations. Moreover, these peak values happen to match with the marginal distribution of languages due to the sparsity. With the advent of LLMs trained on big data and large models, we can now precisely assess the marginal distribution of languages, providing a convenient means of exploring the sparse structures in the joint distribution for effective inferen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09960","kind":"arxiv","version":3},"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/2304.09960/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2304.09960","created_at":"2026-07-05T06:50:28.885788+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.09960v3","created_at":"2026-07-05T06:50:28.885788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09960","created_at":"2026-07-05T06:50:28.885788+00:00"},{"alias_kind":"pith_short_12","alias_value":"QE6QO4FGJTAI","created_at":"2026-07-05T06:50:28.885788+00:00"},{"alias_kind":"pith_short_16","alias_value":"QE6QO4FGJTAICJUI","created_at":"2026-07-05T06:50:28.885788+00:00"},{"alias_kind":"pith_short_8","alias_value":"QE6QO4FG","created_at":"2026-07-05T06:50:28.885788+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12316","citing_title":"Autoregressive Learning in Joint KL: Sharp Oracle Bounds and Lower Bounds","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2301.00234","citing_title":"A Survey on In-context Learning","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QE6QO4FGJTAICJUIBD4UKTURFP","json":"https://pith.science/pith/QE6QO4FGJTAICJUIBD4UKTURFP.json","graph_json":"https://pith.science/api/pith-number/QE6QO4FGJTAICJUIBD4UKTURFP/graph.json","events_json":"https://pith.science/api/pith-number/QE6QO4FGJTAICJUIBD4UKTURFP/events.json","paper":"https://pith.science/paper/QE6QO4FG"},"agent_actions":{"view_html":"https://pith.science/pith/QE6QO4FGJTAICJUIBD4UKTURFP","download_json":"https://pith.science/pith/QE6QO4FGJTAICJUIBD4UKTURFP.json","view_paper":"https://pith.science/paper/QE6QO4FG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.09960&json=true","fetch_graph":"https://pith.science/api/pith-number/QE6QO4FGJTAICJUIBD4UKTURFP/graph.json","fetch_events":"https://pith.science/api/pith-number/QE6QO4FGJTAICJUIBD4UKTURFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QE6QO4FGJTAICJUIBD4UKTURFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QE6QO4FGJTAICJUIBD4UKTURFP/action/storage_attestation","attest_author":"https://pith.science/pith/QE6QO4FGJTAICJUIBD4UKTURFP/action/author_attestation","sign_citation":"https://pith.science/pith/QE6QO4FGJTAICJUIBD4UKTURFP/action/citation_signature","submit_replication":"https://pith.science/pith/QE6QO4FGJTAICJUIBD4UKTURFP/action/replication_record"}},"created_at":"2026-07-05T06:50:28.885788+00:00","updated_at":"2026-07-05T06:50:28.885788+00:00"}