{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MXCIDTUU2NL3MO7FDZ6XWVT4MQ","short_pith_number":"pith:MXCIDTUU","schema_version":"1.0","canonical_sha256":"65c481ce94d357b63be51e7d7b567c64325c55546c2f94f5708cf9591ef08b5b","source":{"kind":"arxiv","id":"2402.02791","version":4},"attestation_state":"computed","paper":{"title":"PanGu-$\\pi$ Pro:Rethinking Optimization and Architecture for Tiny Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fangcheng Liu, Kai Han, Shangling Jui, Sichao Liu, Yehui Tang, Yi-Qi Hu, Yuchuan Tian, Yunhe Wang, Yunsheng Ni, Zheyuan Bai","submitted_at":"2024-02-05T07:59:38Z","abstract_excerpt":"The power of large language models (LLMs) has been demonstrated through numerous data and computing resources. However, the application of language models on mobile devices is facing huge challenge on the computation and memory costs, that is, tiny language models with high performance are urgently required. Limited by the highly complex training process, there are many details for optimizing language models that are seldom studied carefully. In this study, based on a tiny language model with 1B parameters, we carefully design a series of empirical study to analyze the effect of each component"},"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":"2402.02791","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-05T07:59:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e09555b050d520be54a83d7c800725bfffe175bf0e98362a6b9fb474b4c98cda","abstract_canon_sha256":"ba9d9e37b6f73fa96ff29621aedabea58df50e51aa8c863e59b1ef99092cc2cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:34.889323Z","signature_b64":"cTj0MUzTTzMClgXDbBUh6sR9lBq7DCoBneD6TzCDX/PTSksJeGxneDvahaivhBub+HXFmieWLGryzlVovqAVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65c481ce94d357b63be51e7d7b567c64325c55546c2f94f5708cf9591ef08b5b","last_reissued_at":"2026-07-05T10:43:34.888891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:34.888891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PanGu-$\\pi$ Pro:Rethinking Optimization and Architecture for Tiny Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fangcheng Liu, Kai Han, Shangling Jui, Sichao Liu, Yehui Tang, Yi-Qi Hu, Yuchuan Tian, Yunhe Wang, Yunsheng Ni, Zheyuan Bai","submitted_at":"2024-02-05T07:59:38Z","abstract_excerpt":"The power of large language models (LLMs) has been demonstrated through numerous data and computing resources. However, the application of language models on mobile devices is facing huge challenge on the computation and memory costs, that is, tiny language models with high performance are urgently required. Limited by the highly complex training process, there are many details for optimizing language models that are seldom studied carefully. In this study, based on a tiny language model with 1B parameters, we carefully design a series of empirical study to analyze the effect of each component"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02791","kind":"arxiv","version":4},"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/2402.02791/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":"2402.02791","created_at":"2026-07-05T10:43:34.888949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02791v4","created_at":"2026-07-05T10:43:34.888949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02791","created_at":"2026-07-05T10:43:34.888949+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXCIDTUU2NL3","created_at":"2026-07-05T10:43:34.888949+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXCIDTUU2NL3MO7F","created_at":"2026-07-05T10:43:34.888949+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXCIDTUU","created_at":"2026-07-05T10:43:34.888949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MXCIDTUU2NL3MO7FDZ6XWVT4MQ","json":"https://pith.science/pith/MXCIDTUU2NL3MO7FDZ6XWVT4MQ.json","graph_json":"https://pith.science/api/pith-number/MXCIDTUU2NL3MO7FDZ6XWVT4MQ/graph.json","events_json":"https://pith.science/api/pith-number/MXCIDTUU2NL3MO7FDZ6XWVT4MQ/events.json","paper":"https://pith.science/paper/MXCIDTUU"},"agent_actions":{"view_html":"https://pith.science/pith/MXCIDTUU2NL3MO7FDZ6XWVT4MQ","download_json":"https://pith.science/pith/MXCIDTUU2NL3MO7FDZ6XWVT4MQ.json","view_paper":"https://pith.science/paper/MXCIDTUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02791&json=true","fetch_graph":"https://pith.science/api/pith-number/MXCIDTUU2NL3MO7FDZ6XWVT4MQ/graph.json","fetch_events":"https://pith.science/api/pith-number/MXCIDTUU2NL3MO7FDZ6XWVT4MQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXCIDTUU2NL3MO7FDZ6XWVT4MQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXCIDTUU2NL3MO7FDZ6XWVT4MQ/action/storage_attestation","attest_author":"https://pith.science/pith/MXCIDTUU2NL3MO7FDZ6XWVT4MQ/action/author_attestation","sign_citation":"https://pith.science/pith/MXCIDTUU2NL3MO7FDZ6XWVT4MQ/action/citation_signature","submit_replication":"https://pith.science/pith/MXCIDTUU2NL3MO7FDZ6XWVT4MQ/action/replication_record"}},"created_at":"2026-07-05T10:43:34.888949+00:00","updated_at":"2026-07-05T10:43:34.888949+00:00"}