{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CLA4ZHBT6K5RTDCBJIYLJDMZPH","short_pith_number":"pith:CLA4ZHBT","canonical_record":{"source":{"id":"2304.06875","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-14T00:45:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4b132f02517da4a7688b248f1f0e734481293721f50e9a9d4b366ef30fd4ac66","abstract_canon_sha256":"1c6cf5bd277abef7f50ed568082ad66699729d9933b01646fb3bd133c01e9c51"},"schema_version":"1.0"},"canonical_sha256":"12c1cc9c33f2bb198c414a30b48d9979e1cf0b700f1057085fa882b8e8893db8","source":{"kind":"arxiv","id":"2304.06875","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.06875","created_at":"2026-07-05T08:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2304.06875v4","created_at":"2026-07-05T08:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06875","created_at":"2026-07-05T08:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"CLA4ZHBT6K5R","created_at":"2026-07-05T08:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"CLA4ZHBT6K5RTDCB","created_at":"2026-07-05T08:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"CLA4ZHBT","created_at":"2026-07-05T08:04:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CLA4ZHBT6K5RTDCBJIYLJDMZPH","target":"record","payload":{"canonical_record":{"source":{"id":"2304.06875","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-14T00:45:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4b132f02517da4a7688b248f1f0e734481293721f50e9a9d4b366ef30fd4ac66","abstract_canon_sha256":"1c6cf5bd277abef7f50ed568082ad66699729d9933b01646fb3bd133c01e9c51"},"schema_version":"1.0"},"canonical_sha256":"12c1cc9c33f2bb198c414a30b48d9979e1cf0b700f1057085fa882b8e8893db8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:57.130227Z","signature_b64":"LoI2PP8ER64lXdXiqP9AtayLLEywoDsPLXgkCeJsMT0HuHPHFTBpKvnh5oauwydkKqxMAs6Sw7zRCFZTn8UvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12c1cc9c33f2bb198c414a30b48d9979e1cf0b700f1057085fa882b8e8893db8","last_reissued_at":"2026-07-05T08:04:57.129779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:57.129779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.06875","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:04:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CFZLjlGM67xa10iMEzIumL5AQaRDs4ISPve3NBYeiafd4243WMFfNTzlLXIiqAt+iG/M25Xj38Wi+oejq/DiDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:00:01.493293Z"},"content_sha256":"cbd45ae1d757fd5fe64595678d6fe2027b8b670a120cfc13116c147f921b0e85","schema_version":"1.0","event_id":"sha256:cbd45ae1d757fd5fe64595678d6fe2027b8b670a120cfc13116c147f921b0e85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CLA4ZHBT6K5RTDCBJIYLJDMZPH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"nanoLM: an Affordable LLM Pre-training Benchmark via Accurate Loss Prediction across Scales","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aixin Sun, Kang Liu, Peng Han, Shuo Shang, Siqi Fan, Xiang Li, Xin Jiang, Xiusheng Huang, Xuezhi Fang, Xuying Meng, Yequan Wang, Yiqun Yao, Ziyi Ni","submitted_at":"2023-04-14T00:45:01Z","abstract_excerpt":"As language models scale up, it becomes increasingly expensive to verify research ideas because conclusions on small models do not trivially transfer to large ones. A possible solution is to establish a generic system that accurately predicts certain metrics for large models without training them. Existing scaling laws require hyperparameter search on the largest models, limiting their predicative capability. In this paper, we present an approach (namely {\\mu}Scaling) to predict the pre-training loss, based on our observations that Maximal Update Parametrization ({\\mu}P) enables accurate fitti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06875","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/2304.06875/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":"2026-07-05T08:04:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pFeYFUCH8euejOKtAKvZ9zIz709ELjuGMrW8p2rvlO35qYo2khNwtSzdg6WrgsaqTX1Lw6Tbu6COTlmdb0vpAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:00:01.493924Z"},"content_sha256":"35a760ba86717fde7906c11fb32be51b8e55c94002059ed3990618a51c5761b5","schema_version":"1.0","event_id":"sha256:35a760ba86717fde7906c11fb32be51b8e55c94002059ed3990618a51c5761b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CLA4ZHBT6K5RTDCBJIYLJDMZPH/bundle.json","state_url":"https://pith.science/pith/CLA4ZHBT6K5RTDCBJIYLJDMZPH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CLA4ZHBT6K5RTDCBJIYLJDMZPH/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":"2026-08-08T06:00:01Z","links":{"resolver":"https://pith.science/pith/CLA4ZHBT6K5RTDCBJIYLJDMZPH","bundle":"https://pith.science/pith/CLA4ZHBT6K5RTDCBJIYLJDMZPH/bundle.json","state":"https://pith.science/pith/CLA4ZHBT6K5RTDCBJIYLJDMZPH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CLA4ZHBT6K5RTDCBJIYLJDMZPH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CLA4ZHBT6K5RTDCBJIYLJDMZPH","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":"1c6cf5bd277abef7f50ed568082ad66699729d9933b01646fb3bd133c01e9c51","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-14T00:45:01Z","title_canon_sha256":"4b132f02517da4a7688b248f1f0e734481293721f50e9a9d4b366ef30fd4ac66"},"schema_version":"1.0","source":{"id":"2304.06875","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.06875","created_at":"2026-07-05T08:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2304.06875v4","created_at":"2026-07-05T08:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06875","created_at":"2026-07-05T08:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"CLA4ZHBT6K5R","created_at":"2026-07-05T08:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"CLA4ZHBT6K5RTDCB","created_at":"2026-07-05T08:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"CLA4ZHBT","created_at":"2026-07-05T08:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:35a760ba86717fde7906c11fb32be51b8e55c94002059ed3990618a51c5761b5","target":"graph","created_at":"2026-07-05T08:04:57Z","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/2304.06875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As language models scale up, it becomes increasingly expensive to verify research ideas because conclusions on small models do not trivially transfer to large ones. A possible solution is to establish a generic system that accurately predicts certain metrics for large models without training them. Existing scaling laws require hyperparameter search on the largest models, limiting their predicative capability. In this paper, we present an approach (namely {\\mu}Scaling) to predict the pre-training loss, based on our observations that Maximal Update Parametrization ({\\mu}P) enables accurate fitti","authors_text":"Aixin Sun, Kang Liu, Peng Han, Shuo Shang, Siqi Fan, Xiang Li, Xin Jiang, Xiusheng Huang, Xuezhi Fang, Xuying Meng, Yequan Wang, Yiqun Yao, Ziyi Ni","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-14T00:45:01Z","title":"nanoLM: an Affordable LLM Pre-training Benchmark via Accurate Loss Prediction across Scales"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06875","kind":"arxiv","version":4},"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:cbd45ae1d757fd5fe64595678d6fe2027b8b670a120cfc13116c147f921b0e85","target":"record","created_at":"2026-07-05T08:04:57Z","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":"1c6cf5bd277abef7f50ed568082ad66699729d9933b01646fb3bd133c01e9c51","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-14T00:45:01Z","title_canon_sha256":"4b132f02517da4a7688b248f1f0e734481293721f50e9a9d4b366ef30fd4ac66"},"schema_version":"1.0","source":{"id":"2304.06875","kind":"arxiv","version":4}},"canonical_sha256":"12c1cc9c33f2bb198c414a30b48d9979e1cf0b700f1057085fa882b8e8893db8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12c1cc9c33f2bb198c414a30b48d9979e1cf0b700f1057085fa882b8e8893db8","first_computed_at":"2026-07-05T08:04:57.129779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:57.129779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LoI2PP8ER64lXdXiqP9AtayLLEywoDsPLXgkCeJsMT0HuHPHFTBpKvnh5oauwydkKqxMAs6Sw7zRCFZTn8UvAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:57.130227Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.06875","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cbd45ae1d757fd5fe64595678d6fe2027b8b670a120cfc13116c147f921b0e85","sha256:35a760ba86717fde7906c11fb32be51b8e55c94002059ed3990618a51c5761b5"],"state_sha256":"0ca8de03782ccbc61849a58d18698b7608dedfa69c8ca9ac90c4ef953c91f12a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ok4QDeh3l2rYnjCJ2RwHGnfTnn0NSOh5HHyIUiRqWm26HUtTkrKf1FBPGs2N/zac0xohTSJo8GuYy3a3rQnOBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:00:01.504812Z","bundle_sha256":"5ab5f045d79b46b5f512e3d36b2624604584f1a1316a6c7251ec57faa14959fd"}}