{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:V52MEJMLLIHK76JBDO7XRVUXMI","short_pith_number":"pith:V52MEJML","canonical_record":{"source":{"id":"2404.01204","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-01T16:00:01Z","cross_cats_sorted":[],"title_canon_sha256":"8a7e8deb75be02f0fe8df779bb687bb5d99fb8e7ede955780123029e37fdc4a7","abstract_canon_sha256":"7bb7f1d40a064e442bcee9ee9980c35abf719a3f4cdea286166825333c677752"},"schema_version":"1.0"},"canonical_sha256":"af74c2258b5a0eaff9211bbf78d69762343fa31aa61d94fcc0928dd6e40bf700","source":{"kind":"arxiv","id":"2404.01204","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01204","created_at":"2026-07-05T09:31:44Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01204v3","created_at":"2026-07-05T09:31:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01204","created_at":"2026-07-05T09:31:44Z"},{"alias_kind":"pith_short_12","alias_value":"V52MEJMLLIHK","created_at":"2026-07-05T09:31:44Z"},{"alias_kind":"pith_short_16","alias_value":"V52MEJMLLIHK76JB","created_at":"2026-07-05T09:31:44Z"},{"alias_kind":"pith_short_8","alias_value":"V52MEJML","created_at":"2026-07-05T09:31:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:V52MEJMLLIHK76JBDO7XRVUXMI","target":"record","payload":{"canonical_record":{"source":{"id":"2404.01204","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-01T16:00:01Z","cross_cats_sorted":[],"title_canon_sha256":"8a7e8deb75be02f0fe8df779bb687bb5d99fb8e7ede955780123029e37fdc4a7","abstract_canon_sha256":"7bb7f1d40a064e442bcee9ee9980c35abf719a3f4cdea286166825333c677752"},"schema_version":"1.0"},"canonical_sha256":"af74c2258b5a0eaff9211bbf78d69762343fa31aa61d94fcc0928dd6e40bf700","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:44.774514Z","signature_b64":"TVeTkVwVGZuC+Xa3Spd07kV6QCVSjiGvWWnU0p02A27rTazSzxRqGFdujNXnMum3LbSvcOYcarpIefmRL7ueAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af74c2258b5a0eaff9211bbf78d69762343fa31aa61d94fcc0928dd6e40bf700","last_reissued_at":"2026-07-05T09:31:44.773803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:44.773803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.01204","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:31:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lDCtz4EtnYHhB0JBSZAkRP/tQdU9r9h6Bbk+0GzfMG13zocd6qdP3rAaED3jkXNCeFl+HenrMp0irQFiJEuWBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:49:34.163189Z"},"content_sha256":"dcb9e8aabff9e60bc71f959fd3de2473b4877fb3f6777eab8e94de7c96f09508","schema_version":"1.0","event_id":"sha256:dcb9e8aabff9e60bc71f959fd3de2473b4877fb3f6777eab8e94de7c96f09508"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:V52MEJMLLIHK76JBDO7XRVUXMI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Fine Line: Navigating Large Language Model Pretraining with Down-streaming Capability Analysis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Yang, Ge Zhang, Haoran Zhang, Jiaheng Liu, Junzhuo Li, Ruibin Yuan, Shawn Yue, Songyang Gao, Stephen W. Huang, Xingwei Qu, Xinrun Du, Xinyao Niu, Yizhi Li, Zhaoliang Chen","submitted_at":"2024-04-01T16:00:01Z","abstract_excerpt":"Uncovering early-stage metrics that reflect final model performance is one core principle for large-scale pretraining. The existing scaling law demonstrates the power-law correlation between pretraining loss and training flops, which serves as an important indicator of the current training state for large language models. However, this principle only focuses on the model's compression properties on the training data, resulting in an inconsistency with the ability improvements on the downstream tasks. Some follow-up works attempted to extend the scaling-law to more complex metrics (such as hype"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01204","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/2404.01204/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":"2026-07-05T09:31:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WoAHlgqSGYJ7ZvL83GxZQxpcFFWmBTTHHk8cDsY7YdEFfwXn/fpcyr0xle+TLhHiia0B1f+yTXEnv0kfCVF+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:49:34.163896Z"},"content_sha256":"2428c66fba5e60c7f27d02df248a578f8754e61baa9d686c88c4fd62f0bdb71d","schema_version":"1.0","event_id":"sha256:2428c66fba5e60c7f27d02df248a578f8754e61baa9d686c88c4fd62f0bdb71d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V52MEJMLLIHK76JBDO7XRVUXMI/bundle.json","state_url":"https://pith.science/pith/V52MEJMLLIHK76JBDO7XRVUXMI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V52MEJMLLIHK76JBDO7XRVUXMI/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":"2026-08-04T10:49:34Z","links":{"resolver":"https://pith.science/pith/V52MEJMLLIHK76JBDO7XRVUXMI","bundle":"https://pith.science/pith/V52MEJMLLIHK76JBDO7XRVUXMI/bundle.json","state":"https://pith.science/pith/V52MEJMLLIHK76JBDO7XRVUXMI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V52MEJMLLIHK76JBDO7XRVUXMI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V52MEJMLLIHK76JBDO7XRVUXMI","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":"7bb7f1d40a064e442bcee9ee9980c35abf719a3f4cdea286166825333c677752","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-01T16:00:01Z","title_canon_sha256":"8a7e8deb75be02f0fe8df779bb687bb5d99fb8e7ede955780123029e37fdc4a7"},"schema_version":"1.0","source":{"id":"2404.01204","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01204","created_at":"2026-07-05T09:31:44Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01204v3","created_at":"2026-07-05T09:31:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01204","created_at":"2026-07-05T09:31:44Z"},{"alias_kind":"pith_short_12","alias_value":"V52MEJMLLIHK","created_at":"2026-07-05T09:31:44Z"},{"alias_kind":"pith_short_16","alias_value":"V52MEJMLLIHK76JB","created_at":"2026-07-05T09:31:44Z"},{"alias_kind":"pith_short_8","alias_value":"V52MEJML","created_at":"2026-07-05T09:31:44Z"}],"graph_snapshots":[{"event_id":"sha256:2428c66fba5e60c7f27d02df248a578f8754e61baa9d686c88c4fd62f0bdb71d","target":"graph","created_at":"2026-07-05T09:31:44Z","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/2404.01204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Uncovering early-stage metrics that reflect final model performance is one core principle for large-scale pretraining. The existing scaling law demonstrates the power-law correlation between pretraining loss and training flops, which serves as an important indicator of the current training state for large language models. However, this principle only focuses on the model's compression properties on the training data, resulting in an inconsistency with the ability improvements on the downstream tasks. Some follow-up works attempted to extend the scaling-law to more complex metrics (such as hype","authors_text":"Chen Yang, Ge Zhang, Haoran Zhang, Jiaheng Liu, Junzhuo Li, Ruibin Yuan, Shawn Yue, Songyang Gao, Stephen W. Huang, Xingwei Qu, Xinrun Du, Xinyao Niu, Yizhi Li, Zhaoliang Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-01T16:00:01Z","title":"The Fine Line: Navigating Large Language Model Pretraining with Down-streaming Capability Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01204","kind":"arxiv","version":3},"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:dcb9e8aabff9e60bc71f959fd3de2473b4877fb3f6777eab8e94de7c96f09508","target":"record","created_at":"2026-07-05T09:31:44Z","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":"7bb7f1d40a064e442bcee9ee9980c35abf719a3f4cdea286166825333c677752","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-01T16:00:01Z","title_canon_sha256":"8a7e8deb75be02f0fe8df779bb687bb5d99fb8e7ede955780123029e37fdc4a7"},"schema_version":"1.0","source":{"id":"2404.01204","kind":"arxiv","version":3}},"canonical_sha256":"af74c2258b5a0eaff9211bbf78d69762343fa31aa61d94fcc0928dd6e40bf700","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af74c2258b5a0eaff9211bbf78d69762343fa31aa61d94fcc0928dd6e40bf700","first_computed_at":"2026-07-05T09:31:44.773803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:44.773803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TVeTkVwVGZuC+Xa3Spd07kV6QCVSjiGvWWnU0p02A27rTazSzxRqGFdujNXnMum3LbSvcOYcarpIefmRL7ueAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:44.774514Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01204","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcb9e8aabff9e60bc71f959fd3de2473b4877fb3f6777eab8e94de7c96f09508","sha256:2428c66fba5e60c7f27d02df248a578f8754e61baa9d686c88c4fd62f0bdb71d"],"state_sha256":"98ae1441d727262126149e3a59e3bf4ca9345a8a06c9c72499d65688077a5b89"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vMhxiBib9/WXQ73zNKP1+113xfEiKPMc3nhT1xjrqvaqLyXIxwp81YK6fxC5nSG72kzkoeMCrcyCZQLOl4azAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:49:34.169431Z","bundle_sha256":"96c4f6f4e4587e4f14144ff9173e1f603c2efa7cb8e2eb6c1263eff74aa5343e"}}