{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GLMMTYDPAIF3RG3JBKW2SZGAS4","short_pith_number":"pith:GLMMTYDP","canonical_record":{"source":{"id":"2410.03083","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T02:07:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"16aad6771e347c44b47333380d47c73ca00c3e46ec591788728052cc9307a9c4","abstract_canon_sha256":"005310cdf4999c73d66ed8bcf80359751805d2d87ca52cab12913aa19108abac"},"schema_version":"1.0"},"canonical_sha256":"32d8c9e06f020bb89b690aada964c09702084aa88bf2692f3c6aa4d8318773fa","source":{"kind":"arxiv","id":"2410.03083","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03083","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03083v1","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03083","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"pith_short_12","alias_value":"GLMMTYDPAIF3","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"pith_short_16","alias_value":"GLMMTYDPAIF3RG3J","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"pith_short_8","alias_value":"GLMMTYDP","created_at":"2026-07-05T09:15:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GLMMTYDPAIF3RG3JBKW2SZGAS4","target":"record","payload":{"canonical_record":{"source":{"id":"2410.03083","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T02:07:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"16aad6771e347c44b47333380d47c73ca00c3e46ec591788728052cc9307a9c4","abstract_canon_sha256":"005310cdf4999c73d66ed8bcf80359751805d2d87ca52cab12913aa19108abac"},"schema_version":"1.0"},"canonical_sha256":"32d8c9e06f020bb89b690aada964c09702084aa88bf2692f3c6aa4d8318773fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:43.989378Z","signature_b64":"5EcUylrjewZVTtN3O0U/OsYWg2lSFH2bc/gPR4YTMk6iqQ5SoeCuAeeK3m4RKTdk+2VwIAyB8hPAindZozlhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32d8c9e06f020bb89b690aada964c09702084aa88bf2692f3c6aa4d8318773fa","last_reissued_at":"2026-07-05T09:15:43.988871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:43.988871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.03083","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:15:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LHZkD1bIEpB/JuJ+KSLNr7yfbSO7GwYLr+2E6s4PRK7to9WRv0NJsHmoiIiLYePACcXKdGnZ6BsURfqr3cPfCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:25:59.483659Z"},"content_sha256":"eb4a50d780147424b7d2b3cf9a1f52b90960753698bb3ddd483923a7bc85fb65","schema_version":"1.0","event_id":"sha256:eb4a50d780147424b7d2b3cf9a1f52b90960753698bb3ddd483923a7bc85fb65"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GLMMTYDPAIF3RG3JBKW2SZGAS4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Parameter-Constrained Language Models with Quality Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Changsheng Zhao, Ernie Chang, Matteo Paltenghi, Patrick Huber, Pin-Jie Lin, Rastislav Rabatin, Vikas Chandra, Yang Li, Yangyang Shi, Zechun Liu","submitted_at":"2024-10-04T02:07:17Z","abstract_excerpt":"Scaling laws in language modeling traditionally quantify training loss as a function of dataset size and model parameters, providing compute-optimal estimates but often neglecting the impact of data quality on model generalization. In this paper, we extend the conventional understanding of scaling law by offering a microscopic view of data quality within the original formulation -- effective training tokens -- which we posit to be a critical determinant of performance for parameter-constrained language models. Specifically, we formulate the proposed term of effective training tokens to be a co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03083","kind":"arxiv","version":1},"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/2410.03083/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":"2026-07-05T09:15:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZH0Q1WYbvuSg550nUEGRnrt4C0f7XAly4V+QZdylBcOrX6JCKceukcKJj/W+XjB/65CTsee8y1WKqJwkmHHYDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:25:59.484166Z"},"content_sha256":"6f2cbd2497971fa5ebc4e9659e3d23f6e78d6968a5f49717f67bed22d1687243","schema_version":"1.0","event_id":"sha256:6f2cbd2497971fa5ebc4e9659e3d23f6e78d6968a5f49717f67bed22d1687243"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GLMMTYDPAIF3RG3JBKW2SZGAS4/bundle.json","state_url":"https://pith.science/pith/GLMMTYDPAIF3RG3JBKW2SZGAS4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GLMMTYDPAIF3RG3JBKW2SZGAS4/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":"2026-08-08T07:25:59Z","links":{"resolver":"https://pith.science/pith/GLMMTYDPAIF3RG3JBKW2SZGAS4","bundle":"https://pith.science/pith/GLMMTYDPAIF3RG3JBKW2SZGAS4/bundle.json","state":"https://pith.science/pith/GLMMTYDPAIF3RG3JBKW2SZGAS4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GLMMTYDPAIF3RG3JBKW2SZGAS4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GLMMTYDPAIF3RG3JBKW2SZGAS4","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":"005310cdf4999c73d66ed8bcf80359751805d2d87ca52cab12913aa19108abac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T02:07:17Z","title_canon_sha256":"16aad6771e347c44b47333380d47c73ca00c3e46ec591788728052cc9307a9c4"},"schema_version":"1.0","source":{"id":"2410.03083","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03083","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03083v1","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03083","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"pith_short_12","alias_value":"GLMMTYDPAIF3","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"pith_short_16","alias_value":"GLMMTYDPAIF3RG3J","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"pith_short_8","alias_value":"GLMMTYDP","created_at":"2026-07-05T09:15:43Z"}],"graph_snapshots":[{"event_id":"sha256:6f2cbd2497971fa5ebc4e9659e3d23f6e78d6968a5f49717f67bed22d1687243","target":"graph","created_at":"2026-07-05T09:15:43Z","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/2410.03083/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling laws in language modeling traditionally quantify training loss as a function of dataset size and model parameters, providing compute-optimal estimates but often neglecting the impact of data quality on model generalization. In this paper, we extend the conventional understanding of scaling law by offering a microscopic view of data quality within the original formulation -- effective training tokens -- which we posit to be a critical determinant of performance for parameter-constrained language models. Specifically, we formulate the proposed term of effective training tokens to be a co","authors_text":"Changsheng Zhao, Ernie Chang, Matteo Paltenghi, Patrick Huber, Pin-Jie Lin, Rastislav Rabatin, Vikas Chandra, Yang Li, Yangyang Shi, Zechun Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T02:07:17Z","title":"Scaling Parameter-Constrained Language Models with Quality Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03083","kind":"arxiv","version":1},"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:eb4a50d780147424b7d2b3cf9a1f52b90960753698bb3ddd483923a7bc85fb65","target":"record","created_at":"2026-07-05T09:15:43Z","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":"005310cdf4999c73d66ed8bcf80359751805d2d87ca52cab12913aa19108abac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T02:07:17Z","title_canon_sha256":"16aad6771e347c44b47333380d47c73ca00c3e46ec591788728052cc9307a9c4"},"schema_version":"1.0","source":{"id":"2410.03083","kind":"arxiv","version":1}},"canonical_sha256":"32d8c9e06f020bb89b690aada964c09702084aa88bf2692f3c6aa4d8318773fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32d8c9e06f020bb89b690aada964c09702084aa88bf2692f3c6aa4d8318773fa","first_computed_at":"2026-07-05T09:15:43.988871Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:43.988871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5EcUylrjewZVTtN3O0U/OsYWg2lSFH2bc/gPR4YTMk6iqQ5SoeCuAeeK3m4RKTdk+2VwIAyB8hPAindZozlhDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:43.989378Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03083","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb4a50d780147424b7d2b3cf9a1f52b90960753698bb3ddd483923a7bc85fb65","sha256:6f2cbd2497971fa5ebc4e9659e3d23f6e78d6968a5f49717f67bed22d1687243"],"state_sha256":"bb03767d4234ee1db7b6bde6265cba9b6449cc38b748f3eddb01d22676aba7c3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TwCnbbtlSeKgiy160OdFFnfOipmfJzu52n9NBK8rEnZCbz7ODxKBI0EjewPXan+/ycq8TuTUiKD74DUvKXQbAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:25:59.487351Z","bundle_sha256":"5dedf4d85e5fdb5462d28e62bce7825b37d946e1115af323ecec25ff492b8e26"}}