{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X5WVKWM6GG46GTXVK6CII4PE2C","short_pith_number":"pith:X5WVKWM6","schema_version":"1.0","canonical_sha256":"bf6d55599e31b9e34ef557848471e4d0ab23fd2434931b641633dbd80c1939f1","source":{"kind":"arxiv","id":"2606.19781","version":1},"attestation_state":"computed","paper":{"title":"Towards Engineering Scaling Laws with Pretraining Data Composition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"hep-ex","authors_text":"Benjamin Nachman, Daniel Whiteson, Jan-Lucas Uslu, Kevin Greif","submitted_at":"2026-06-18T04:32:06Z","abstract_excerpt":"Neural scaling laws describe how model performance improves as a power law in compute, model size, and dataset size. While well-established for large language models, these relationships are emerging for large models in particle physics. As with language, empirical studies show that the performance scales as a power law. However, unlike natural language or image domains, fundamental physics has high-fidelity simulators that produce synthetic data cheaply. This favors scaling regimes where additional data is cheaper than additional parameters, and allows the pretraining dataset itself to be eng"},"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":"2606.19781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"hep-ex","submitted_at":"2026-06-18T04:32:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d48cf087c26fe54789332973e3b424af44f2dd82e414ab9b2cda348d51f85d7a","abstract_canon_sha256":"18b15581e0db50f30f83b48368ea78656ebd7db9ce9af0df592ea8edc80437a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:34.978668Z","signature_b64":"qubRHqdTIqEY1vpaTxTzDvYQoAFWa1JTH+2Gz8SFfOeXFud6WyqEPPtYtJW0OMJlII/Ot90wUrsq1ge7RGFaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf6d55599e31b9e34ef557848471e4d0ab23fd2434931b641633dbd80c1939f1","last_reissued_at":"2026-06-19T16:12:34.978309Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:34.978309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Engineering Scaling Laws with Pretraining Data Composition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"hep-ex","authors_text":"Benjamin Nachman, Daniel Whiteson, Jan-Lucas Uslu, Kevin Greif","submitted_at":"2026-06-18T04:32:06Z","abstract_excerpt":"Neural scaling laws describe how model performance improves as a power law in compute, model size, and dataset size. While well-established for large language models, these relationships are emerging for large models in particle physics. As with language, empirical studies show that the performance scales as a power law. However, unlike natural language or image domains, fundamental physics has high-fidelity simulators that produce synthetic data cheaply. This favors scaling regimes where additional data is cheaper than additional parameters, and allows the pretraining dataset itself to be eng"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19781","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/2606.19781/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":"2606.19781","created_at":"2026-06-19T16:12:34.978383+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19781v1","created_at":"2026-06-19T16:12:34.978383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19781","created_at":"2026-06-19T16:12:34.978383+00:00"},{"alias_kind":"pith_short_12","alias_value":"X5WVKWM6GG46","created_at":"2026-06-19T16:12:34.978383+00:00"},{"alias_kind":"pith_short_16","alias_value":"X5WVKWM6GG46GTXV","created_at":"2026-06-19T16:12:34.978383+00:00"},{"alias_kind":"pith_short_8","alias_value":"X5WVKWM6","created_at":"2026-06-19T16:12:34.978383+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/X5WVKWM6GG46GTXVK6CII4PE2C","json":"https://pith.science/pith/X5WVKWM6GG46GTXVK6CII4PE2C.json","graph_json":"https://pith.science/api/pith-number/X5WVKWM6GG46GTXVK6CII4PE2C/graph.json","events_json":"https://pith.science/api/pith-number/X5WVKWM6GG46GTXVK6CII4PE2C/events.json","paper":"https://pith.science/paper/X5WVKWM6"},"agent_actions":{"view_html":"https://pith.science/pith/X5WVKWM6GG46GTXVK6CII4PE2C","download_json":"https://pith.science/pith/X5WVKWM6GG46GTXVK6CII4PE2C.json","view_paper":"https://pith.science/paper/X5WVKWM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19781&json=true","fetch_graph":"https://pith.science/api/pith-number/X5WVKWM6GG46GTXVK6CII4PE2C/graph.json","fetch_events":"https://pith.science/api/pith-number/X5WVKWM6GG46GTXVK6CII4PE2C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X5WVKWM6GG46GTXVK6CII4PE2C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X5WVKWM6GG46GTXVK6CII4PE2C/action/storage_attestation","attest_author":"https://pith.science/pith/X5WVKWM6GG46GTXVK6CII4PE2C/action/author_attestation","sign_citation":"https://pith.science/pith/X5WVKWM6GG46GTXVK6CII4PE2C/action/citation_signature","submit_replication":"https://pith.science/pith/X5WVKWM6GG46GTXVK6CII4PE2C/action/replication_record"}},"created_at":"2026-06-19T16:12:34.978383+00:00","updated_at":"2026-06-19T16:12:34.978383+00:00"}