{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VR7643PR4QRPYJVEHXB4OSQPHX","short_pith_number":"pith:VR7643PR","schema_version":"1.0","canonical_sha256":"ac7fee6df1e422fc26a43dc3c74a0f3dfb46f9ab573460f73f0e60fae5b2165b","source":{"kind":"arxiv","id":"2606.08167","version":1},"attestation_state":"computed","paper":{"title":"Explaining Data Mixing Scaling Laws","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Rui Dai, Shuran Zheng","submitted_at":"2026-06-06T13:31:38Z","abstract_excerpt":"Recent research has established empirical scaling laws to predict model performance on multi-domain data mixtures. However, a theoretical understanding of these model loss behaviors remains absent. In this work, we propose a unified framework to explain the underlying mechanics of data mixing. Our approach extends theoretical perspectives originally developed for standard neural scaling laws (e.g., Kaplan and Chinchilla) to the multi-domain setting. Based on the distributional assumption that domains overlap on fundamental skills while diverging on specialized skills, we identify two key facto"},"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":"2606.08167","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T13:31:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b3afdfcedce02916db60d8178e1f1c22cc29dac2a1ecb1b3ead21065d4589bec","abstract_canon_sha256":"6da817131d458833f0c5855da5d4e63c75af9f310e638e2a32887747f7cf3fe9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:28.800161Z","signature_b64":"L7ohYCaUipGlKXuGpAMm6E7sjC07RPNRppvhVnR5cMMa9J2ovcLS0beuXr4r77LqkszaH7DoLIMBfCmwWxjxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac7fee6df1e422fc26a43dc3c74a0f3dfb46f9ab573460f73f0e60fae5b2165b","last_reissued_at":"2026-06-09T01:05:28.799727Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:28.799727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explaining Data Mixing Scaling Laws","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Rui Dai, Shuran Zheng","submitted_at":"2026-06-06T13:31:38Z","abstract_excerpt":"Recent research has established empirical scaling laws to predict model performance on multi-domain data mixtures. However, a theoretical understanding of these model loss behaviors remains absent. In this work, we propose a unified framework to explain the underlying mechanics of data mixing. Our approach extends theoretical perspectives originally developed for standard neural scaling laws (e.g., Kaplan and Chinchilla) to the multi-domain setting. Based on the distributional assumption that domains overlap on fundamental skills while diverging on specialized skills, we identify two key facto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08167","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/2606.08167/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":"2606.08167","created_at":"2026-06-09T01:05:28.799789+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08167v1","created_at":"2026-06-09T01:05:28.799789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08167","created_at":"2026-06-09T01:05:28.799789+00:00"},{"alias_kind":"pith_short_12","alias_value":"VR7643PR4QRP","created_at":"2026-06-09T01:05:28.799789+00:00"},{"alias_kind":"pith_short_16","alias_value":"VR7643PR4QRPYJVE","created_at":"2026-06-09T01:05:28.799789+00:00"},{"alias_kind":"pith_short_8","alias_value":"VR7643PR","created_at":"2026-06-09T01:05:28.799789+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/VR7643PR4QRPYJVEHXB4OSQPHX","json":"https://pith.science/pith/VR7643PR4QRPYJVEHXB4OSQPHX.json","graph_json":"https://pith.science/api/pith-number/VR7643PR4QRPYJVEHXB4OSQPHX/graph.json","events_json":"https://pith.science/api/pith-number/VR7643PR4QRPYJVEHXB4OSQPHX/events.json","paper":"https://pith.science/paper/VR7643PR"},"agent_actions":{"view_html":"https://pith.science/pith/VR7643PR4QRPYJVEHXB4OSQPHX","download_json":"https://pith.science/pith/VR7643PR4QRPYJVEHXB4OSQPHX.json","view_paper":"https://pith.science/paper/VR7643PR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08167&json=true","fetch_graph":"https://pith.science/api/pith-number/VR7643PR4QRPYJVEHXB4OSQPHX/graph.json","fetch_events":"https://pith.science/api/pith-number/VR7643PR4QRPYJVEHXB4OSQPHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VR7643PR4QRPYJVEHXB4OSQPHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VR7643PR4QRPYJVEHXB4OSQPHX/action/storage_attestation","attest_author":"https://pith.science/pith/VR7643PR4QRPYJVEHXB4OSQPHX/action/author_attestation","sign_citation":"https://pith.science/pith/VR7643PR4QRPYJVEHXB4OSQPHX/action/citation_signature","submit_replication":"https://pith.science/pith/VR7643PR4QRPYJVEHXB4OSQPHX/action/replication_record"}},"created_at":"2026-06-09T01:05:28.799789+00:00","updated_at":"2026-06-09T01:05:28.799789+00:00"}