{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VR7643PR4QRPYJVEHXB4OSQPHX","short_pith_number":"pith:VR7643PR","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"},"canonical_sha256":"ac7fee6df1e422fc26a43dc3c74a0f3dfb46f9ab573460f73f0e60fae5b2165b","source":{"kind":"arxiv","id":"2606.08167","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08167","created_at":"2026-06-09T01:05:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08167v1","created_at":"2026-06-09T01:05:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08167","created_at":"2026-06-09T01:05:28Z"},{"alias_kind":"pith_short_12","alias_value":"VR7643PR4QRP","created_at":"2026-06-09T01:05:28Z"},{"alias_kind":"pith_short_16","alias_value":"VR7643PR4QRPYJVE","created_at":"2026-06-09T01:05:28Z"},{"alias_kind":"pith_short_8","alias_value":"VR7643PR","created_at":"2026-06-09T01:05:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VR7643PR4QRPYJVEHXB4OSQPHX","target":"record","payload":{"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"},"canonical_sha256":"ac7fee6df1e422fc26a43dc3c74a0f3dfb46f9ab573460f73f0e60fae5b2165b","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"},"source_kind":"arxiv","source_id":"2606.08167","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":"2026-06-09T01:05:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AVboODPBvTyfQUsPzydKfAfjGx4YwBwjm5m0LdHfdHe51cN7lSrx/dKJVg2vq2tIZKGjkXDCW1o6JF3hXTbjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T00:49:34.032215Z"},"content_sha256":"222f3925e6dfcbcf24615d6d751ca17082c224561a9ba2ed5a77dc77396344bc","schema_version":"1.0","event_id":"sha256:222f3925e6dfcbcf24615d6d751ca17082c224561a9ba2ed5a77dc77396344bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VR7643PR4QRPYJVEHXB4OSQPHX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:05:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c7sYFR8zDoqCLdvp/7+BL1+FNXfGvZi97pUkrtf9luyAy2If5k3VdxqozX1Ce5GjRvAiTaT1BymDVlON86pDBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T00:49:34.032659Z"},"content_sha256":"24c0055eac72ad473fa58a19fd11e3b30b7dd4fc682405a2a9c34993db7ceab0","schema_version":"1.0","event_id":"sha256:24c0055eac72ad473fa58a19fd11e3b30b7dd4fc682405a2a9c34993db7ceab0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VR7643PR4QRPYJVEHXB4OSQPHX/bundle.json","state_url":"https://pith.science/pith/VR7643PR4QRPYJVEHXB4OSQPHX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VR7643PR4QRPYJVEHXB4OSQPHX/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":"2026-07-03T00:49:34Z","links":{"resolver":"https://pith.science/pith/VR7643PR4QRPYJVEHXB4OSQPHX","bundle":"https://pith.science/pith/VR7643PR4QRPYJVEHXB4OSQPHX/bundle.json","state":"https://pith.science/pith/VR7643PR4QRPYJVEHXB4OSQPHX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VR7643PR4QRPYJVEHXB4OSQPHX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VR7643PR4QRPYJVEHXB4OSQPHX","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":"6da817131d458833f0c5855da5d4e63c75af9f310e638e2a32887747f7cf3fe9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T13:31:38Z","title_canon_sha256":"b3afdfcedce02916db60d8178e1f1c22cc29dac2a1ecb1b3ead21065d4589bec"},"schema_version":"1.0","source":{"id":"2606.08167","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08167","created_at":"2026-06-09T01:05:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08167v1","created_at":"2026-06-09T01:05:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08167","created_at":"2026-06-09T01:05:28Z"},{"alias_kind":"pith_short_12","alias_value":"VR7643PR4QRP","created_at":"2026-06-09T01:05:28Z"},{"alias_kind":"pith_short_16","alias_value":"VR7643PR4QRPYJVE","created_at":"2026-06-09T01:05:28Z"},{"alias_kind":"pith_short_8","alias_value":"VR7643PR","created_at":"2026-06-09T01:05:28Z"}],"graph_snapshots":[{"event_id":"sha256:24c0055eac72ad473fa58a19fd11e3b30b7dd4fc682405a2a9c34993db7ceab0","target":"graph","created_at":"2026-06-09T01:05:28Z","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/2606.08167/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Rui Dai, Shuran Zheng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T13:31:38Z","title":"Explaining Data Mixing Scaling Laws"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08167","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":"sha256:222f3925e6dfcbcf24615d6d751ca17082c224561a9ba2ed5a77dc77396344bc","target":"record","created_at":"2026-06-09T01:05:28Z","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":"6da817131d458833f0c5855da5d4e63c75af9f310e638e2a32887747f7cf3fe9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T13:31:38Z","title_canon_sha256":"b3afdfcedce02916db60d8178e1f1c22cc29dac2a1ecb1b3ead21065d4589bec"},"schema_version":"1.0","source":{"id":"2606.08167","kind":"arxiv","version":1}},"canonical_sha256":"ac7fee6df1e422fc26a43dc3c74a0f3dfb46f9ab573460f73f0e60fae5b2165b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac7fee6df1e422fc26a43dc3c74a0f3dfb46f9ab573460f73f0e60fae5b2165b","first_computed_at":"2026-06-09T01:05:28.799727Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:28.799727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L7ohYCaUipGlKXuGpAMm6E7sjC07RPNRppvhVnR5cMMa9J2ovcLS0beuXr4r77LqkszaH7DoLIMBfCmwWxjxBA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:28.800161Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08167","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:222f3925e6dfcbcf24615d6d751ca17082c224561a9ba2ed5a77dc77396344bc","sha256:24c0055eac72ad473fa58a19fd11e3b30b7dd4fc682405a2a9c34993db7ceab0"],"state_sha256":"16459371f54a833acf9e5a8b45879f44e936e26da9d1957d1a975b3830ce8109"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xLRMd6rPXsZugUneGx6Q9UaXZJfhNwqBHFUvMuKqGWLRLcTa+VO1TC3wM+3/xXVD8uhcffDVhb6zBa4w+sXGBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T00:49:34.034944Z","bundle_sha256":"bd0620cae598384903730f9adc8389520e167fc746fd8bbcf8aaf3469a942e98"}}