{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:H2HCYYFUDFMVUAMQS432VYXC54","short_pith_number":"pith:H2HCYYFU","canonical_record":{"source":{"id":"2607.11052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-13T03:31:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8f267b3826f9405e5b6cf9a55b5a0fcd8649fc1508dd9ddbc5a4b58a9452de5e","abstract_canon_sha256":"9837ad1ed38c3e4a064bcc7cc76dad3e0ee24fd68d5ff6cd2c2967d8b343f8c7"},"schema_version":"1.0"},"canonical_sha256":"3e8e2c60b419595a01909737aae2e2ef23350511ac3bc9075b07ebe8053b91a0","source":{"kind":"arxiv","id":"2607.11052","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.11052","created_at":"2026-07-14T01:22:13Z"},{"alias_kind":"arxiv_version","alias_value":"2607.11052v1","created_at":"2026-07-14T01:22:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11052","created_at":"2026-07-14T01:22:13Z"},{"alias_kind":"pith_short_12","alias_value":"H2HCYYFUDFMV","created_at":"2026-07-14T01:22:13Z"},{"alias_kind":"pith_short_16","alias_value":"H2HCYYFUDFMVUAMQ","created_at":"2026-07-14T01:22:13Z"},{"alias_kind":"pith_short_8","alias_value":"H2HCYYFU","created_at":"2026-07-14T01:22:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:H2HCYYFUDFMVUAMQS432VYXC54","target":"record","payload":{"canonical_record":{"source":{"id":"2607.11052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-13T03:31:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8f267b3826f9405e5b6cf9a55b5a0fcd8649fc1508dd9ddbc5a4b58a9452de5e","abstract_canon_sha256":"9837ad1ed38c3e4a064bcc7cc76dad3e0ee24fd68d5ff6cd2c2967d8b343f8c7"},"schema_version":"1.0"},"canonical_sha256":"3e8e2c60b419595a01909737aae2e2ef23350511ac3bc9075b07ebe8053b91a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:22:13.864336Z","signature_b64":"5TG8cjvmixccGXaltxUUFM06pTUTrpeUKIUFlbqMY8732nNebYDCz3/u2WkxvKRG2IqZzzPk4HxV7+Wfmkd+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e8e2c60b419595a01909737aae2e2ef23350511ac3bc9075b07ebe8053b91a0","last_reissued_at":"2026-07-14T01:22:13.863509Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:22:13.863509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.11052","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":"2026-07-14T01:22:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4t8ViR3drf+qZXj/7sf+RICBGSXiRo7LtTKPqDKULC2l3FdR9j0VCZz4TB/L4ysRHCFk4t4taPNgvK48T+wODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T03:10:15.536295Z"},"content_sha256":"4824885fb66d422364270f6550293bb12758626c4cfde17fe260674d6ea335b0","schema_version":"1.0","event_id":"sha256:4824885fb66d422364270f6550293bb12758626c4cfde17fe260674d6ea335b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:H2HCYYFUDFMVUAMQS432VYXC54","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Domain-Aware Scaling Laws Uncover Data Synergy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"David Alvarez-Melis, Kimia Hamidieh, Lester Mackey","submitted_at":"2026-07-13T03:31:03Z","abstract_excerpt":"Machine learning progress is often attributed to scaling model size and dataset volume, yet the composition of data can be just as consequential. Empirical findings repeatedly show that combining datasets from different domains yields nontrivial interactions. For instance, adding code improves mathematical reasoning, while certain mixtures introduce interference that reduces model performance. We refer to these effects collectively as data synergy, where the contribution of multiple domains exceeds or falls short of the sum of their isolated contributions. In this work, we formalize and quanti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11052","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/2607.11052/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":"2026-07-14T01:22:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BUk1oE88z1WL20IPN2q4aMox/NWeplIDrMILdNlnKnuHM+TX47R54+qPdW5jhRcbU7EmQ+96guzl/pSBFMcfBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T03:10:15.536823Z"},"content_sha256":"533e96fd735c67a2406ed7f1ac9ddbcb37ccf06c316c32fd112ee72d1cc8c64f","schema_version":"1.0","event_id":"sha256:533e96fd735c67a2406ed7f1ac9ddbcb37ccf06c316c32fd112ee72d1cc8c64f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H2HCYYFUDFMVUAMQS432VYXC54/bundle.json","state_url":"https://pith.science/pith/H2HCYYFUDFMVUAMQS432VYXC54/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H2HCYYFUDFMVUAMQS432VYXC54/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":"2026-08-02T03:10:15Z","links":{"resolver":"https://pith.science/pith/H2HCYYFUDFMVUAMQS432VYXC54","bundle":"https://pith.science/pith/H2HCYYFUDFMVUAMQS432VYXC54/bundle.json","state":"https://pith.science/pith/H2HCYYFUDFMVUAMQS432VYXC54/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H2HCYYFUDFMVUAMQS432VYXC54/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:H2HCYYFUDFMVUAMQS432VYXC54","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":"9837ad1ed38c3e4a064bcc7cc76dad3e0ee24fd68d5ff6cd2c2967d8b343f8c7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-13T03:31:03Z","title_canon_sha256":"8f267b3826f9405e5b6cf9a55b5a0fcd8649fc1508dd9ddbc5a4b58a9452de5e"},"schema_version":"1.0","source":{"id":"2607.11052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.11052","created_at":"2026-07-14T01:22:13Z"},{"alias_kind":"arxiv_version","alias_value":"2607.11052v1","created_at":"2026-07-14T01:22:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11052","created_at":"2026-07-14T01:22:13Z"},{"alias_kind":"pith_short_12","alias_value":"H2HCYYFUDFMV","created_at":"2026-07-14T01:22:13Z"},{"alias_kind":"pith_short_16","alias_value":"H2HCYYFUDFMVUAMQ","created_at":"2026-07-14T01:22:13Z"},{"alias_kind":"pith_short_8","alias_value":"H2HCYYFU","created_at":"2026-07-14T01:22:13Z"}],"graph_snapshots":[{"event_id":"sha256:533e96fd735c67a2406ed7f1ac9ddbcb37ccf06c316c32fd112ee72d1cc8c64f","target":"graph","created_at":"2026-07-14T01:22:13Z","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/2607.11052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning progress is often attributed to scaling model size and dataset volume, yet the composition of data can be just as consequential. Empirical findings repeatedly show that combining datasets from different domains yields nontrivial interactions. For instance, adding code improves mathematical reasoning, while certain mixtures introduce interference that reduces model performance. We refer to these effects collectively as data synergy, where the contribution of multiple domains exceeds or falls short of the sum of their isolated contributions. In this work, we formalize and quanti","authors_text":"David Alvarez-Melis, Kimia Hamidieh, Lester Mackey","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-13T03:31:03Z","title":"Domain-Aware Scaling Laws Uncover Data Synergy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11052","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":"sha256:4824885fb66d422364270f6550293bb12758626c4cfde17fe260674d6ea335b0","target":"record","created_at":"2026-07-14T01:22:13Z","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":"9837ad1ed38c3e4a064bcc7cc76dad3e0ee24fd68d5ff6cd2c2967d8b343f8c7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-13T03:31:03Z","title_canon_sha256":"8f267b3826f9405e5b6cf9a55b5a0fcd8649fc1508dd9ddbc5a4b58a9452de5e"},"schema_version":"1.0","source":{"id":"2607.11052","kind":"arxiv","version":1}},"canonical_sha256":"3e8e2c60b419595a01909737aae2e2ef23350511ac3bc9075b07ebe8053b91a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e8e2c60b419595a01909737aae2e2ef23350511ac3bc9075b07ebe8053b91a0","first_computed_at":"2026-07-14T01:22:13.863509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:22:13.863509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5TG8cjvmixccGXaltxUUFM06pTUTrpeUKIUFlbqMY8732nNebYDCz3/u2WkxvKRG2IqZzzPk4HxV7+Wfmkd+Dg==","signature_status":"signed_v1","signed_at":"2026-07-14T01:22:13.864336Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.11052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4824885fb66d422364270f6550293bb12758626c4cfde17fe260674d6ea335b0","sha256:533e96fd735c67a2406ed7f1ac9ddbcb37ccf06c316c32fd112ee72d1cc8c64f"],"state_sha256":"14f16071fd4979d63a28823effb0e1b2749bfc756e6831c7aaecf3b6fbe0633e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5R6TwDO4JRRD/VHtfakRJ28GIDTuOECC04GLM07q84I9HsyZ0iqKNENNK1DYTZsIFzLMSKFitCHWRioynI8JAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T03:10:15.541942Z","bundle_sha256":"654d2600ae7c7e61f51fa448fc72efdad673bd05eaa46e2e3427866bb4cbb693"}}