{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z4REOJCG3J5PCNSR74CXD4LJQJ","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":"fd331797bb474d735499fde9618e84f80ca209f692e5bf826be6276863dbf71f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T17:53:51Z","title_canon_sha256":"b32e9a84213e1810f111dd3998275fbfdd68b15f530bbc1e553367860a594d35"},"schema_version":"1.0","source":{"id":"2506.10952","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.10952","created_at":"2026-07-05T11:20:40Z"},{"alias_kind":"arxiv_version","alias_value":"2506.10952v1","created_at":"2026-07-05T11:20:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10952","created_at":"2026-07-05T11:20:40Z"},{"alias_kind":"pith_short_12","alias_value":"Z4REOJCG3J5P","created_at":"2026-07-05T11:20:40Z"},{"alias_kind":"pith_short_16","alias_value":"Z4REOJCG3J5PCNSR","created_at":"2026-07-05T11:20:40Z"},{"alias_kind":"pith_short_8","alias_value":"Z4REOJCG","created_at":"2026-07-05T11:20:40Z"}],"graph_snapshots":[{"event_id":"sha256:a99273f2cf6cc9a963c8ce0c713490026d369c923ad696bc612837d293148ea3","target":"graph","created_at":"2026-07-05T11:20:40Z","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/2506.10952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce~\\textsc{Domain2Vec}, a novel approach that decomposes any dataset into a linear combination of several \\emph{meta-domains}, a new concept designed to capture the key underlying features of datasets. \\textsc{Domain2Vec} maintains a vocabulary of meta-domains and uses a classifier to decompose any given dataset into a domain vector that corresponds to a distribution over this vocabulary. These domain vectors enable the identification of the optimal data mixture for language model (LM) pretraining in a training-free manner under the \\emph{\\textbf{D}istribution \\textbf{A}lignment \\tex","authors_text":"Howe Tissue, Lu Wang, Mozhi Zhang, Xipeng Qiu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T17:53:51Z","title":"Domain2Vec: Vectorizing Datasets to Find the Optimal Data Mixture without Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10952","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":"sha256:3afded58d8d14f38e5cb58f9b2275836d6ebe65e33b11327de7a39418441110b","target":"record","created_at":"2026-07-05T11:20:40Z","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":"fd331797bb474d735499fde9618e84f80ca209f692e5bf826be6276863dbf71f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T17:53:51Z","title_canon_sha256":"b32e9a84213e1810f111dd3998275fbfdd68b15f530bbc1e553367860a594d35"},"schema_version":"1.0","source":{"id":"2506.10952","kind":"arxiv","version":1}},"canonical_sha256":"cf22472446da7af13651ff0571f169826ec8fe29d34314ef723925eb9d5321ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf22472446da7af13651ff0571f169826ec8fe29d34314ef723925eb9d5321ad","first_computed_at":"2026-07-05T11:20:40.836680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:40.836680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oJ1MiNAEN0r3yM/MSP1fxdCCQMnpud1swnlSA9WUNr46gM36VX2hz9tC6B3Y3jchVE9SpQ8oQ2hVUme+CHlpBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:40.837113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.10952","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3afded58d8d14f38e5cb58f9b2275836d6ebe65e33b11327de7a39418441110b","sha256:a99273f2cf6cc9a963c8ce0c713490026d369c923ad696bc612837d293148ea3"],"state_sha256":"0724c77ff214f4a1639546b21074cc65bf04aa174e983d8ecfeb97904c918b33"}