{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X6U2NLAAHNE6MEVT234LSFR3BH","short_pith_number":"pith:X6U2NLAA","schema_version":"1.0","canonical_sha256":"bfa9a6ac003b49e612b3d6f8b9163b09ec3a39d1fe45ff45b83956bf4b8a1262","source":{"kind":"arxiv","id":"2508.21632","version":1},"attestation_state":"computed","paper":{"title":"QZhou-Embedding Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bin Chen, En Xu, Haibiao Chen, Peng Yu, Yinfei Xu","submitted_at":"2025-08-29T13:47:22Z","abstract_excerpt":"We present QZhou-Embedding, a general-purpose contextual text embedding model with exceptional text representation capabilities. Built upon the Qwen2.5-7B-Instruct foundation model, we designed a unified multi-task framework comprising specialized data transformation and training strategies. The data transformation scheme enables the incorporation of more diverse textual training datasets, while the task-specific training strategies enhance model learning efficiency. We developed a data synthesis pipeline leveraging LLM API, incorporating techniques such as paraphrasing, augmentation, and hard"},"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":"2508.21632","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-29T13:47:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"672ac3ae113c218e55fd40e42f9ff9e3c8a0fb141fd396282b867523eda78d2b","abstract_canon_sha256":"e595d1dcc67b98c2e5bfd50e778b624dd46051e951bd59782a2f06b5c1abe51d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:46.943894Z","signature_b64":"QlqlcACQfJrMYgD/djCj7RyJi0tcPgRV2242VTngqlQf+LieTWcR0emys5RubFQIPOqvcvZ12gtrCNGXVH16BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfa9a6ac003b49e612b3d6f8b9163b09ec3a39d1fe45ff45b83956bf4b8a1262","last_reissued_at":"2026-07-05T12:01:46.943335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:46.943335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QZhou-Embedding Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bin Chen, En Xu, Haibiao Chen, Peng Yu, Yinfei Xu","submitted_at":"2025-08-29T13:47:22Z","abstract_excerpt":"We present QZhou-Embedding, a general-purpose contextual text embedding model with exceptional text representation capabilities. Built upon the Qwen2.5-7B-Instruct foundation model, we designed a unified multi-task framework comprising specialized data transformation and training strategies. The data transformation scheme enables the incorporation of more diverse textual training datasets, while the task-specific training strategies enhance model learning efficiency. We developed a data synthesis pipeline leveraging LLM API, incorporating techniques such as paraphrasing, augmentation, and hard"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21632","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/2508.21632/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":"2508.21632","created_at":"2026-07-05T12:01:46.943403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.21632v1","created_at":"2026-07-05T12:01:46.943403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21632","created_at":"2026-07-05T12:01:46.943403+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6U2NLAAHNE6","created_at":"2026-07-05T12:01:46.943403+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6U2NLAAHNE6MEVT","created_at":"2026-07-05T12:01:46.943403+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6U2NLAA","created_at":"2026-07-05T12:01:46.943403+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04962","citing_title":"TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6U2NLAAHNE6MEVT234LSFR3BH","json":"https://pith.science/pith/X6U2NLAAHNE6MEVT234LSFR3BH.json","graph_json":"https://pith.science/api/pith-number/X6U2NLAAHNE6MEVT234LSFR3BH/graph.json","events_json":"https://pith.science/api/pith-number/X6U2NLAAHNE6MEVT234LSFR3BH/events.json","paper":"https://pith.science/paper/X6U2NLAA"},"agent_actions":{"view_html":"https://pith.science/pith/X6U2NLAAHNE6MEVT234LSFR3BH","download_json":"https://pith.science/pith/X6U2NLAAHNE6MEVT234LSFR3BH.json","view_paper":"https://pith.science/paper/X6U2NLAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.21632&json=true","fetch_graph":"https://pith.science/api/pith-number/X6U2NLAAHNE6MEVT234LSFR3BH/graph.json","fetch_events":"https://pith.science/api/pith-number/X6U2NLAAHNE6MEVT234LSFR3BH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6U2NLAAHNE6MEVT234LSFR3BH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6U2NLAAHNE6MEVT234LSFR3BH/action/storage_attestation","attest_author":"https://pith.science/pith/X6U2NLAAHNE6MEVT234LSFR3BH/action/author_attestation","sign_citation":"https://pith.science/pith/X6U2NLAAHNE6MEVT234LSFR3BH/action/citation_signature","submit_replication":"https://pith.science/pith/X6U2NLAAHNE6MEVT234LSFR3BH/action/replication_record"}},"created_at":"2026-07-05T12:01:46.943403+00:00","updated_at":"2026-07-05T12:01:46.943403+00:00"}