{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WDXXXGLW446BC2XZDRSFHW6EUS","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":"f5bb40bb6bcfb868836a5af7ade5537e8a6c99301976ce2e7dda353ee06e2d55","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-29T03:12:28Z","title_canon_sha256":"4147663170abb3c27758a09e7088921a09fbac34bc18eb491a29c780a52bb08f"},"schema_version":"1.0","source":{"id":"2407.19669","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.19669","created_at":"2026-07-05T09:20:01Z"},{"alias_kind":"arxiv_version","alias_value":"2407.19669v2","created_at":"2026-07-05T09:20:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19669","created_at":"2026-07-05T09:20:01Z"},{"alias_kind":"pith_short_12","alias_value":"WDXXXGLW446B","created_at":"2026-07-05T09:20:01Z"},{"alias_kind":"pith_short_16","alias_value":"WDXXXGLW446BC2XZ","created_at":"2026-07-05T09:20:01Z"},{"alias_kind":"pith_short_8","alias_value":"WDXXXGLW","created_at":"2026-07-05T09:20:01Z"}],"graph_snapshots":[{"event_id":"sha256:0ecede3bd2103b57a0af08f53c52cf3bfb844f5c18d18c5b824bbefd05ddfa04","target":"graph","created_at":"2026-07-05T09:20:01Z","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/2407.19669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present systematic efforts in building long-context multilingual text representation model (TRM) and reranker from scratch for text retrieval. We first introduce a text encoder (base size) enhanced with RoPE and unpadding, pre-trained in a native 8192-token context (longer than 512 of previous multilingual encoders). Then we construct a hybrid TRM and a cross-encoder reranker by contrastive learning. Evaluations show that our text encoder outperforms the same-sized previous state-of-the-art XLM-R. Meanwhile, our TRM and reranker match the performance of large-sized state-of-the-art BGE-M3 m","authors_text":"Baosong Yang, Dingkun Long, Fei Huang, Huan Lin, Jialong Tang, Meishan Zhang, Min Zhang, Pengjun Xie, Wenjie Li, Wen Xie, Xin Zhang, Yanzhao Zhang, Ziqi Dai","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-29T03:12:28Z","title":"mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19669","kind":"arxiv","version":2},"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:be27411f89515b008ba1b87f37e7357652a22919776297d4ead9bd3d2df7c70c","target":"record","created_at":"2026-07-05T09:20:01Z","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":"f5bb40bb6bcfb868836a5af7ade5537e8a6c99301976ce2e7dda353ee06e2d55","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-29T03:12:28Z","title_canon_sha256":"4147663170abb3c27758a09e7088921a09fbac34bc18eb491a29c780a52bb08f"},"schema_version":"1.0","source":{"id":"2407.19669","kind":"arxiv","version":2}},"canonical_sha256":"b0ef7b9976e73c116af91c6453dbc4a4a87e5181b4ed7dec92c232459c375aa2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0ef7b9976e73c116af91c6453dbc4a4a87e5181b4ed7dec92c232459c375aa2","first_computed_at":"2026-07-05T09:20:01.529818Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:01.529818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G2L4ZkStffVL/HAcO9yJofYFBZadq6I/SevAxofYiq2povmyNMoDU492rKsAcQCvD2gDkkFWg01lbWwh9zbaCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:01.530251Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.19669","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be27411f89515b008ba1b87f37e7357652a22919776297d4ead9bd3d2df7c70c","sha256:0ecede3bd2103b57a0af08f53c52cf3bfb844f5c18d18c5b824bbefd05ddfa04"],"state_sha256":"0d969b420602a32ef53b853c204959abe7add6caf455ab0e7f8f724025ced620"}