{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LRVJHGFPTOC4YGSR4EOZJCFCNB","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":"a62580131331782baf88c668f7b7970a62645b4d6e0ea7edd43fd418d219831a","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T22:59:36Z","title_canon_sha256":"e44cedf4fe247fb39249605b90716b0d59dae33158894b352d3ca80a12096a39"},"schema_version":"1.0","source":{"id":"2412.04506","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.04506","created_at":"2026-07-05T09:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"2412.04506v2","created_at":"2026-07-05T09:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04506","created_at":"2026-07-05T09:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"LRVJHGFPTOC4","created_at":"2026-07-05T09:49:13Z"},{"alias_kind":"pith_short_16","alias_value":"LRVJHGFPTOC4YGSR","created_at":"2026-07-05T09:49:13Z"},{"alias_kind":"pith_short_8","alias_value":"LRVJHGFP","created_at":"2026-07-05T09:49:13Z"}],"graph_snapshots":[{"event_id":"sha256:ad131209a4206c6d04fccdcf7c999fb3813ab39eab28e0a551fcfb8c887742e0","target":"graph","created_at":"2026-07-05T09:49:13Z","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/2412.04506/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents the training methodology of Arctic-Embed 2.0, a set of open-source text embedding models built for accurate and efficient multilingual retrieval. While prior works have suffered from degraded English retrieval quality, Arctic-Embed 2.0 delivers competitive retrieval quality on multilingual and English-only benchmarks, and supports Matryoshka Representation Learning (MRL) for efficient embedding storage with significantly lower compressed quality degradation compared to alternatives. We detail the design and implementation, presenting several important open research question","authors_text":"Daniel Campos, Gaurav Nuti, Luke Merrick, Puxuan Yu","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T22:59:36Z","title":"Arctic-Embed 2.0: Multilingual Retrieval Without Compromise"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04506","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":"sha256:58774bb4e5e19aa379af13ff16c12518f872e7bcb1ec60de0f5bcc3a047a360d","target":"record","created_at":"2026-07-05T09:49:13Z","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":"a62580131331782baf88c668f7b7970a62645b4d6e0ea7edd43fd418d219831a","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T22:59:36Z","title_canon_sha256":"e44cedf4fe247fb39249605b90716b0d59dae33158894b352d3ca80a12096a39"},"schema_version":"1.0","source":{"id":"2412.04506","kind":"arxiv","version":2}},"canonical_sha256":"5c6a9398af9b85cc1a51e11d9488a2687b8e51111d16e7956166e127a383e2e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c6a9398af9b85cc1a51e11d9488a2687b8e51111d16e7956166e127a383e2e5","first_computed_at":"2026-07-05T09:49:13.385087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:13.385087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/kqtxAbWnwFz1J3uQ8g4wdZ/Q9Pf8kpc7sFj+K1fGtmW4o1IW7jX2H4+ArrGtaEriekWQnz9fuEa+95fqc7KCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:13.385539Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.04506","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58774bb4e5e19aa379af13ff16c12518f872e7bcb1ec60de0f5bcc3a047a360d","sha256:ad131209a4206c6d04fccdcf7c999fb3813ab39eab28e0a551fcfb8c887742e0"],"state_sha256":"55ca1fd3f07fb4d5e0ad19d26e6fe06c37e1fae8df645113c6c94ace295e4fdc"}