{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LRVJHGFPTOC4YGSR4EOZJCFCNB","short_pith_number":"pith:LRVJHGFP","canonical_record":{"source":{"id":"2412.04506","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T22:59:36Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"e44cedf4fe247fb39249605b90716b0d59dae33158894b352d3ca80a12096a39","abstract_canon_sha256":"a62580131331782baf88c668f7b7970a62645b4d6e0ea7edd43fd418d219831a"},"schema_version":"1.0"},"canonical_sha256":"5c6a9398af9b85cc1a51e11d9488a2687b8e51111d16e7956166e127a383e2e5","source":{"kind":"arxiv","id":"2412.04506","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LRVJHGFPTOC4YGSR4EOZJCFCNB","target":"record","payload":{"canonical_record":{"source":{"id":"2412.04506","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-03T22:59:36Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"e44cedf4fe247fb39249605b90716b0d59dae33158894b352d3ca80a12096a39","abstract_canon_sha256":"a62580131331782baf88c668f7b7970a62645b4d6e0ea7edd43fd418d219831a"},"schema_version":"1.0"},"canonical_sha256":"5c6a9398af9b85cc1a51e11d9488a2687b8e51111d16e7956166e127a383e2e5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:13.385539Z","signature_b64":"/kqtxAbWnwFz1J3uQ8g4wdZ/Q9Pf8kpc7sFj+K1fGtmW4o1IW7jX2H4+ArrGtaEriekWQnz9fuEa+95fqc7KCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c6a9398af9b85cc1a51e11d9488a2687b8e51111d16e7956166e127a383e2e5","last_reissued_at":"2026-07-05T09:49:13.385087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:13.385087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.04506","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IXS058GyrwOSCIR7aEBlb+NspOp/k7CmavVq9gRirD1mmxiwsCVtMlkMmoZIsEAW/OC7RPTLVY3KBf0jNWyIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:06:39.953052Z"},"content_sha256":"58774bb4e5e19aa379af13ff16c12518f872e7bcb1ec60de0f5bcc3a047a360d","schema_version":"1.0","event_id":"sha256:58774bb4e5e19aa379af13ff16c12518f872e7bcb1ec60de0f5bcc3a047a360d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LRVJHGFPTOC4YGSR4EOZJCFCNB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Arctic-Embed 2.0: Multilingual Retrieval Without Compromise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Daniel Campos, Gaurav Nuti, Luke Merrick, Puxuan Yu","submitted_at":"2024-12-03T22:59:36Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04506","kind":"arxiv","version":2},"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/2412.04506/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":"2026-07-05T09:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JqfPqZWfsLQCMTKfNMHPWq4WQ+pVD2BKDqEugXvphf1Zpcflqlf7DhY1cpYDpmaQor7uhrQ/iQ95BwtPKP70CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:06:39.953975Z"},"content_sha256":"ad131209a4206c6d04fccdcf7c999fb3813ab39eab28e0a551fcfb8c887742e0","schema_version":"1.0","event_id":"sha256:ad131209a4206c6d04fccdcf7c999fb3813ab39eab28e0a551fcfb8c887742e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LRVJHGFPTOC4YGSR4EOZJCFCNB/bundle.json","state_url":"https://pith.science/pith/LRVJHGFPTOC4YGSR4EOZJCFCNB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LRVJHGFPTOC4YGSR4EOZJCFCNB/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":"2026-08-04T03:06:39Z","links":{"resolver":"https://pith.science/pith/LRVJHGFPTOC4YGSR4EOZJCFCNB","bundle":"https://pith.science/pith/LRVJHGFPTOC4YGSR4EOZJCFCNB/bundle.json","state":"https://pith.science/pith/LRVJHGFPTOC4YGSR4EOZJCFCNB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LRVJHGFPTOC4YGSR4EOZJCFCNB/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bVtmN3595I61tUlIPzIaVJejyUqo4ViYa6oR2jC7mSpx4oADVcPPSE6ETqo0hqnaLifi9sAJ21d7TUmgmtkCBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:06:39.960298Z","bundle_sha256":"965f7f1ea8a972beb40eb7e1b674167bab21989f4b0d973ffa00fe7de21a0dec"}}