{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PK22GE3BGDHZXT54YA2VBFGPKH","short_pith_number":"pith:PK22GE3B","canonical_record":{"source":{"id":"2408.12503","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T15:53:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b77533d3910edfa994cd12bf7d725ef3878ab952e94149f506970fbea79ccfad","abstract_canon_sha256":"a31cb30f048b60f5bc2456a78a883c8188d2f4af0c36e068b5f32e254fae7147"},"schema_version":"1.0"},"canonical_sha256":"7ab5a3136130cf9bcfbcc0355094cf51f74a662d692dfc9c4a2553da8bd140fc","source":{"kind":"arxiv","id":"2408.12503","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12503","created_at":"2026-07-05T10:08:20Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12503v2","created_at":"2026-07-05T10:08:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12503","created_at":"2026-07-05T10:08:20Z"},{"alias_kind":"pith_short_12","alias_value":"PK22GE3BGDHZ","created_at":"2026-07-05T10:08:20Z"},{"alias_kind":"pith_short_16","alias_value":"PK22GE3BGDHZXT54","created_at":"2026-07-05T10:08:20Z"},{"alias_kind":"pith_short_8","alias_value":"PK22GE3B","created_at":"2026-07-05T10:08:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PK22GE3BGDHZXT54YA2VBFGPKH","target":"record","payload":{"canonical_record":{"source":{"id":"2408.12503","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T15:53:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b77533d3910edfa994cd12bf7d725ef3878ab952e94149f506970fbea79ccfad","abstract_canon_sha256":"a31cb30f048b60f5bc2456a78a883c8188d2f4af0c36e068b5f32e254fae7147"},"schema_version":"1.0"},"canonical_sha256":"7ab5a3136130cf9bcfbcc0355094cf51f74a662d692dfc9c4a2553da8bd140fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:20.297045Z","signature_b64":"N+CUmIA9vypI1WaDHIuJypg6wvTnJUHQbwrN27G2ocdu0FHomcLKSLfiC6olk83eXZbzMmlIjXi3nxXmb1jlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ab5a3136130cf9bcfbcc0355094cf51f74a662d692dfc9c4a2553da8bd140fc","last_reissued_at":"2026-07-05T10:08:20.296620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:20.296620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.12503","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":"2026-07-05T10:08:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h0/Z6MWDP1BN9u4NN1tU8IELaGAiKoL0BL4mkvzMmrBbRy6k9d+zderl2Sad6Pgcpq87JJj0SpYJMj9Cudf2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:25:26.247463Z"},"content_sha256":"ca435c636d818e5d2e976245eeacf26d4e310108872129ea989dbf08f5edc3a9","schema_version":"1.0","event_id":"sha256:ca435c636d818e5d2e976245eeacf26d4e310108872129ea989dbf08f5edc3a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PK22GE3BGDHZXT54YA2VBFGPKH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Russian-focused embedders' exploration: ruMTEB benchmark and Russian embedding model design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alena Fenogenova, Alexander Abramov, Anna Maksimova, Artem Snegirev, Maria Tikhonova","submitted_at":"2024-08-22T15:53:23Z","abstract_excerpt":"Embedding models play a crucial role in Natural Language Processing (NLP) by creating text embeddings used in various tasks such as information retrieval and assessing semantic text similarity. This paper focuses on research related to embedding models in the Russian language. It introduces a new Russian-focused embedding model called ru-en-RoSBERTa and the ruMTEB benchmark, the Russian version extending the Massive Text Embedding Benchmark (MTEB). Our benchmark includes seven categories of tasks, such as semantic textual similarity, text classification, reranking, and retrieval.The research a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12503","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/2408.12503/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":"2026-07-05T10:08:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4yQ3DJRD3rnq0zf9NAcnBuvgVpYWBBVIjt5vkLku9MNenjQpr+AC8OvPD/ReLLVpA/gZJNS5QmWkzorX09V+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:25:26.247853Z"},"content_sha256":"c98cc0f6547243b8d96e68ead1048b29310d987bf7b3cab8ea19912fbe626137","schema_version":"1.0","event_id":"sha256:c98cc0f6547243b8d96e68ead1048b29310d987bf7b3cab8ea19912fbe626137"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PK22GE3BGDHZXT54YA2VBFGPKH/bundle.json","state_url":"https://pith.science/pith/PK22GE3BGDHZXT54YA2VBFGPKH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PK22GE3BGDHZXT54YA2VBFGPKH/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":"2026-07-06T20:25:26Z","links":{"resolver":"https://pith.science/pith/PK22GE3BGDHZXT54YA2VBFGPKH","bundle":"https://pith.science/pith/PK22GE3BGDHZXT54YA2VBFGPKH/bundle.json","state":"https://pith.science/pith/PK22GE3BGDHZXT54YA2VBFGPKH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PK22GE3BGDHZXT54YA2VBFGPKH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PK22GE3BGDHZXT54YA2VBFGPKH","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":"a31cb30f048b60f5bc2456a78a883c8188d2f4af0c36e068b5f32e254fae7147","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T15:53:23Z","title_canon_sha256":"b77533d3910edfa994cd12bf7d725ef3878ab952e94149f506970fbea79ccfad"},"schema_version":"1.0","source":{"id":"2408.12503","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12503","created_at":"2026-07-05T10:08:20Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12503v2","created_at":"2026-07-05T10:08:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12503","created_at":"2026-07-05T10:08:20Z"},{"alias_kind":"pith_short_12","alias_value":"PK22GE3BGDHZ","created_at":"2026-07-05T10:08:20Z"},{"alias_kind":"pith_short_16","alias_value":"PK22GE3BGDHZXT54","created_at":"2026-07-05T10:08:20Z"},{"alias_kind":"pith_short_8","alias_value":"PK22GE3B","created_at":"2026-07-05T10:08:20Z"}],"graph_snapshots":[{"event_id":"sha256:c98cc0f6547243b8d96e68ead1048b29310d987bf7b3cab8ea19912fbe626137","target":"graph","created_at":"2026-07-05T10:08:20Z","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/2408.12503/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Embedding models play a crucial role in Natural Language Processing (NLP) by creating text embeddings used in various tasks such as information retrieval and assessing semantic text similarity. This paper focuses on research related to embedding models in the Russian language. It introduces a new Russian-focused embedding model called ru-en-RoSBERTa and the ruMTEB benchmark, the Russian version extending the Massive Text Embedding Benchmark (MTEB). Our benchmark includes seven categories of tasks, such as semantic textual similarity, text classification, reranking, and retrieval.The research a","authors_text":"Alena Fenogenova, Alexander Abramov, Anna Maksimova, Artem Snegirev, Maria Tikhonova","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T15:53:23Z","title":"The Russian-focused embedders' exploration: ruMTEB benchmark and Russian embedding model design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12503","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:ca435c636d818e5d2e976245eeacf26d4e310108872129ea989dbf08f5edc3a9","target":"record","created_at":"2026-07-05T10:08:20Z","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":"a31cb30f048b60f5bc2456a78a883c8188d2f4af0c36e068b5f32e254fae7147","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-22T15:53:23Z","title_canon_sha256":"b77533d3910edfa994cd12bf7d725ef3878ab952e94149f506970fbea79ccfad"},"schema_version":"1.0","source":{"id":"2408.12503","kind":"arxiv","version":2}},"canonical_sha256":"7ab5a3136130cf9bcfbcc0355094cf51f74a662d692dfc9c4a2553da8bd140fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ab5a3136130cf9bcfbcc0355094cf51f74a662d692dfc9c4a2553da8bd140fc","first_computed_at":"2026-07-05T10:08:20.296620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:20.296620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N+CUmIA9vypI1WaDHIuJypg6wvTnJUHQbwrN27G2ocdu0FHomcLKSLfiC6olk83eXZbzMmlIjXi3nxXmb1jlBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:20.297045Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.12503","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca435c636d818e5d2e976245eeacf26d4e310108872129ea989dbf08f5edc3a9","sha256:c98cc0f6547243b8d96e68ead1048b29310d987bf7b3cab8ea19912fbe626137"],"state_sha256":"cc350a7402df6d4fee7b1ae511ad2e81aa10571eccf8c170bef1dc6e586a4533"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cj0HKprVV4W4MWbXU4IHScbP5xkeJpkGBYgaroKdvEowWE4i4YjOacqULglKbhj0e4BicYemvm64oiNJiu4fBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:25:26.249851Z","bundle_sha256":"6b9bd31cc464a072c7efa01e07de5f4241b944b33222f1d3b0490fb14557d7af"}}