{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:USZW23UF6GNVZYNABISGHI2S2V","short_pith_number":"pith:USZW23UF","canonical_record":{"source":{"id":"2504.12879","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-17T12:11:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"05742a482f574c3b6e07c70e0f1d10cc16f88d81482b9809223625af5513e808","abstract_canon_sha256":"a2cd3af1f6c4f17c0493b7196341ee913f70bb10a0d563a2c364f6d20b963358"},"schema_version":"1.0"},"canonical_sha256":"a4b36d6e85f19b5ce1a00a2463a352d56fd4bdd9f5024ac64e84a8777b281d4e","source":{"kind":"arxiv","id":"2504.12879","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12879","created_at":"2026-07-05T10:50:34Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12879v1","created_at":"2026-07-05T10:50:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12879","created_at":"2026-07-05T10:50:34Z"},{"alias_kind":"pith_short_12","alias_value":"USZW23UF6GNV","created_at":"2026-07-05T10:50:34Z"},{"alias_kind":"pith_short_16","alias_value":"USZW23UF6GNVZYNA","created_at":"2026-07-05T10:50:34Z"},{"alias_kind":"pith_short_8","alias_value":"USZW23UF","created_at":"2026-07-05T10:50:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:USZW23UF6GNVZYNABISGHI2S2V","target":"record","payload":{"canonical_record":{"source":{"id":"2504.12879","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-17T12:11:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"05742a482f574c3b6e07c70e0f1d10cc16f88d81482b9809223625af5513e808","abstract_canon_sha256":"a2cd3af1f6c4f17c0493b7196341ee913f70bb10a0d563a2c364f6d20b963358"},"schema_version":"1.0"},"canonical_sha256":"a4b36d6e85f19b5ce1a00a2463a352d56fd4bdd9f5024ac64e84a8777b281d4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:34.162117Z","signature_b64":"TuLevoXAN9uFHF4eCB8ZCrvY0UU6Q2xMoNOtzhnniBvS9RIBOsH8sRdJH+3PVgec4Eidgk6vcZX6yGXdls3ICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4b36d6e85f19b5ce1a00a2463a352d56fd4bdd9f5024ac64e84a8777b281d4e","last_reissued_at":"2026-07-05T10:50:34.161645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:34.161645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.12879","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:50:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FvnohrCAb7d419pVi/hq7qfzXw1YpQC2k3LlVATzy5W6+oPJ854a2HQR88omaE9Zj6hBLhKAbGIVZVkU5KNMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T12:47:50.774997Z"},"content_sha256":"852a25355a13b891a7b0014d6d3fb4dbdab7a3f08263ca3f41a57867a63b305f","schema_version":"1.0","event_id":"sha256:852a25355a13b891a7b0014d6d3fb4dbdab7a3f08263ca3f41a57867a63b305f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:USZW23UF6GNVZYNABISGHI2S2V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Building Russian Benchmark for Evaluation of Information Retrieval Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Evgeny Kozhevnikov, Grigory Kovalev, Max Kornilov, Mikhail Tikhomirov, Natalia Loukachevitch","submitted_at":"2025-04-17T12:11:14Z","abstract_excerpt":"We introduce RusBEIR, a comprehensive benchmark designed for zero-shot evaluation of information retrieval (IR) models in the Russian language. Comprising 17 datasets from various domains, it integrates adapted, translated, and newly created datasets, enabling systematic comparison of lexical and neural models. Our study highlights the importance of preprocessing for lexical models in morphologically rich languages and confirms BM25 as a strong baseline for full-document retrieval. Neural models, such as mE5-large and BGE-M3, demonstrate superior performance on most datasets, but face challeng"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12879","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/2504.12879/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":"2026-07-05T10:50:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e53F7DhcEsjpFm6mW2DXpV2DX6uerlPLnBxJVoI6ZxvOiRPfl/mgcJNwzA8wKQnFJnkbomAHw5C9bbUvwSVOAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T12:47:50.775523Z"},"content_sha256":"0b171a5052f266ddaa13f77330bc5663efdb8eefeed41ac999b6b537e523198d","schema_version":"1.0","event_id":"sha256:0b171a5052f266ddaa13f77330bc5663efdb8eefeed41ac999b6b537e523198d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/USZW23UF6GNVZYNABISGHI2S2V/bundle.json","state_url":"https://pith.science/pith/USZW23UF6GNVZYNABISGHI2S2V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/USZW23UF6GNVZYNABISGHI2S2V/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":"2026-08-23T12:47:50Z","links":{"resolver":"https://pith.science/pith/USZW23UF6GNVZYNABISGHI2S2V","bundle":"https://pith.science/pith/USZW23UF6GNVZYNABISGHI2S2V/bundle.json","state":"https://pith.science/pith/USZW23UF6GNVZYNABISGHI2S2V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/USZW23UF6GNVZYNABISGHI2S2V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:USZW23UF6GNVZYNABISGHI2S2V","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":"a2cd3af1f6c4f17c0493b7196341ee913f70bb10a0d563a2c364f6d20b963358","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-17T12:11:14Z","title_canon_sha256":"05742a482f574c3b6e07c70e0f1d10cc16f88d81482b9809223625af5513e808"},"schema_version":"1.0","source":{"id":"2504.12879","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.12879","created_at":"2026-07-05T10:50:34Z"},{"alias_kind":"arxiv_version","alias_value":"2504.12879v1","created_at":"2026-07-05T10:50:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.12879","created_at":"2026-07-05T10:50:34Z"},{"alias_kind":"pith_short_12","alias_value":"USZW23UF6GNV","created_at":"2026-07-05T10:50:34Z"},{"alias_kind":"pith_short_16","alias_value":"USZW23UF6GNVZYNA","created_at":"2026-07-05T10:50:34Z"},{"alias_kind":"pith_short_8","alias_value":"USZW23UF","created_at":"2026-07-05T10:50:34Z"}],"graph_snapshots":[{"event_id":"sha256:0b171a5052f266ddaa13f77330bc5663efdb8eefeed41ac999b6b537e523198d","target":"graph","created_at":"2026-07-05T10:50:34Z","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/2504.12879/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce RusBEIR, a comprehensive benchmark designed for zero-shot evaluation of information retrieval (IR) models in the Russian language. Comprising 17 datasets from various domains, it integrates adapted, translated, and newly created datasets, enabling systematic comparison of lexical and neural models. Our study highlights the importance of preprocessing for lexical models in morphologically rich languages and confirms BM25 as a strong baseline for full-document retrieval. Neural models, such as mE5-large and BGE-M3, demonstrate superior performance on most datasets, but face challeng","authors_text":"Evgeny Kozhevnikov, Grigory Kovalev, Max Kornilov, Mikhail Tikhomirov, Natalia Loukachevitch","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-17T12:11:14Z","title":"Building Russian Benchmark for Evaluation of Information Retrieval Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.12879","kind":"arxiv","version":1},"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":"sha256:852a25355a13b891a7b0014d6d3fb4dbdab7a3f08263ca3f41a57867a63b305f","target":"record","created_at":"2026-07-05T10:50:34Z","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":"a2cd3af1f6c4f17c0493b7196341ee913f70bb10a0d563a2c364f6d20b963358","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-17T12:11:14Z","title_canon_sha256":"05742a482f574c3b6e07c70e0f1d10cc16f88d81482b9809223625af5513e808"},"schema_version":"1.0","source":{"id":"2504.12879","kind":"arxiv","version":1}},"canonical_sha256":"a4b36d6e85f19b5ce1a00a2463a352d56fd4bdd9f5024ac64e84a8777b281d4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4b36d6e85f19b5ce1a00a2463a352d56fd4bdd9f5024ac64e84a8777b281d4e","first_computed_at":"2026-07-05T10:50:34.161645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:34.161645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TuLevoXAN9uFHF4eCB8ZCrvY0UU6Q2xMoNOtzhnniBvS9RIBOsH8sRdJH+3PVgec4Eidgk6vcZX6yGXdls3ICQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:34.162117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.12879","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:852a25355a13b891a7b0014d6d3fb4dbdab7a3f08263ca3f41a57867a63b305f","sha256:0b171a5052f266ddaa13f77330bc5663efdb8eefeed41ac999b6b537e523198d"],"state_sha256":"6ff11d7069b823e6e330d9e56e712012ae27ac4a78104bf137a9774e53170a27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BPMmHHH5qw6+wRWMVwdseWLLKZsCpVFHkN0T+CpM8dgdeAm4TznOxBjUaP/KjE1CqTQkbhmAA3+LLIAYHV8CBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T12:47:50.779208Z","bundle_sha256":"da2784e404d5261854721ce1adff4873ed92e780f827877258332a9a05357a0c"}}