{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QYS6CXD4BLYSIKXJB4TVAQOBOI","short_pith_number":"pith:QYS6CXD4","canonical_record":{"source":{"id":"2503.13102","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T12:15:16Z","cross_cats_sorted":[],"title_canon_sha256":"1a0556ecc79be01a648820a3e1c345a40b55328fa370192860a2df96f5e282a6","abstract_canon_sha256":"2b7821e85450b17ecd87f18b0a2a75cacb1cefed3aa7d684354c73194da8ce1b"},"schema_version":"1.0"},"canonical_sha256":"8625e15c7c0af1242ae90f275041c172310c2736a751e02c8aca404c99b8fcf8","source":{"kind":"arxiv","id":"2503.13102","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13102","created_at":"2026-07-05T11:21:44Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13102v2","created_at":"2026-07-05T11:21:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13102","created_at":"2026-07-05T11:21:44Z"},{"alias_kind":"pith_short_12","alias_value":"QYS6CXD4BLYS","created_at":"2026-07-05T11:21:44Z"},{"alias_kind":"pith_short_16","alias_value":"QYS6CXD4BLYSIKXJ","created_at":"2026-07-05T11:21:44Z"},{"alias_kind":"pith_short_8","alias_value":"QYS6CXD4","created_at":"2026-07-05T11:21:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QYS6CXD4BLYSIKXJB4TVAQOBOI","target":"record","payload":{"canonical_record":{"source":{"id":"2503.13102","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T12:15:16Z","cross_cats_sorted":[],"title_canon_sha256":"1a0556ecc79be01a648820a3e1c345a40b55328fa370192860a2df96f5e282a6","abstract_canon_sha256":"2b7821e85450b17ecd87f18b0a2a75cacb1cefed3aa7d684354c73194da8ce1b"},"schema_version":"1.0"},"canonical_sha256":"8625e15c7c0af1242ae90f275041c172310c2736a751e02c8aca404c99b8fcf8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:44.314079Z","signature_b64":"99gcb5mlwftjYDWG8+Vi1lwnroeRrTt7kTYq1SEiAlXax8fm3UZNkb3oAfpEGgiIwcH+SGb44Uxab2MLtaMvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8625e15c7c0af1242ae90f275041c172310c2736a751e02c8aca404c99b8fcf8","last_reissued_at":"2026-07-05T11:21:44.313506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:44.313506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.13102","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":"2026-07-05T11:21:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S08ar3gDOhldoJr4WSGhUZXnVHLMcmYlmj6LOLimabIrdcxoe+5XpL+PeOUxT49x4sp5DLnRWUx0fQVJJFBUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T19:59:45.708671Z"},"content_sha256":"1ef66df76cfb10b0e143a958daf7339b214e513ba845ba5e1742bff12431ab9c","schema_version":"1.0","event_id":"sha256:1ef66df76cfb10b0e143a958daf7339b214e513ba845ba5e1742bff12431ab9c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QYS6CXD4BLYSIKXJB4TVAQOBOI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"REPA: Russian Error Types Annotation for Evaluating Text Generation and Judgment Capabilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alena Fenogenova, Alexander Pugachev, Ekaterina Artemova, Vladislav Mikhailov","submitted_at":"2025-03-17T12:15:16Z","abstract_excerpt":"Recent advances in large language models (LLMs) have introduced the novel paradigm of using LLMs as judges, where an LLM evaluates and scores the outputs of another LLM, which often correlates highly with human preferences. However, the use of LLM-as-a-judge has been primarily studied in English. In this paper, we evaluate this framework in Russian by introducing the Russian Error tyPes Annotation dataset (REPA), a dataset of 1k user queries and 2k LLM-generated responses. Human annotators labeled each response pair expressing their preferences across ten specific error types, as well as selec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13102","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/2503.13102/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":"2026-07-05T11:21:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dwstb/dn60YlKiAzMjr/cw3MAjiuSXKUndAIdLxrDUS1j2XYheaZj+tmzmDyezlZYnmY75zerAwuIPzkcSvaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T19:59:45.709197Z"},"content_sha256":"d000fa8190c20dfd59b5d56b8dff1b10095eb08f15c3a1edbfb5bd7e4dcefcf8","schema_version":"1.0","event_id":"sha256:d000fa8190c20dfd59b5d56b8dff1b10095eb08f15c3a1edbfb5bd7e4dcefcf8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QYS6CXD4BLYSIKXJB4TVAQOBOI/bundle.json","state_url":"https://pith.science/pith/QYS6CXD4BLYSIKXJB4TVAQOBOI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QYS6CXD4BLYSIKXJB4TVAQOBOI/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":"2026-08-22T19:59:45Z","links":{"resolver":"https://pith.science/pith/QYS6CXD4BLYSIKXJB4TVAQOBOI","bundle":"https://pith.science/pith/QYS6CXD4BLYSIKXJB4TVAQOBOI/bundle.json","state":"https://pith.science/pith/QYS6CXD4BLYSIKXJB4TVAQOBOI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QYS6CXD4BLYSIKXJB4TVAQOBOI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QYS6CXD4BLYSIKXJB4TVAQOBOI","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":"2b7821e85450b17ecd87f18b0a2a75cacb1cefed3aa7d684354c73194da8ce1b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T12:15:16Z","title_canon_sha256":"1a0556ecc79be01a648820a3e1c345a40b55328fa370192860a2df96f5e282a6"},"schema_version":"1.0","source":{"id":"2503.13102","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13102","created_at":"2026-07-05T11:21:44Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13102v2","created_at":"2026-07-05T11:21:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13102","created_at":"2026-07-05T11:21:44Z"},{"alias_kind":"pith_short_12","alias_value":"QYS6CXD4BLYS","created_at":"2026-07-05T11:21:44Z"},{"alias_kind":"pith_short_16","alias_value":"QYS6CXD4BLYSIKXJ","created_at":"2026-07-05T11:21:44Z"},{"alias_kind":"pith_short_8","alias_value":"QYS6CXD4","created_at":"2026-07-05T11:21:44Z"}],"graph_snapshots":[{"event_id":"sha256:d000fa8190c20dfd59b5d56b8dff1b10095eb08f15c3a1edbfb5bd7e4dcefcf8","target":"graph","created_at":"2026-07-05T11:21:44Z","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/2503.13102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models (LLMs) have introduced the novel paradigm of using LLMs as judges, where an LLM evaluates and scores the outputs of another LLM, which often correlates highly with human preferences. However, the use of LLM-as-a-judge has been primarily studied in English. In this paper, we evaluate this framework in Russian by introducing the Russian Error tyPes Annotation dataset (REPA), a dataset of 1k user queries and 2k LLM-generated responses. Human annotators labeled each response pair expressing their preferences across ten specific error types, as well as selec","authors_text":"Alena Fenogenova, Alexander Pugachev, Ekaterina Artemova, Vladislav Mikhailov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T12:15:16Z","title":"REPA: Russian Error Types Annotation for Evaluating Text Generation and Judgment Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13102","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":"sha256:1ef66df76cfb10b0e143a958daf7339b214e513ba845ba5e1742bff12431ab9c","target":"record","created_at":"2026-07-05T11:21:44Z","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":"2b7821e85450b17ecd87f18b0a2a75cacb1cefed3aa7d684354c73194da8ce1b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T12:15:16Z","title_canon_sha256":"1a0556ecc79be01a648820a3e1c345a40b55328fa370192860a2df96f5e282a6"},"schema_version":"1.0","source":{"id":"2503.13102","kind":"arxiv","version":2}},"canonical_sha256":"8625e15c7c0af1242ae90f275041c172310c2736a751e02c8aca404c99b8fcf8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8625e15c7c0af1242ae90f275041c172310c2736a751e02c8aca404c99b8fcf8","first_computed_at":"2026-07-05T11:21:44.313506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:44.313506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"99gcb5mlwftjYDWG8+Vi1lwnroeRrTt7kTYq1SEiAlXax8fm3UZNkb3oAfpEGgiIwcH+SGb44Uxab2MLtaMvDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:44.314079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.13102","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ef66df76cfb10b0e143a958daf7339b214e513ba845ba5e1742bff12431ab9c","sha256:d000fa8190c20dfd59b5d56b8dff1b10095eb08f15c3a1edbfb5bd7e4dcefcf8"],"state_sha256":"f99bf3a6d235fcba2bcf454c3c4bde77d52f6666c137b4de37696beb3990ba43"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QKQZ1ImGghSPjhL/TqLx3hsnMdgNbrT3w/H3uyfF/vyfeiEQzIhxgUYfyCNHTPMHO3vWNer4SusoY/T8Z+QlAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T19:59:45.713658Z","bundle_sha256":"1ca43d6c3b9867114703a8d5cc88c309a60824799e8d9fa6d48d5fe5201bf323"}}