{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AF27BFYD6CEHHSWHOF2SYL6D52","short_pith_number":"pith:AF27BFYD","canonical_record":{"source":{"id":"2505.11026","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T09:22:07Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"title_canon_sha256":"dde1304fbab7674d49ef9087e1b9c84ce525ea16657c6f3ee9bafb42e8370314","abstract_canon_sha256":"d7590d9724e58934afc0855d0be309b4e735babe2805bd43b230ec22e76bef87"},"schema_version":"1.0"},"canonical_sha256":"0175f09703f08873cac771752c2fc3ee99e7c50bb57fc30ad18d6a097b7aad05","source":{"kind":"arxiv","id":"2505.11026","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11026","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11026v1","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11026","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"pith_short_12","alias_value":"AF27BFYD6CEH","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"pith_short_16","alias_value":"AF27BFYD6CEHHSWH","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"pith_short_8","alias_value":"AF27BFYD","created_at":"2026-07-05T11:04:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AF27BFYD6CEHHSWHOF2SYL6D52","target":"record","payload":{"canonical_record":{"source":{"id":"2505.11026","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T09:22:07Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"title_canon_sha256":"dde1304fbab7674d49ef9087e1b9c84ce525ea16657c6f3ee9bafb42e8370314","abstract_canon_sha256":"d7590d9724e58934afc0855d0be309b4e735babe2805bd43b230ec22e76bef87"},"schema_version":"1.0"},"canonical_sha256":"0175f09703f08873cac771752c2fc3ee99e7c50bb57fc30ad18d6a097b7aad05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:09.640089Z","signature_b64":"h6hvVEox0pkDizpfRAcPplksLb8kTCqUbDfFd+gw9DN+kIZ811gcE4m/RvvoujSNXiIbcYTfW2eMcGHYq0j0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0175f09703f08873cac771752c2fc3ee99e7c50bb57fc30ad18d6a097b7aad05","last_reissued_at":"2026-07-05T11:04:09.639600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:09.639600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.11026","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":"2026-07-05T11:04:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2siZEwDQMavtbFiBBcarsYdS/+0ihwWWixak/3aeahePGvclab8oMUXU3hTZ8ZbviVojM1hID3FLFz6tlx7FCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:29:48.592939Z"},"content_sha256":"3941520f92e9b1ad85db7f47bb8ff8e923ec8a13d614be813e14ad7624fd1d48","schema_version":"1.0","event_id":"sha256:3941520f92e9b1ad85db7f47bb8ff8e923ec8a13d614be813e14ad7624fd1d48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AF27BFYD6CEHHSWHOF2SYL6D52","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StRuCom: A Novel Dataset of Structured Code Comments in Russian","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Maria Dziuba, Valentin Malykh","submitted_at":"2025-05-16T09:22:07Z","abstract_excerpt":"Structured code comments in docstring format are essential for code comprehension and maintenance, but existing machine learning models for their generation perform poorly for Russian compared to English. To bridge this gap, we present StRuCom - the first large-scale dataset (153K examples) specifically designed for Russian code documentation. Unlike machine-translated English datasets that distort terminology (e.g., technical loanwords vs. literal translations) and docstring structures, StRuCom combines human-written comments from Russian GitHub repositories with synthetically generated ones,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11026","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/2505.11026/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":"2026-07-05T11:04:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uiv7AYQF2hNypvI0qzng0l1AC2S9nZ9oIaeS4ilTDR1mVlS3skf8fLuUJkA7+8ef/3x83a7mEMShOQCVbIM9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:29:48.593520Z"},"content_sha256":"427ac08964190043e5fb5b35bfdf8dd09bb57e0710af5a73834664a60b6c90b7","schema_version":"1.0","event_id":"sha256:427ac08964190043e5fb5b35bfdf8dd09bb57e0710af5a73834664a60b6c90b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AF27BFYD6CEHHSWHOF2SYL6D52/bundle.json","state_url":"https://pith.science/pith/AF27BFYD6CEHHSWHOF2SYL6D52/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AF27BFYD6CEHHSWHOF2SYL6D52/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":"2026-08-09T00:29:48Z","links":{"resolver":"https://pith.science/pith/AF27BFYD6CEHHSWHOF2SYL6D52","bundle":"https://pith.science/pith/AF27BFYD6CEHHSWHOF2SYL6D52/bundle.json","state":"https://pith.science/pith/AF27BFYD6CEHHSWHOF2SYL6D52/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AF27BFYD6CEHHSWHOF2SYL6D52/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AF27BFYD6CEHHSWHOF2SYL6D52","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":"d7590d9724e58934afc0855d0be309b4e735babe2805bd43b230ec22e76bef87","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T09:22:07Z","title_canon_sha256":"dde1304fbab7674d49ef9087e1b9c84ce525ea16657c6f3ee9bafb42e8370314"},"schema_version":"1.0","source":{"id":"2505.11026","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11026","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11026v1","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11026","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"pith_short_12","alias_value":"AF27BFYD6CEH","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"pith_short_16","alias_value":"AF27BFYD6CEHHSWH","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"pith_short_8","alias_value":"AF27BFYD","created_at":"2026-07-05T11:04:09Z"}],"graph_snapshots":[{"event_id":"sha256:427ac08964190043e5fb5b35bfdf8dd09bb57e0710af5a73834664a60b6c90b7","target":"graph","created_at":"2026-07-05T11:04:09Z","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/2505.11026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Structured code comments in docstring format are essential for code comprehension and maintenance, but existing machine learning models for their generation perform poorly for Russian compared to English. To bridge this gap, we present StRuCom - the first large-scale dataset (153K examples) specifically designed for Russian code documentation. Unlike machine-translated English datasets that distort terminology (e.g., technical loanwords vs. literal translations) and docstring structures, StRuCom combines human-written comments from Russian GitHub repositories with synthetically generated ones,","authors_text":"Maria Dziuba, Valentin Malykh","cross_cats":["cs.AI","cs.LG","cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T09:22:07Z","title":"StRuCom: A Novel Dataset of Structured Code Comments in Russian"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11026","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":"sha256:3941520f92e9b1ad85db7f47bb8ff8e923ec8a13d614be813e14ad7624fd1d48","target":"record","created_at":"2026-07-05T11:04:09Z","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":"d7590d9724e58934afc0855d0be309b4e735babe2805bd43b230ec22e76bef87","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T09:22:07Z","title_canon_sha256":"dde1304fbab7674d49ef9087e1b9c84ce525ea16657c6f3ee9bafb42e8370314"},"schema_version":"1.0","source":{"id":"2505.11026","kind":"arxiv","version":1}},"canonical_sha256":"0175f09703f08873cac771752c2fc3ee99e7c50bb57fc30ad18d6a097b7aad05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0175f09703f08873cac771752c2fc3ee99e7c50bb57fc30ad18d6a097b7aad05","first_computed_at":"2026-07-05T11:04:09.639600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:09.639600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h6hvVEox0pkDizpfRAcPplksLb8kTCqUbDfFd+gw9DN+kIZ811gcE4m/RvvoujSNXiIbcYTfW2eMcGHYq0j0Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:09.640089Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11026","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3941520f92e9b1ad85db7f47bb8ff8e923ec8a13d614be813e14ad7624fd1d48","sha256:427ac08964190043e5fb5b35bfdf8dd09bb57e0710af5a73834664a60b6c90b7"],"state_sha256":"e1ed772a7369ea257f3ce213a2f941c0e9ccb38751b5f4afc66cd26c532aee9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ra4k7dNtcxoFx+gWCl9ho2pa3zg7Q1FAXYj2z/XfUfAMj7aJOANNYxullLyqKI/KKZeQiLztSff01HN7naziAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:29:48.597004Z","bundle_sha256":"1b68dccbdf66ccd73b69322e9e07477d5a5bb460ceda7ff95abd6989802c9d94"}}