{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:T5Y4JCCHSWV6NIJHFIQ7QOZG62","short_pith_number":"pith:T5Y4JCCH","canonical_record":{"source":{"id":"2606.26015","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T16:36:11Z","cross_cats_sorted":[],"title_canon_sha256":"79c496c4190cb4b716089886accaf66129fe5beb44a4793a94fa465bc6c150d0","abstract_canon_sha256":"427a09ed526c4de31329d06e3a300cdf46f60fad16d2e1efc3e91684fb4c9c09"},"schema_version":"1.0"},"canonical_sha256":"9f71c4884795abe6a1272a21f83b26f689b1c5da3ed504609bb8904ee29c1669","source":{"kind":"arxiv","id":"2606.26015","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26015","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26015v1","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26015","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"pith_short_12","alias_value":"T5Y4JCCHSWV6","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"pith_short_16","alias_value":"T5Y4JCCHSWV6NIJH","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"pith_short_8","alias_value":"T5Y4JCCH","created_at":"2026-06-25T01:18:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:T5Y4JCCHSWV6NIJHFIQ7QOZG62","target":"record","payload":{"canonical_record":{"source":{"id":"2606.26015","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T16:36:11Z","cross_cats_sorted":[],"title_canon_sha256":"79c496c4190cb4b716089886accaf66129fe5beb44a4793a94fa465bc6c150d0","abstract_canon_sha256":"427a09ed526c4de31329d06e3a300cdf46f60fad16d2e1efc3e91684fb4c9c09"},"schema_version":"1.0"},"canonical_sha256":"9f71c4884795abe6a1272a21f83b26f689b1c5da3ed504609bb8904ee29c1669","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:45.929677Z","signature_b64":"MJPr3Sy5YZ3RzGabZCQz0s75tDR7tmJMaVNgtOsPdb9+j1FABYqBH2hywEjC5xOkGltJAG1H9WLV7/UItsbJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f71c4884795abe6a1272a21f83b26f689b1c5da3ed504609bb8904ee29c1669","last_reissued_at":"2026-06-25T01:18:45.929246Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:45.929246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.26015","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":"2026-06-25T01:18:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M+xiees7iSxKAVWuSyk3sViUgoO2a4kbYFnqMcmT53qKtwNgvq029hoRl9/dfLb0kB6Q9hS7yxuJC92YkYDrBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:12:52.718798Z"},"content_sha256":"c5b150df36a073d37b7eca6eecb3746e183b7f4727158d7eb9f562ac639981f3","schema_version":"1.0","event_id":"sha256:c5b150df36a073d37b7eca6eecb3746e183b7f4727158d7eb9f562ac639981f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:T5Y4JCCHSWV6NIJHFIQ7QOZG62","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Panchenko, Artyom Mazur, Bogdan Monogov, Bulat Khakimov, Daniil Antonov, Ilseyar Alimova, Vitaliy Egorov, Vsevolod Karimov","submitted_at":"2026-06-24T16:36:11Z","abstract_excerpt":"Text detoxification, the automated detection and mitigation of abusive and harmful content, is essential for ensuring the safety of online communities and protecting users. However, low resource languages such as Tatar have received little research attention. In this paper we present Tatoxa, a novel state-of-the-art system for text detoxification in the Tatar language. Comparative experiments show that the proposed approach outperforms existing open source and proprietary commercial LLMs on key quality metrics. We also introduce a new dataset for text detoxification in Tatar, designed for fine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26015","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/2606.26015/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":"2026-06-25T01:18:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MhsPbwRQrN4xFzRySh7+OAYAYe8bvr76+/6vL+CsJqCjOYGVkL6fgGrxdQ2yHiq5dgiBcGJZ9P9JQXAEYcGTAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:12:52.719232Z"},"content_sha256":"4c9eac1f08fe5716a2a7cc3769bab4676a0e11effede22ac101f6ee5b5b86e1f","schema_version":"1.0","event_id":"sha256:4c9eac1f08fe5716a2a7cc3769bab4676a0e11effede22ac101f6ee5b5b86e1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T5Y4JCCHSWV6NIJHFIQ7QOZG62/bundle.json","state_url":"https://pith.science/pith/T5Y4JCCHSWV6NIJHFIQ7QOZG62/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T5Y4JCCHSWV6NIJHFIQ7QOZG62/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":"2026-08-06T19:12:52Z","links":{"resolver":"https://pith.science/pith/T5Y4JCCHSWV6NIJHFIQ7QOZG62","bundle":"https://pith.science/pith/T5Y4JCCHSWV6NIJHFIQ7QOZG62/bundle.json","state":"https://pith.science/pith/T5Y4JCCHSWV6NIJHFIQ7QOZG62/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T5Y4JCCHSWV6NIJHFIQ7QOZG62/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T5Y4JCCHSWV6NIJHFIQ7QOZG62","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":"427a09ed526c4de31329d06e3a300cdf46f60fad16d2e1efc3e91684fb4c9c09","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T16:36:11Z","title_canon_sha256":"79c496c4190cb4b716089886accaf66129fe5beb44a4793a94fa465bc6c150d0"},"schema_version":"1.0","source":{"id":"2606.26015","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26015","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26015v1","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26015","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"pith_short_12","alias_value":"T5Y4JCCHSWV6","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"pith_short_16","alias_value":"T5Y4JCCHSWV6NIJH","created_at":"2026-06-25T01:18:45Z"},{"alias_kind":"pith_short_8","alias_value":"T5Y4JCCH","created_at":"2026-06-25T01:18:45Z"}],"graph_snapshots":[{"event_id":"sha256:4c9eac1f08fe5716a2a7cc3769bab4676a0e11effede22ac101f6ee5b5b86e1f","target":"graph","created_at":"2026-06-25T01:18:45Z","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/2606.26015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text detoxification, the automated detection and mitigation of abusive and harmful content, is essential for ensuring the safety of online communities and protecting users. However, low resource languages such as Tatar have received little research attention. In this paper we present Tatoxa, a novel state-of-the-art system for text detoxification in the Tatar language. Comparative experiments show that the proposed approach outperforms existing open source and proprietary commercial LLMs on key quality metrics. We also introduce a new dataset for text detoxification in Tatar, designed for fine","authors_text":"Alexander Panchenko, Artyom Mazur, Bogdan Monogov, Bulat Khakimov, Daniil Antonov, Ilseyar Alimova, Vitaliy Egorov, Vsevolod Karimov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T16:36:11Z","title":"The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26015","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:c5b150df36a073d37b7eca6eecb3746e183b7f4727158d7eb9f562ac639981f3","target":"record","created_at":"2026-06-25T01:18:45Z","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":"427a09ed526c4de31329d06e3a300cdf46f60fad16d2e1efc3e91684fb4c9c09","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T16:36:11Z","title_canon_sha256":"79c496c4190cb4b716089886accaf66129fe5beb44a4793a94fa465bc6c150d0"},"schema_version":"1.0","source":{"id":"2606.26015","kind":"arxiv","version":1}},"canonical_sha256":"9f71c4884795abe6a1272a21f83b26f689b1c5da3ed504609bb8904ee29c1669","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f71c4884795abe6a1272a21f83b26f689b1c5da3ed504609bb8904ee29c1669","first_computed_at":"2026-06-25T01:18:45.929246Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:45.929246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MJPr3Sy5YZ3RzGabZCQz0s75tDR7tmJMaVNgtOsPdb9+j1FABYqBH2hywEjC5xOkGltJAG1H9WLV7/UItsbJCw==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:45.929677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.26015","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5b150df36a073d37b7eca6eecb3746e183b7f4727158d7eb9f562ac639981f3","sha256:4c9eac1f08fe5716a2a7cc3769bab4676a0e11effede22ac101f6ee5b5b86e1f"],"state_sha256":"995044390642c53a46ebd15dd3c5dd3f82a2e3c9e78fcc2ce706294065000b7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4OPIj/rYLlxWpEduKdbuZuipPS6pblq0X6UWFG+WXu3SBf5IaR4AlHIsEIQcJ620BjwZPRkR8Gh9oExqcl87BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:12:52.721802Z","bundle_sha256":"636ed960c6b7502fbe96196a80a61c962cc37188e022b362703dfbb4c882b15a"}}