{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WNAEULL3X5XJFCNRGE547PTOI4","short_pith_number":"pith:WNAEULL3","canonical_record":{"source":{"id":"2510.21364","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-24T11:48:49Z","cross_cats_sorted":[],"title_canon_sha256":"dd2cdb6bb1d6c66c882abb0915d9ea23755af86193bed9950b9974179243f7c4","abstract_canon_sha256":"daee77b06061858ef0c3bf73a742da2259d507580adfef95558956ba14a7c24c"},"schema_version":"1.0"},"canonical_sha256":"b3404a2d7bbf6e9289b1313bcfbe6e4708b97d5d94b3a965db13fb7ec3ca7353","source":{"kind":"arxiv","id":"2510.21364","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.21364","created_at":"2026-06-02T02:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2510.21364v2","created_at":"2026-06-02T02:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.21364","created_at":"2026-06-02T02:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"WNAEULL3X5XJ","created_at":"2026-06-02T02:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"WNAEULL3X5XJFCNR","created_at":"2026-06-02T02:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"WNAEULL3","created_at":"2026-06-02T02:04:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WNAEULL3X5XJFCNRGE547PTOI4","target":"record","payload":{"canonical_record":{"source":{"id":"2510.21364","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-24T11:48:49Z","cross_cats_sorted":[],"title_canon_sha256":"dd2cdb6bb1d6c66c882abb0915d9ea23755af86193bed9950b9974179243f7c4","abstract_canon_sha256":"daee77b06061858ef0c3bf73a742da2259d507580adfef95558956ba14a7c24c"},"schema_version":"1.0"},"canonical_sha256":"b3404a2d7bbf6e9289b1313bcfbe6e4708b97d5d94b3a965db13fb7ec3ca7353","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:48.632536Z","signature_b64":"fzTnTS3SYg2F7oFxrCleZswvJSBpTtJ6QJsaocKucUHNvbM10zGtizD6Kf7Lx7sIUUXqMgJfaYIo90JEUwENAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3404a2d7bbf6e9289b1313bcfbe6e4708b97d5d94b3a965db13fb7ec3ca7353","last_reissued_at":"2026-06-02T02:04:48.632017Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:48.632017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.21364","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":"2026-06-02T02:04:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LSE6nobzXC5aueKNrkzNMpMPoL72ssWFC9Q6bTIkF3GrI7znLr8eVF9sP35Zmy3cYyvM3+Drqhw2gk19yBHWBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:26:28.809435Z"},"content_sha256":"c1c00b0446bc2a7aa2b67d3febc640a2f73628367df85c0d169c923511d7d541","schema_version":"1.0","event_id":"sha256:c1c00b0446bc2a7aa2b67d3febc640a2f73628367df85c0d169c923511d7d541"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WNAEULL3X5XJFCNRGE547PTOI4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SindBERT, the Sailor: Charting the Seas of Turkish NLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Raphael Schmitt, Stefan Schweter","submitted_at":"2025-10-24T11:48:49Z","abstract_excerpt":"Transformer models have revolutionized NLP, yet many morphologically rich languages remain underrepresented in large-scale pre-training efforts. With SindBERT, we set out to chart the seas of Turkish NLP, providing the first large-scale RoBERTa-based encoder for Turkish. Trained from scratch on 312~GB of Turkish text (mC4, OSCAR23, Wikipedia), SindBERT is released in both base and large configurations, representing the first large-scale encoder-only language model available for Turkish. We evaluate SindBERT on part-of-speech tagging, named entity recognition, offensive language detection, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.21364","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/2510.21364/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":"2026-06-02T02:04:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ap9kA4eHBpwMwttcM4IGME9VHcAFCB3I+ahToFU0Q3UNKC4sNBpME3wBFGwE+FEW42qvtzdgpedqfDvKLVyoAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:26:28.810248Z"},"content_sha256":"c17dfd0b9a0d9934039ebc494139e7533d2d379d45cae1905831f259ca944eee","schema_version":"1.0","event_id":"sha256:c17dfd0b9a0d9934039ebc494139e7533d2d379d45cae1905831f259ca944eee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WNAEULL3X5XJFCNRGE547PTOI4/bundle.json","state_url":"https://pith.science/pith/WNAEULL3X5XJFCNRGE547PTOI4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WNAEULL3X5XJFCNRGE547PTOI4/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":"2026-08-06T06:26:28Z","links":{"resolver":"https://pith.science/pith/WNAEULL3X5XJFCNRGE547PTOI4","bundle":"https://pith.science/pith/WNAEULL3X5XJFCNRGE547PTOI4/bundle.json","state":"https://pith.science/pith/WNAEULL3X5XJFCNRGE547PTOI4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WNAEULL3X5XJFCNRGE547PTOI4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WNAEULL3X5XJFCNRGE547PTOI4","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":"daee77b06061858ef0c3bf73a742da2259d507580adfef95558956ba14a7c24c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-24T11:48:49Z","title_canon_sha256":"dd2cdb6bb1d6c66c882abb0915d9ea23755af86193bed9950b9974179243f7c4"},"schema_version":"1.0","source":{"id":"2510.21364","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.21364","created_at":"2026-06-02T02:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2510.21364v2","created_at":"2026-06-02T02:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.21364","created_at":"2026-06-02T02:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"WNAEULL3X5XJ","created_at":"2026-06-02T02:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"WNAEULL3X5XJFCNR","created_at":"2026-06-02T02:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"WNAEULL3","created_at":"2026-06-02T02:04:48Z"}],"graph_snapshots":[{"event_id":"sha256:c17dfd0b9a0d9934039ebc494139e7533d2d379d45cae1905831f259ca944eee","target":"graph","created_at":"2026-06-02T02:04:48Z","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/2510.21364/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer models have revolutionized NLP, yet many morphologically rich languages remain underrepresented in large-scale pre-training efforts. With SindBERT, we set out to chart the seas of Turkish NLP, providing the first large-scale RoBERTa-based encoder for Turkish. Trained from scratch on 312~GB of Turkish text (mC4, OSCAR23, Wikipedia), SindBERT is released in both base and large configurations, representing the first large-scale encoder-only language model available for Turkish. We evaluate SindBERT on part-of-speech tagging, named entity recognition, offensive language detection, and ","authors_text":"Raphael Schmitt, Stefan Schweter","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-24T11:48:49Z","title":"SindBERT, the Sailor: Charting the Seas of Turkish NLP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.21364","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:c1c00b0446bc2a7aa2b67d3febc640a2f73628367df85c0d169c923511d7d541","target":"record","created_at":"2026-06-02T02:04:48Z","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":"daee77b06061858ef0c3bf73a742da2259d507580adfef95558956ba14a7c24c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-24T11:48:49Z","title_canon_sha256":"dd2cdb6bb1d6c66c882abb0915d9ea23755af86193bed9950b9974179243f7c4"},"schema_version":"1.0","source":{"id":"2510.21364","kind":"arxiv","version":2}},"canonical_sha256":"b3404a2d7bbf6e9289b1313bcfbe6e4708b97d5d94b3a965db13fb7ec3ca7353","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3404a2d7bbf6e9289b1313bcfbe6e4708b97d5d94b3a965db13fb7ec3ca7353","first_computed_at":"2026-06-02T02:04:48.632017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:48.632017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fzTnTS3SYg2F7oFxrCleZswvJSBpTtJ6QJsaocKucUHNvbM10zGtizD6Kf7Lx7sIUUXqMgJfaYIo90JEUwENAA==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:48.632536Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.21364","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1c00b0446bc2a7aa2b67d3febc640a2f73628367df85c0d169c923511d7d541","sha256:c17dfd0b9a0d9934039ebc494139e7533d2d379d45cae1905831f259ca944eee"],"state_sha256":"861455ec4d769bc180723ab16a498d5563810980d9d8730293db230fefce5ede"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xHgwzpJjKrGKy8H1hhltw9WanH+XdCpNER7fRBeWIURsOF3MBEdwCqz8LA8wULy4nZk74TbKjXJZehoy6zVgBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:26:28.816542Z","bundle_sha256":"168a6f39d604a5861b41407357544b074451a31aaf4b15082bc11e14b81ef741"}}