{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BCPZQOFJVJDSUO2WQTHKIQ7PDJ","short_pith_number":"pith:BCPZQOFJ","canonical_record":{"source":{"id":"2507.14664","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-19T15:28:58Z","cross_cats_sorted":[],"title_canon_sha256":"dfa1aa63a46c1985748222d5af38ae5683730185b1aca649b58072be459dff8c","abstract_canon_sha256":"cfa7451f482006a47dd97c61e64a549b562db4ffd7859a1c5437c06be90e3fbd"},"schema_version":"1.0"},"canonical_sha256":"089f9838a9aa472a3b5684cea443ef1a77e4c3288541ee47879e4aad0b731465","source":{"kind":"arxiv","id":"2507.14664","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14664","created_at":"2026-07-05T11:41:26Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14664v2","created_at":"2026-07-05T11:41:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14664","created_at":"2026-07-05T11:41:26Z"},{"alias_kind":"pith_short_12","alias_value":"BCPZQOFJVJDS","created_at":"2026-07-05T11:41:26Z"},{"alias_kind":"pith_short_16","alias_value":"BCPZQOFJVJDSUO2W","created_at":"2026-07-05T11:41:26Z"},{"alias_kind":"pith_short_8","alias_value":"BCPZQOFJ","created_at":"2026-07-05T11:41:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BCPZQOFJVJDSUO2WQTHKIQ7PDJ","target":"record","payload":{"canonical_record":{"source":{"id":"2507.14664","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-19T15:28:58Z","cross_cats_sorted":[],"title_canon_sha256":"dfa1aa63a46c1985748222d5af38ae5683730185b1aca649b58072be459dff8c","abstract_canon_sha256":"cfa7451f482006a47dd97c61e64a549b562db4ffd7859a1c5437c06be90e3fbd"},"schema_version":"1.0"},"canonical_sha256":"089f9838a9aa472a3b5684cea443ef1a77e4c3288541ee47879e4aad0b731465","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:26.946505Z","signature_b64":"7ppuTeHOklzN88WliU9hE6Pz0rVXysseG+GqUnAo4x24nJlJJemeGrZxt8oH654HAYKMUYCvPj4/KH44h1MHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"089f9838a9aa472a3b5684cea443ef1a77e4c3288541ee47879e4aad0b731465","last_reissued_at":"2026-07-05T11:41:26.946000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:26.946000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.14664","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":"2026-07-05T11:41:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AEIH7qeR6fQ28huTHbjpAZYuuqwKYY3PDJ3wav5vGjMuyaisEvRe1M/qpUc11s5Bv2MHY7iDwGFs3XkIovQMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T14:17:22.027846Z"},"content_sha256":"99117d9d7fcc200a842e67c97427382bfebcf02356fa281ec8b94e2352387368","schema_version":"1.0","event_id":"sha256:99117d9d7fcc200a842e67c97427382bfebcf02356fa281ec8b94e2352387368"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BCPZQOFJVJDSUO2WQTHKIQ7PDJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mangosteen: An Open Thai Corpus for Language Model Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Can Udomcharoenchaikit, Ekapol Chuangsuwanich, Kunat Pipatanakul, Pakpoom Singkorapoom, Peerat Limkonchotiwat, Sarana Nutanong, Wannaphong Phatthiyaphaibun","submitted_at":"2025-07-19T15:28:58Z","abstract_excerpt":"Pre-training data shapes a language model's quality, but raw web text is noisy and demands careful cleaning. Existing large-scale corpora rely on English-centric or language-agnostic pipelines whose heuristics do not capture Thai script or cultural nuances, leaving risky material such as gambling content untreated. Prior Thai-specific efforts customize pipelines or build new ones, yet seldom release their data or document design choices, hindering reproducibility and raising the question of how to construct a transparent, high-quality Thai corpus. We introduce Mangosteen: a 47 billion-token Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14664","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/2507.14664/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":"2026-07-05T11:41:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f3Z45tgEg1yFXwppktgDppdhCbkJkefJfLUHtTf+Jd7piezyHO0HiAYpM2oDldGkluAv2NhV3ZQ10GK6pqI7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T14:17:22.028227Z"},"content_sha256":"6343724a73ea8e679eca6ae88752294d28bd4c86607966b95716d39e6b643fb0","schema_version":"1.0","event_id":"sha256:6343724a73ea8e679eca6ae88752294d28bd4c86607966b95716d39e6b643fb0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BCPZQOFJVJDSUO2WQTHKIQ7PDJ/bundle.json","state_url":"https://pith.science/pith/BCPZQOFJVJDSUO2WQTHKIQ7PDJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BCPZQOFJVJDSUO2WQTHKIQ7PDJ/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":"2026-07-08T14:17:22Z","links":{"resolver":"https://pith.science/pith/BCPZQOFJVJDSUO2WQTHKIQ7PDJ","bundle":"https://pith.science/pith/BCPZQOFJVJDSUO2WQTHKIQ7PDJ/bundle.json","state":"https://pith.science/pith/BCPZQOFJVJDSUO2WQTHKIQ7PDJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BCPZQOFJVJDSUO2WQTHKIQ7PDJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BCPZQOFJVJDSUO2WQTHKIQ7PDJ","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":"cfa7451f482006a47dd97c61e64a549b562db4ffd7859a1c5437c06be90e3fbd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-19T15:28:58Z","title_canon_sha256":"dfa1aa63a46c1985748222d5af38ae5683730185b1aca649b58072be459dff8c"},"schema_version":"1.0","source":{"id":"2507.14664","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14664","created_at":"2026-07-05T11:41:26Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14664v2","created_at":"2026-07-05T11:41:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14664","created_at":"2026-07-05T11:41:26Z"},{"alias_kind":"pith_short_12","alias_value":"BCPZQOFJVJDS","created_at":"2026-07-05T11:41:26Z"},{"alias_kind":"pith_short_16","alias_value":"BCPZQOFJVJDSUO2W","created_at":"2026-07-05T11:41:26Z"},{"alias_kind":"pith_short_8","alias_value":"BCPZQOFJ","created_at":"2026-07-05T11:41:26Z"}],"graph_snapshots":[{"event_id":"sha256:6343724a73ea8e679eca6ae88752294d28bd4c86607966b95716d39e6b643fb0","target":"graph","created_at":"2026-07-05T11:41:26Z","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/2507.14664/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-training data shapes a language model's quality, but raw web text is noisy and demands careful cleaning. Existing large-scale corpora rely on English-centric or language-agnostic pipelines whose heuristics do not capture Thai script or cultural nuances, leaving risky material such as gambling content untreated. Prior Thai-specific efforts customize pipelines or build new ones, yet seldom release their data or document design choices, hindering reproducibility and raising the question of how to construct a transparent, high-quality Thai corpus. We introduce Mangosteen: a 47 billion-token Th","authors_text":"Can Udomcharoenchaikit, Ekapol Chuangsuwanich, Kunat Pipatanakul, Pakpoom Singkorapoom, Peerat Limkonchotiwat, Sarana Nutanong, Wannaphong Phatthiyaphaibun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-19T15:28:58Z","title":"Mangosteen: An Open Thai Corpus for Language Model Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14664","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":"sha256:99117d9d7fcc200a842e67c97427382bfebcf02356fa281ec8b94e2352387368","target":"record","created_at":"2026-07-05T11:41:26Z","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":"cfa7451f482006a47dd97c61e64a549b562db4ffd7859a1c5437c06be90e3fbd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-19T15:28:58Z","title_canon_sha256":"dfa1aa63a46c1985748222d5af38ae5683730185b1aca649b58072be459dff8c"},"schema_version":"1.0","source":{"id":"2507.14664","kind":"arxiv","version":2}},"canonical_sha256":"089f9838a9aa472a3b5684cea443ef1a77e4c3288541ee47879e4aad0b731465","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"089f9838a9aa472a3b5684cea443ef1a77e4c3288541ee47879e4aad0b731465","first_computed_at":"2026-07-05T11:41:26.946000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:41:26.946000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7ppuTeHOklzN88WliU9hE6Pz0rVXysseG+GqUnAo4x24nJlJJemeGrZxt8oH654HAYKMUYCvPj4/KH44h1MHBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:41:26.946505Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.14664","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99117d9d7fcc200a842e67c97427382bfebcf02356fa281ec8b94e2352387368","sha256:6343724a73ea8e679eca6ae88752294d28bd4c86607966b95716d39e6b643fb0"],"state_sha256":"4a1a76f2dce529b613df3b9bdf0a141498d3b2eca55361f24c1310151b1c3ec1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o4Q2WrK3Uf6u3wzGY9YS7OO+oeOLD7iRCycijl+IyPq3MXd5yxtOF0IA5xBu+KSqXN0x+VEdf4LvI1DzlTSLDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T14:17:22.030774Z","bundle_sha256":"cbc6b128eb8d9348a96d7135eb39d73db99017cbd95bf55d491fd213b27c7ef8"}}