{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BGSNM53SLBH5G6V5OZUYZH46YE","short_pith_number":"pith:BGSNM53S","canonical_record":{"source":{"id":"2608.10678","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-11T08:58:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6192ed9d604fc19d788d99edf2af40b89866f7bffae965eee8e4b0cea7ea948f","abstract_canon_sha256":"51fdf612f1aacded8755cd8c3e8eee2da22818415c1a3d44e7661e36a4c3ceee"},"schema_version":"1.0"},"canonical_sha256":"09a4d67772584fd37abd76698c9f9ec12052630c4b11cf2128d06af8e350e7ae","source":{"kind":"arxiv","id":"2608.10678","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10678","created_at":"2026-08-12T01:23:00Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10678v1","created_at":"2026-08-12T01:23:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10678","created_at":"2026-08-12T01:23:00Z"},{"alias_kind":"pith_short_12","alias_value":"BGSNM53SLBH5","created_at":"2026-08-12T01:23:00Z"},{"alias_kind":"pith_short_16","alias_value":"BGSNM53SLBH5G6V5","created_at":"2026-08-12T01:23:00Z"},{"alias_kind":"pith_short_8","alias_value":"BGSNM53S","created_at":"2026-08-12T01:23:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BGSNM53SLBH5G6V5OZUYZH46YE","target":"record","payload":{"canonical_record":{"source":{"id":"2608.10678","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-11T08:58:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6192ed9d604fc19d788d99edf2af40b89866f7bffae965eee8e4b0cea7ea948f","abstract_canon_sha256":"51fdf612f1aacded8755cd8c3e8eee2da22818415c1a3d44e7661e36a4c3ceee"},"schema_version":"1.0"},"canonical_sha256":"09a4d67772584fd37abd76698c9f9ec12052630c4b11cf2128d06af8e350e7ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:23:00.456801Z","signature_b64":"MBMzW71qa5uiEUlGvZ83jcIS+QG6OXPDGv62qJkGkZAsKGO+40Q5jTE0YxjSG4plhTncBZN8pLsab8pEzvH1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09a4d67772584fd37abd76698c9f9ec12052630c4b11cf2128d06af8e350e7ae","last_reissued_at":"2026-08-12T01:23:00.455156Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:23:00.455156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.10678","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":"2026-08-12T01:23:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dG/1AVOodty2Bs0PzufgdrgDbwI0ZdFoKT5jrJTZ897lhWO1vF816oQOVdEMnb8v0a5+bNEbgv9oNszrXE/wAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:43:57.153822Z"},"content_sha256":"40d90ce68250baf86080a214fd3feaeccfc4c91de45fe1609d7346dde80ade7d","schema_version":"1.0","event_id":"sha256:40d90ce68250baf86080a214fd3feaeccfc4c91de45fe1609d7346dde80ade7d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BGSNM53SLBH5G6V5OZUYZH46YE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Auditing Chinese Web-scale Corpora via Sampled BPE Token Statistics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Gelei Deng, Han Qiu, Hui Xue, Jie Zhang, Jinfeng Li, Qingjie Zhang, Tianwei Zhang, Yitong Yang, Yuefeng Chen, Ziqi Tang","submitted_at":"2026-08-11T08:58:06Z","abstract_excerpt":"Chinese web pollution has surfaced in LLMs, motivating audits of upstream Chinese corpora. However, auditing such corpora faces three challenges: (1) their web-scale size makes full scan costly; (2) prior analyses are often too coarse to expose token-level pollution; (3) Chinese web pollution is implicit and rapidly changing. We propose Sampled-BPE, a lightweight token-level auditing pipeline that sample a small subset and train BPE tokenizer to surface polluted tokens. Experiments show that Sampled-BPE preserves usable estimates while substantially reducing runtime and memory: a 148.4 $\\times"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10678","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/2608.10678/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":"2026-08-12T01:23:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b37L3lnaP4SjVlAORaenwlrCY3Ki0P8JTC0wRPx6c63JBoiuvAImM9DjU7+r2c8JpJUH65gIoPokS6XKkLAcDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T01:43:57.154765Z"},"content_sha256":"92732c8681b106487336e649f84a916d91417383d4519efd1f83296b51baf6e7","schema_version":"1.0","event_id":"sha256:92732c8681b106487336e649f84a916d91417383d4519efd1f83296b51baf6e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BGSNM53SLBH5G6V5OZUYZH46YE/bundle.json","state_url":"https://pith.science/pith/BGSNM53SLBH5G6V5OZUYZH46YE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BGSNM53SLBH5G6V5OZUYZH46YE/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":"2026-08-16T01:43:57Z","links":{"resolver":"https://pith.science/pith/BGSNM53SLBH5G6V5OZUYZH46YE","bundle":"https://pith.science/pith/BGSNM53SLBH5G6V5OZUYZH46YE/bundle.json","state":"https://pith.science/pith/BGSNM53SLBH5G6V5OZUYZH46YE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BGSNM53SLBH5G6V5OZUYZH46YE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BGSNM53SLBH5G6V5OZUYZH46YE","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":"51fdf612f1aacded8755cd8c3e8eee2da22818415c1a3d44e7661e36a4c3ceee","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-11T08:58:06Z","title_canon_sha256":"6192ed9d604fc19d788d99edf2af40b89866f7bffae965eee8e4b0cea7ea948f"},"schema_version":"1.0","source":{"id":"2608.10678","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10678","created_at":"2026-08-12T01:23:00Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10678v1","created_at":"2026-08-12T01:23:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10678","created_at":"2026-08-12T01:23:00Z"},{"alias_kind":"pith_short_12","alias_value":"BGSNM53SLBH5","created_at":"2026-08-12T01:23:00Z"},{"alias_kind":"pith_short_16","alias_value":"BGSNM53SLBH5G6V5","created_at":"2026-08-12T01:23:00Z"},{"alias_kind":"pith_short_8","alias_value":"BGSNM53S","created_at":"2026-08-12T01:23:00Z"}],"graph_snapshots":[{"event_id":"sha256:92732c8681b106487336e649f84a916d91417383d4519efd1f83296b51baf6e7","target":"graph","created_at":"2026-08-12T01:23:00Z","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/2608.10678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chinese web pollution has surfaced in LLMs, motivating audits of upstream Chinese corpora. However, auditing such corpora faces three challenges: (1) their web-scale size makes full scan costly; (2) prior analyses are often too coarse to expose token-level pollution; (3) Chinese web pollution is implicit and rapidly changing. We propose Sampled-BPE, a lightweight token-level auditing pipeline that sample a small subset and train BPE tokenizer to surface polluted tokens. Experiments show that Sampled-BPE preserves usable estimates while substantially reducing runtime and memory: a 148.4 $\\times","authors_text":"Gelei Deng, Han Qiu, Hui Xue, Jie Zhang, Jinfeng Li, Qingjie Zhang, Tianwei Zhang, Yitong Yang, Yuefeng Chen, Ziqi Tang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-11T08:58:06Z","title":"Auditing Chinese Web-scale Corpora via Sampled BPE Token Statistics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10678","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":"sha256:40d90ce68250baf86080a214fd3feaeccfc4c91de45fe1609d7346dde80ade7d","target":"record","created_at":"2026-08-12T01:23:00Z","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":"51fdf612f1aacded8755cd8c3e8eee2da22818415c1a3d44e7661e36a4c3ceee","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-11T08:58:06Z","title_canon_sha256":"6192ed9d604fc19d788d99edf2af40b89866f7bffae965eee8e4b0cea7ea948f"},"schema_version":"1.0","source":{"id":"2608.10678","kind":"arxiv","version":1}},"canonical_sha256":"09a4d67772584fd37abd76698c9f9ec12052630c4b11cf2128d06af8e350e7ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09a4d67772584fd37abd76698c9f9ec12052630c4b11cf2128d06af8e350e7ae","first_computed_at":"2026-08-12T01:23:00.455156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T01:23:00.455156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MBMzW71qa5uiEUlGvZ83jcIS+QG6OXPDGv62qJkGkZAsKGO+40Q5jTE0YxjSG4plhTncBZN8pLsab8pEzvH1Dw==","signature_status":"signed_v1","signed_at":"2026-08-12T01:23:00.456801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10678","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40d90ce68250baf86080a214fd3feaeccfc4c91de45fe1609d7346dde80ade7d","sha256:92732c8681b106487336e649f84a916d91417383d4519efd1f83296b51baf6e7"],"state_sha256":"615e5ae33dc4f975c5b0b46551220be4fc555afd312cc1ec3bcb8ff4da31320f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JnCTYveZvmQPtgaY3QON9wUrnnd/uf5mq3nVrDTO6whIreKHogFnWi+CQTr7iH4B60zaYFX3Ztvz2oZrnYYYAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T01:43:57.162406Z","bundle_sha256":"01a5d87032d50f120cf4ae0da169da3a7612f4b1ca264382c8c4643ceb251e00"}}