{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7ELODANB2FKLCLCLTH5E3KMPDR","short_pith_number":"pith:7ELODANB","canonical_record":{"source":{"id":"2608.10690","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-11T09:14:25Z","cross_cats_sorted":[],"title_canon_sha256":"cb808467d7efa1646bfc8dee8377a2204e83b0a2144d456a2e6b4b0072b0199c","abstract_canon_sha256":"435a959cb29defb16f58797e17cddcc80b6704b8ac3caf885534f945e622a724"},"schema_version":"1.0"},"canonical_sha256":"f916e181a1d154b12c4b99fa4da98f1c7a87bc3aa42bf1d92a477e0b9aa41438","source":{"kind":"arxiv","id":"2608.10690","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10690","created_at":"2026-08-12T01:23:03Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10690v1","created_at":"2026-08-12T01:23:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10690","created_at":"2026-08-12T01:23:03Z"},{"alias_kind":"pith_short_12","alias_value":"7ELODANB2FKL","created_at":"2026-08-12T01:23:03Z"},{"alias_kind":"pith_short_16","alias_value":"7ELODANB2FKLCLCL","created_at":"2026-08-12T01:23:03Z"},{"alias_kind":"pith_short_8","alias_value":"7ELODANB","created_at":"2026-08-12T01:23:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7ELODANB2FKLCLCLTH5E3KMPDR","target":"record","payload":{"canonical_record":{"source":{"id":"2608.10690","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-11T09:14:25Z","cross_cats_sorted":[],"title_canon_sha256":"cb808467d7efa1646bfc8dee8377a2204e83b0a2144d456a2e6b4b0072b0199c","abstract_canon_sha256":"435a959cb29defb16f58797e17cddcc80b6704b8ac3caf885534f945e622a724"},"schema_version":"1.0"},"canonical_sha256":"f916e181a1d154b12c4b99fa4da98f1c7a87bc3aa42bf1d92a477e0b9aa41438","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:23:03.556623Z","signature_b64":"s9SSR7PvehiL/sIPrQR5CqtFJUyVaMWNqbNKZgWlVRqhI0jg3P98D0vHrFa5tez5RAkoyibnUguUWoz79ip7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f916e181a1d154b12c4b99fa4da98f1c7a87bc3aa42bf1d92a477e0b9aa41438","last_reissued_at":"2026-08-12T01:23:03.553623Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:23:03.553623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.10690","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":"2026-08-12T01:23:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HIM5x7jO0KW4mnm9/9UCpDNhgXhQF0lpYsvQTxy2GJBmVUJHrIJneVNRSm0q0xEQ+LZW0EIAkFN1edJywQBnBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:13:14.208358Z"},"content_sha256":"3e2dad911cb4fcaa748574498afbe4cdd2d18ce28c81cfe731a501738f0c295a","schema_version":"1.0","event_id":"sha256:3e2dad911cb4fcaa748574498afbe4cdd2d18ce28c81cfe731a501738f0c295a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7ELODANB2FKLCLCLTH5E3KMPDR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Released LLM Vocabularies Support Token-Level Estimation of Hidden Corpora?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dayiheng Liu, Han Qiu, Hui Xue, Jinfeng Li, Qingjie Zhang, Xingzhang Ren, Yitong Yang, Yuefeng Chen, Zixuan Chen","submitted_at":"2026-08-11T09:14:25Z","abstract_excerpt":"Pretraining corpus composition shapes LLM capabilities, but it often remains hidden even when model weights are released. Prior work has inferred corpus mixtures or traced specific token groups from released tokenizer vocabularies; in contrast, we estimate corpus ratios for arbitrary target tokens. We first show that BPE tokenizers trained on different corpora share stable token ID--ratio distributions, motivating distribution transfer from known corpora to a target tokenizer trained on hidden corpora. We then propose Quantile-Guided Density Estimation (QGDE), which approximates this distribut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10690","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/2608.10690/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":"2026-08-12T01:23:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1wW0NAj9hZHhzu0emAh82eYjVaVeuMMyKZuIWPai7j4yVriHUfTTeH0PbPlyEvY8oG/CnBiBpWooKKCJaYhjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:13:14.208680Z"},"content_sha256":"d31ff4f67c39ceffbf7f9591507bcaf92c560549a759ba267f52992700238572","schema_version":"1.0","event_id":"sha256:d31ff4f67c39ceffbf7f9591507bcaf92c560549a759ba267f52992700238572"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7ELODANB2FKLCLCLTH5E3KMPDR/bundle.json","state_url":"https://pith.science/pith/7ELODANB2FKLCLCLTH5E3KMPDR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7ELODANB2FKLCLCLTH5E3KMPDR/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":"2026-08-14T19:13:14Z","links":{"resolver":"https://pith.science/pith/7ELODANB2FKLCLCLTH5E3KMPDR","bundle":"https://pith.science/pith/7ELODANB2FKLCLCLTH5E3KMPDR/bundle.json","state":"https://pith.science/pith/7ELODANB2FKLCLCLTH5E3KMPDR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7ELODANB2FKLCLCLTH5E3KMPDR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7ELODANB2FKLCLCLTH5E3KMPDR","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":"435a959cb29defb16f58797e17cddcc80b6704b8ac3caf885534f945e622a724","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-11T09:14:25Z","title_canon_sha256":"cb808467d7efa1646bfc8dee8377a2204e83b0a2144d456a2e6b4b0072b0199c"},"schema_version":"1.0","source":{"id":"2608.10690","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10690","created_at":"2026-08-12T01:23:03Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10690v1","created_at":"2026-08-12T01:23:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10690","created_at":"2026-08-12T01:23:03Z"},{"alias_kind":"pith_short_12","alias_value":"7ELODANB2FKL","created_at":"2026-08-12T01:23:03Z"},{"alias_kind":"pith_short_16","alias_value":"7ELODANB2FKLCLCL","created_at":"2026-08-12T01:23:03Z"},{"alias_kind":"pith_short_8","alias_value":"7ELODANB","created_at":"2026-08-12T01:23:03Z"}],"graph_snapshots":[{"event_id":"sha256:d31ff4f67c39ceffbf7f9591507bcaf92c560549a759ba267f52992700238572","target":"graph","created_at":"2026-08-12T01:23:03Z","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/2608.10690/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining corpus composition shapes LLM capabilities, but it often remains hidden even when model weights are released. Prior work has inferred corpus mixtures or traced specific token groups from released tokenizer vocabularies; in contrast, we estimate corpus ratios for arbitrary target tokens. We first show that BPE tokenizers trained on different corpora share stable token ID--ratio distributions, motivating distribution transfer from known corpora to a target tokenizer trained on hidden corpora. We then propose Quantile-Guided Density Estimation (QGDE), which approximates this distribut","authors_text":"Dayiheng Liu, Han Qiu, Hui Xue, Jinfeng Li, Qingjie Zhang, Xingzhang Ren, Yitong Yang, Yuefeng Chen, Zixuan Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-11T09:14:25Z","title":"Can Released LLM Vocabularies Support Token-Level Estimation of Hidden Corpora?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10690","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":"sha256:3e2dad911cb4fcaa748574498afbe4cdd2d18ce28c81cfe731a501738f0c295a","target":"record","created_at":"2026-08-12T01:23:03Z","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":"435a959cb29defb16f58797e17cddcc80b6704b8ac3caf885534f945e622a724","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-11T09:14:25Z","title_canon_sha256":"cb808467d7efa1646bfc8dee8377a2204e83b0a2144d456a2e6b4b0072b0199c"},"schema_version":"1.0","source":{"id":"2608.10690","kind":"arxiv","version":1}},"canonical_sha256":"f916e181a1d154b12c4b99fa4da98f1c7a87bc3aa42bf1d92a477e0b9aa41438","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f916e181a1d154b12c4b99fa4da98f1c7a87bc3aa42bf1d92a477e0b9aa41438","first_computed_at":"2026-08-12T01:23:03.553623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T01:23:03.553623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s9SSR7PvehiL/sIPrQR5CqtFJUyVaMWNqbNKZgWlVRqhI0jg3P98D0vHrFa5tez5RAkoyibnUguUWoz79ip7AA==","signature_status":"signed_v1","signed_at":"2026-08-12T01:23:03.556623Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10690","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e2dad911cb4fcaa748574498afbe4cdd2d18ce28c81cfe731a501738f0c295a","sha256:d31ff4f67c39ceffbf7f9591507bcaf92c560549a759ba267f52992700238572"],"state_sha256":"6735b450c35aa3d4e67a5a12b78ac698aabcb896d635dd102c3df313d46b856a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xGsQ7FqZIdw/qynGRCuGbx28c1B3TgVdkyEhYZQckCAS8xWeSLG0O5pJQ8E3s97Njop6IdwjBcs5kwh/d0IWBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:13:14.237424Z","bundle_sha256":"ed6a142f63e9d9a4488ea7b4390db94ed7e1b8be58d3b2dfdf2bc71ffa0068c3"}}