{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:V7BUY55IGIEJPJZR2D77ZFLCLE","short_pith_number":"pith:V7BUY55I","canonical_record":{"source":{"id":"2305.08787","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-15T16:46:47Z","cross_cats_sorted":[],"title_canon_sha256":"8accb111723f888f5bdfcd103927c888e5c777cb5aff7b1c1a27330256af7d66","abstract_canon_sha256":"fe26d56d77037a96483eadccb81f06d165d099b9bed27e4b77de358e1d28def4"},"schema_version":"1.0"},"canonical_sha256":"afc34c77a8320897a731d0fffc9562591a53b3d75378911d790102e1422ba050","source":{"kind":"arxiv","id":"2305.08787","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.08787","created_at":"2026-07-05T06:10:06Z"},{"alias_kind":"arxiv_version","alias_value":"2305.08787v1","created_at":"2026-07-05T06:10:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08787","created_at":"2026-07-05T06:10:06Z"},{"alias_kind":"pith_short_12","alias_value":"V7BUY55IGIEJ","created_at":"2026-07-05T06:10:06Z"},{"alias_kind":"pith_short_16","alias_value":"V7BUY55IGIEJPJZR","created_at":"2026-07-05T06:10:06Z"},{"alias_kind":"pith_short_8","alias_value":"V7BUY55I","created_at":"2026-07-05T06:10:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:V7BUY55IGIEJPJZR2D77ZFLCLE","target":"record","payload":{"canonical_record":{"source":{"id":"2305.08787","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-15T16:46:47Z","cross_cats_sorted":[],"title_canon_sha256":"8accb111723f888f5bdfcd103927c888e5c777cb5aff7b1c1a27330256af7d66","abstract_canon_sha256":"fe26d56d77037a96483eadccb81f06d165d099b9bed27e4b77de358e1d28def4"},"schema_version":"1.0"},"canonical_sha256":"afc34c77a8320897a731d0fffc9562591a53b3d75378911d790102e1422ba050","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:10:06.053927Z","signature_b64":"9fe/UsPhvrJoAWj9JS1Kp1nDBPlbFsowoYzyH9NiK91Ko9tMuXB1zF07qZpUjziFY+wFqx+I1os+eAk19Kk5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afc34c77a8320897a731d0fffc9562591a53b3d75378911d790102e1422ba050","last_reissued_at":"2026-07-05T06:10:06.053561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:10:06.053561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.08787","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":"2026-07-05T06:10:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TS+W/0XqwU5ZZw4hGxH7PeDoNx/jjrQx8bDxqVoMo6jWX9KWnm8YxSSKfFeSeX69cwuLymqiOvg5/RFZI4GfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T02:59:06.670754Z"},"content_sha256":"338d39d187298fdaa0ff528327c2b99bb558e4112deeccb9f5c5c734f8c9e757","schema_version":"1.0","event_id":"sha256:338d39d187298fdaa0ff528327c2b99bb558e4112deeccb9f5c5c734f8c9e757"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:V7BUY55IGIEJPJZR2D77ZFLCLE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Comparing Variation in Tokenizer Outputs Using a Series of Problematic and Challenging Biomedical Sentences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christopher Meaney, Michael Escobar, Peter C Austin, Therese A Stukel","submitted_at":"2023-05-15T16:46:47Z","abstract_excerpt":"Background & Objective: Biomedical text data are increasingly available for research. Tokenization is an initial step in many biomedical text mining pipelines. Tokenization is the process of parsing an input biomedical sentence (represented as a digital character sequence) into a discrete set of word/token symbols, which convey focused semantic/syntactic meaning. The objective of this study is to explore variation in tokenizer outputs when applied across a series of challenging biomedical sentences.\n  Method: Diaz [2015] introduce 24 challenging example biomedical sentences for comparing token"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08787","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/2305.08787/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":"2026-07-05T06:10:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ldT4jxij6cZNJWErFzzbA9tWa28qjTGSwm8Nbqb0TQBR2C0WT7ttVmIfd000xV0zmg3TE8ddeNPRXnqecxcDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T02:59:06.671287Z"},"content_sha256":"44528e1bf726cafdbe3ba0c503e020e9675ffd06763acee02407e513cfff9f37","schema_version":"1.0","event_id":"sha256:44528e1bf726cafdbe3ba0c503e020e9675ffd06763acee02407e513cfff9f37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V7BUY55IGIEJPJZR2D77ZFLCLE/bundle.json","state_url":"https://pith.science/pith/V7BUY55IGIEJPJZR2D77ZFLCLE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V7BUY55IGIEJPJZR2D77ZFLCLE/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":"2026-08-16T02:59:06Z","links":{"resolver":"https://pith.science/pith/V7BUY55IGIEJPJZR2D77ZFLCLE","bundle":"https://pith.science/pith/V7BUY55IGIEJPJZR2D77ZFLCLE/bundle.json","state":"https://pith.science/pith/V7BUY55IGIEJPJZR2D77ZFLCLE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V7BUY55IGIEJPJZR2D77ZFLCLE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:V7BUY55IGIEJPJZR2D77ZFLCLE","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":"fe26d56d77037a96483eadccb81f06d165d099b9bed27e4b77de358e1d28def4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-15T16:46:47Z","title_canon_sha256":"8accb111723f888f5bdfcd103927c888e5c777cb5aff7b1c1a27330256af7d66"},"schema_version":"1.0","source":{"id":"2305.08787","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.08787","created_at":"2026-07-05T06:10:06Z"},{"alias_kind":"arxiv_version","alias_value":"2305.08787v1","created_at":"2026-07-05T06:10:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08787","created_at":"2026-07-05T06:10:06Z"},{"alias_kind":"pith_short_12","alias_value":"V7BUY55IGIEJ","created_at":"2026-07-05T06:10:06Z"},{"alias_kind":"pith_short_16","alias_value":"V7BUY55IGIEJPJZR","created_at":"2026-07-05T06:10:06Z"},{"alias_kind":"pith_short_8","alias_value":"V7BUY55I","created_at":"2026-07-05T06:10:06Z"}],"graph_snapshots":[{"event_id":"sha256:44528e1bf726cafdbe3ba0c503e020e9675ffd06763acee02407e513cfff9f37","target":"graph","created_at":"2026-07-05T06:10:06Z","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/2305.08787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Background & Objective: Biomedical text data are increasingly available for research. Tokenization is an initial step in many biomedical text mining pipelines. Tokenization is the process of parsing an input biomedical sentence (represented as a digital character sequence) into a discrete set of word/token symbols, which convey focused semantic/syntactic meaning. The objective of this study is to explore variation in tokenizer outputs when applied across a series of challenging biomedical sentences.\n  Method: Diaz [2015] introduce 24 challenging example biomedical sentences for comparing token","authors_text":"Christopher Meaney, Michael Escobar, Peter C Austin, Therese A Stukel","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-15T16:46:47Z","title":"Comparing Variation in Tokenizer Outputs Using a Series of Problematic and Challenging Biomedical Sentences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08787","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":"sha256:338d39d187298fdaa0ff528327c2b99bb558e4112deeccb9f5c5c734f8c9e757","target":"record","created_at":"2026-07-05T06:10:06Z","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":"fe26d56d77037a96483eadccb81f06d165d099b9bed27e4b77de358e1d28def4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-15T16:46:47Z","title_canon_sha256":"8accb111723f888f5bdfcd103927c888e5c777cb5aff7b1c1a27330256af7d66"},"schema_version":"1.0","source":{"id":"2305.08787","kind":"arxiv","version":1}},"canonical_sha256":"afc34c77a8320897a731d0fffc9562591a53b3d75378911d790102e1422ba050","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afc34c77a8320897a731d0fffc9562591a53b3d75378911d790102e1422ba050","first_computed_at":"2026-07-05T06:10:06.053561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:10:06.053561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9fe/UsPhvrJoAWj9JS1Kp1nDBPlbFsowoYzyH9NiK91Ko9tMuXB1zF07qZpUjziFY+wFqx+I1os+eAk19Kk5Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:10:06.053927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.08787","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:338d39d187298fdaa0ff528327c2b99bb558e4112deeccb9f5c5c734f8c9e757","sha256:44528e1bf726cafdbe3ba0c503e020e9675ffd06763acee02407e513cfff9f37"],"state_sha256":"91e8ab4a9ec52768d575a893b0a0e5a3cd34ef81a9541eced0567e6a07704cb5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fvb3ttiG96lxkwSKm7IvCroOeBjye6ur2gnSrLp1uDICgoFiCH9IbwTMzaM5bHqHbSkgbGQNXuLKwwv9KwJBCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T02:59:06.676236Z","bundle_sha256":"72a640a9ca295d13da8cf4b8eae9e88cb66e61ee71a08b813202109baf82bd84"}}