{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:73UFGPNJJK76ACDAFCENSSFTBS","short_pith_number":"pith:73UFGPNJ","canonical_record":{"source":{"id":"2208.01561","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-02T16:07:31Z","cross_cats_sorted":[],"title_canon_sha256":"5b1719988a8927a3b1aeaabf4c78f3a7faa312d3687835be82ab31a0045a15c5","abstract_canon_sha256":"d628db9e90f5789530e5b1337a6b60ccd36690dff45cf67889cfbd636412e99f"},"schema_version":"1.0"},"canonical_sha256":"fee8533da94abfe008602888d948b30ca3a96fe13c2fbb254683436ec8a5a348","source":{"kind":"arxiv","id":"2208.01561","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.01561","created_at":"2026-07-05T04:45:35Z"},{"alias_kind":"arxiv_version","alias_value":"2208.01561v1","created_at":"2026-07-05T04:45:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.01561","created_at":"2026-07-05T04:45:35Z"},{"alias_kind":"pith_short_12","alias_value":"73UFGPNJJK76","created_at":"2026-07-05T04:45:35Z"},{"alias_kind":"pith_short_16","alias_value":"73UFGPNJJK76ACDA","created_at":"2026-07-05T04:45:35Z"},{"alias_kind":"pith_short_8","alias_value":"73UFGPNJ","created_at":"2026-07-05T04:45:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:73UFGPNJJK76ACDAFCENSSFTBS","target":"record","payload":{"canonical_record":{"source":{"id":"2208.01561","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-02T16:07:31Z","cross_cats_sorted":[],"title_canon_sha256":"5b1719988a8927a3b1aeaabf4c78f3a7faa312d3687835be82ab31a0045a15c5","abstract_canon_sha256":"d628db9e90f5789530e5b1337a6b60ccd36690dff45cf67889cfbd636412e99f"},"schema_version":"1.0"},"canonical_sha256":"fee8533da94abfe008602888d948b30ca3a96fe13c2fbb254683436ec8a5a348","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:35.036900Z","signature_b64":"KxhW3ic4Mhq4GxMrLAjQl4FB9pU6ps05wBYsZd6NXYyxgJbiGGWZ+uWTDgqLCzVmODbn7Xh6gtTWnD2+XmkkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fee8533da94abfe008602888d948b30ca3a96fe13c2fbb254683436ec8a5a348","last_reissued_at":"2026-07-05T04:45:35.036492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:35.036492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.01561","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":"2026-07-05T04:45:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dcb2Mu5J8oJy/HA2OsVRsE8pFpX/ibmYVqIoO5fEVHZ/N88e6qZNUy9KgqcQdZMKuT+eOnqVgogbyO6tqPXmDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T00:26:23.553531Z"},"content_sha256":"0cffe35c18d3b7042005333771a72e886a1644f6c26421be97073fa97fbbdcdb","schema_version":"1.0","event_id":"sha256:0cffe35c18d3b7042005333771a72e886a1644f6c26421be97073fa97fbbdcdb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:73UFGPNJJK76ACDAFCENSSFTBS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lost in Space Marking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cassandra L. Jacobs, Yuval Pinter","submitted_at":"2022-08-02T16:07:31Z","abstract_excerpt":"We look at a decision taken early in training a subword tokenizer, namely whether it should be the word-initial token that carries a special mark, or the word-final one. Based on surface-level considerations of efficiency and cohesion, as well as morphological coverage, we find that a Unigram LM tokenizer trained on pre-tokenized English text is better off marking the word-initial token, while one trained on raw text benefits from marking word ends. Our findings generalize across domains."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.01561","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/2208.01561/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":"2026-07-05T04:45:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6yG7kdScgh6rSx5g/GDFfMDmAjrVRVNisCqgmAHj98oI9WTAoGRvUM3T+GvSel7GvaYBa7kugiC+B6wYcW6+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T00:26:23.554039Z"},"content_sha256":"6565656874d8d392555a58a6cd72c504c275443a9a133eff67f8953afe0f4d21","schema_version":"1.0","event_id":"sha256:6565656874d8d392555a58a6cd72c504c275443a9a133eff67f8953afe0f4d21"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/73UFGPNJJK76ACDAFCENSSFTBS/bundle.json","state_url":"https://pith.science/pith/73UFGPNJJK76ACDAFCENSSFTBS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/73UFGPNJJK76ACDAFCENSSFTBS/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":"2026-08-23T00:26:23Z","links":{"resolver":"https://pith.science/pith/73UFGPNJJK76ACDAFCENSSFTBS","bundle":"https://pith.science/pith/73UFGPNJJK76ACDAFCENSSFTBS/bundle.json","state":"https://pith.science/pith/73UFGPNJJK76ACDAFCENSSFTBS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/73UFGPNJJK76ACDAFCENSSFTBS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:73UFGPNJJK76ACDAFCENSSFTBS","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":"d628db9e90f5789530e5b1337a6b60ccd36690dff45cf67889cfbd636412e99f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-02T16:07:31Z","title_canon_sha256":"5b1719988a8927a3b1aeaabf4c78f3a7faa312d3687835be82ab31a0045a15c5"},"schema_version":"1.0","source":{"id":"2208.01561","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.01561","created_at":"2026-07-05T04:45:35Z"},{"alias_kind":"arxiv_version","alias_value":"2208.01561v1","created_at":"2026-07-05T04:45:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.01561","created_at":"2026-07-05T04:45:35Z"},{"alias_kind":"pith_short_12","alias_value":"73UFGPNJJK76","created_at":"2026-07-05T04:45:35Z"},{"alias_kind":"pith_short_16","alias_value":"73UFGPNJJK76ACDA","created_at":"2026-07-05T04:45:35Z"},{"alias_kind":"pith_short_8","alias_value":"73UFGPNJ","created_at":"2026-07-05T04:45:35Z"}],"graph_snapshots":[{"event_id":"sha256:6565656874d8d392555a58a6cd72c504c275443a9a133eff67f8953afe0f4d21","target":"graph","created_at":"2026-07-05T04:45:35Z","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/2208.01561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We look at a decision taken early in training a subword tokenizer, namely whether it should be the word-initial token that carries a special mark, or the word-final one. Based on surface-level considerations of efficiency and cohesion, as well as morphological coverage, we find that a Unigram LM tokenizer trained on pre-tokenized English text is better off marking the word-initial token, while one trained on raw text benefits from marking word ends. Our findings generalize across domains.","authors_text":"Cassandra L. Jacobs, Yuval Pinter","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-02T16:07:31Z","title":"Lost in Space Marking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.01561","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":"sha256:0cffe35c18d3b7042005333771a72e886a1644f6c26421be97073fa97fbbdcdb","target":"record","created_at":"2026-07-05T04:45:35Z","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":"d628db9e90f5789530e5b1337a6b60ccd36690dff45cf67889cfbd636412e99f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-02T16:07:31Z","title_canon_sha256":"5b1719988a8927a3b1aeaabf4c78f3a7faa312d3687835be82ab31a0045a15c5"},"schema_version":"1.0","source":{"id":"2208.01561","kind":"arxiv","version":1}},"canonical_sha256":"fee8533da94abfe008602888d948b30ca3a96fe13c2fbb254683436ec8a5a348","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fee8533da94abfe008602888d948b30ca3a96fe13c2fbb254683436ec8a5a348","first_computed_at":"2026-07-05T04:45:35.036492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:45:35.036492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KxhW3ic4Mhq4GxMrLAjQl4FB9pU6ps05wBYsZd6NXYyxgJbiGGWZ+uWTDgqLCzVmODbn7Xh6gtTWnD2+XmkkBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:45:35.036900Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.01561","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cffe35c18d3b7042005333771a72e886a1644f6c26421be97073fa97fbbdcdb","sha256:6565656874d8d392555a58a6cd72c504c275443a9a133eff67f8953afe0f4d21"],"state_sha256":"76988f586de2e420cbf573f21b1d5fefadc958a533141d10d7346cd5be7625e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"akoPPsCDZXRocU3KafbzruUsXg5ah3sl0DudPd/ZVz9vA9wKwnPayxC4rAgGRWEI8+UCiLLmco6CT99J2CowDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T00:26:23.559092Z","bundle_sha256":"abfdd706cb871df131de71b2c7e84da8bda57295dc72daab41fb8b5772d285dc"}}