{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RCM2DUUXDHURMUCDLHGOFTIUF3","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":"ece05768f9bdefa71b9db8378fc3fed8853bf726a410cff5085223d4831ee575","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T12:21:48Z","title_canon_sha256":"47bcfef5f6413bfeb8118c8bfd21d4aa7388dba4d4b322aa425a6e386be07864"},"schema_version":"1.0","source":{"id":"2405.17103","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17103","created_at":"2026-07-05T08:31:51Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17103v2","created_at":"2026-07-05T08:31:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17103","created_at":"2026-07-05T08:31:51Z"},{"alias_kind":"pith_short_12","alias_value":"RCM2DUUXDHUR","created_at":"2026-07-05T08:31:51Z"},{"alias_kind":"pith_short_16","alias_value":"RCM2DUUXDHURMUCD","created_at":"2026-07-05T08:31:51Z"},{"alias_kind":"pith_short_8","alias_value":"RCM2DUUX","created_at":"2026-07-05T08:31:51Z"}],"graph_snapshots":[{"event_id":"sha256:b44e28b35daf4deb03d2147100f58a0ac0c3f69628104d63cef3c340cb7f6456","target":"graph","created_at":"2026-07-05T08:31:51Z","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/2405.17103/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In infilling tasks, sub-tokens, representing instances where a complete token is segmented into two parts, often emerge at the boundaries of prefixes, middles, and suffixes. Traditional methods focused on training models at the token level, leading to sub-optimal performance in character-level infilling tasks during the inference stage. Alternately, some approaches considered character-level infilling, but they relied on predicting sub-tokens in inference, yet this strategy diminished ability in character-level infilling tasks due to the large perplexity of the model on sub-tokens. In this pap","authors_text":"Hongsheng Li, Houxing Ren, Mingjie Zhan, Zhongyuan Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T12:21:48Z","title":"Empowering Character-level Text Infilling by Eliminating Sub-Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17103","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:e5837cbacc0c3abfb40dfd23b33d10313f706d7717fb7f7efe83e15c4a00e79d","target":"record","created_at":"2026-07-05T08:31:51Z","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":"ece05768f9bdefa71b9db8378fc3fed8853bf726a410cff5085223d4831ee575","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T12:21:48Z","title_canon_sha256":"47bcfef5f6413bfeb8118c8bfd21d4aa7388dba4d4b322aa425a6e386be07864"},"schema_version":"1.0","source":{"id":"2405.17103","kind":"arxiv","version":2}},"canonical_sha256":"8899a1d29719e916504359cce2cd142eea6e32d2b42d5b2ea85a6dd88b7068be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8899a1d29719e916504359cce2cd142eea6e32d2b42d5b2ea85a6dd88b7068be","first_computed_at":"2026-07-05T08:31:51.517209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:51.517209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RjGxt7RqBPbjkbg8Ei1cuMMeEX9Rl/Ha51ZBz8yKC03nUMvKamxFW1nNo18cyPjWudD3XDu3N4MbUS1YtH7qAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:51.517658Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17103","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5837cbacc0c3abfb40dfd23b33d10313f706d7717fb7f7efe83e15c4a00e79d","sha256:b44e28b35daf4deb03d2147100f58a0ac0c3f69628104d63cef3c340cb7f6456"],"state_sha256":"de16b8247caaabe194749cc1d1876c98895c12ee8d6fc843ad41e4b414c38ffb"}