{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RCM2DUUXDHURMUCDLHGOFTIUF3","short_pith_number":"pith:RCM2DUUX","schema_version":"1.0","canonical_sha256":"8899a1d29719e916504359cce2cd142eea6e32d2b42d5b2ea85a6dd88b7068be","source":{"kind":"arxiv","id":"2405.17103","version":2},"attestation_state":"computed","paper":{"title":"Empowering Character-level Text Infilling by Eliminating Sub-Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongsheng Li, Houxing Ren, Mingjie Zhan, Zhongyuan Wu","submitted_at":"2024-05-27T12:21:48Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.17103","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T12:21:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"47bcfef5f6413bfeb8118c8bfd21d4aa7388dba4d4b322aa425a6e386be07864","abstract_canon_sha256":"ece05768f9bdefa71b9db8378fc3fed8853bf726a410cff5085223d4831ee575"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:51.517658Z","signature_b64":"RjGxt7RqBPbjkbg8Ei1cuMMeEX9Rl/Ha51ZBz8yKC03nUMvKamxFW1nNo18cyPjWudD3XDu3N4MbUS1YtH7qAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8899a1d29719e916504359cce2cd142eea6e32d2b42d5b2ea85a6dd88b7068be","last_reissued_at":"2026-07-05T08:31:51.517209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:51.517209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empowering Character-level Text Infilling by Eliminating Sub-Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hongsheng Li, Houxing Ren, Mingjie Zhan, Zhongyuan Wu","submitted_at":"2024-05-27T12:21:48Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17103","kind":"arxiv","version":2},"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/2405.17103/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.17103","created_at":"2026-07-05T08:31:51.517276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17103v2","created_at":"2026-07-05T08:31:51.517276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17103","created_at":"2026-07-05T08:31:51.517276+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCM2DUUXDHUR","created_at":"2026-07-05T08:31:51.517276+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCM2DUUXDHURMUCD","created_at":"2026-07-05T08:31:51.517276+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCM2DUUX","created_at":"2026-07-05T08:31:51.517276+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13567","citing_title":"K-COMP: Retrieval-Augmented Medical Domain Question Answering With Knowledge-Injected Compressor","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RCM2DUUXDHURMUCDLHGOFTIUF3","json":"https://pith.science/pith/RCM2DUUXDHURMUCDLHGOFTIUF3.json","graph_json":"https://pith.science/api/pith-number/RCM2DUUXDHURMUCDLHGOFTIUF3/graph.json","events_json":"https://pith.science/api/pith-number/RCM2DUUXDHURMUCDLHGOFTIUF3/events.json","paper":"https://pith.science/paper/RCM2DUUX"},"agent_actions":{"view_html":"https://pith.science/pith/RCM2DUUXDHURMUCDLHGOFTIUF3","download_json":"https://pith.science/pith/RCM2DUUXDHURMUCDLHGOFTIUF3.json","view_paper":"https://pith.science/paper/RCM2DUUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17103&json=true","fetch_graph":"https://pith.science/api/pith-number/RCM2DUUXDHURMUCDLHGOFTIUF3/graph.json","fetch_events":"https://pith.science/api/pith-number/RCM2DUUXDHURMUCDLHGOFTIUF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCM2DUUXDHURMUCDLHGOFTIUF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCM2DUUXDHURMUCDLHGOFTIUF3/action/storage_attestation","attest_author":"https://pith.science/pith/RCM2DUUXDHURMUCDLHGOFTIUF3/action/author_attestation","sign_citation":"https://pith.science/pith/RCM2DUUXDHURMUCDLHGOFTIUF3/action/citation_signature","submit_replication":"https://pith.science/pith/RCM2DUUXDHURMUCDLHGOFTIUF3/action/replication_record"}},"created_at":"2026-07-05T08:31:51.517276+00:00","updated_at":"2026-07-05T08:31:51.517276+00:00"}