{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FO6AXAZLP55MFPBNIM7JT23EKP","short_pith_number":"pith:FO6AXAZL","schema_version":"1.0","canonical_sha256":"2bbc0b832b7f7ac2bc2d433e99eb6453f2f8a8998064bcc86902c454c4329d44","source":{"kind":"arxiv","id":"2508.05468","version":1},"attestation_state":"computed","paper":{"title":"TASE: Token Awareness and Structured Evaluation for Multilingual Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenzhuo Zhao, Junting Lu, Xinda Wang, Yue Huang, Ziqian Liu","submitted_at":"2025-08-07T15:11:17Z","abstract_excerpt":"While large language models (LLMs) have demonstrated remarkable performance on high-level semantic tasks, they often struggle with fine-grained, token-level understanding and structural reasoning--capabilities that are essential for applications requiring precision and control. We introduce TASE, a comprehensive benchmark designed to evaluate LLMs' ability to perceive and reason about token-level information across languages. TASE covers 10 tasks under two core categories: token awareness and structural understanding, spanning Chinese, English, and Korean, with a 35,927-instance evaluation set"},"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":"2508.05468","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-07T15:11:17Z","cross_cats_sorted":[],"title_canon_sha256":"cbb40a847fc5af9bd3b9629ae642aea653fedadbc7e40ae1b9f5190a05944c28","abstract_canon_sha256":"b17d3855f8b09b573b172347203a208c6ad25627b61443d59b94cafe5425956f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:13.782839Z","signature_b64":"IQ+wrfu8cNGjMaS0sKh1JzfC86JtdLdH+eGzch0ytjHqIrYNN5uFqNFPKe7IQUw94yVWDIl50aIQa7cVMdZeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bbc0b832b7f7ac2bc2d433e99eb6453f2f8a8998064bcc86902c454c4329d44","last_reissued_at":"2026-07-05T11:50:13.782337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:13.782337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TASE: Token Awareness and Structured Evaluation for Multilingual Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenzhuo Zhao, Junting Lu, Xinda Wang, Yue Huang, Ziqian Liu","submitted_at":"2025-08-07T15:11:17Z","abstract_excerpt":"While large language models (LLMs) have demonstrated remarkable performance on high-level semantic tasks, they often struggle with fine-grained, token-level understanding and structural reasoning--capabilities that are essential for applications requiring precision and control. We introduce TASE, a comprehensive benchmark designed to evaluate LLMs' ability to perceive and reason about token-level information across languages. TASE covers 10 tasks under two core categories: token awareness and structural understanding, spanning Chinese, English, and Korean, with a 35,927-instance evaluation set"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05468","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/2508.05468/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":"2508.05468","created_at":"2026-07-05T11:50:13.782398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.05468v1","created_at":"2026-07-05T11:50:13.782398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05468","created_at":"2026-07-05T11:50:13.782398+00:00"},{"alias_kind":"pith_short_12","alias_value":"FO6AXAZLP55M","created_at":"2026-07-05T11:50:13.782398+00:00"},{"alias_kind":"pith_short_16","alias_value":"FO6AXAZLP55MFPBN","created_at":"2026-07-05T11:50:13.782398+00:00"},{"alias_kind":"pith_short_8","alias_value":"FO6AXAZL","created_at":"2026-07-05T11:50:13.782398+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FO6AXAZLP55MFPBNIM7JT23EKP","json":"https://pith.science/pith/FO6AXAZLP55MFPBNIM7JT23EKP.json","graph_json":"https://pith.science/api/pith-number/FO6AXAZLP55MFPBNIM7JT23EKP/graph.json","events_json":"https://pith.science/api/pith-number/FO6AXAZLP55MFPBNIM7JT23EKP/events.json","paper":"https://pith.science/paper/FO6AXAZL"},"agent_actions":{"view_html":"https://pith.science/pith/FO6AXAZLP55MFPBNIM7JT23EKP","download_json":"https://pith.science/pith/FO6AXAZLP55MFPBNIM7JT23EKP.json","view_paper":"https://pith.science/paper/FO6AXAZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.05468&json=true","fetch_graph":"https://pith.science/api/pith-number/FO6AXAZLP55MFPBNIM7JT23EKP/graph.json","fetch_events":"https://pith.science/api/pith-number/FO6AXAZLP55MFPBNIM7JT23EKP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FO6AXAZLP55MFPBNIM7JT23EKP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FO6AXAZLP55MFPBNIM7JT23EKP/action/storage_attestation","attest_author":"https://pith.science/pith/FO6AXAZLP55MFPBNIM7JT23EKP/action/author_attestation","sign_citation":"https://pith.science/pith/FO6AXAZLP55MFPBNIM7JT23EKP/action/citation_signature","submit_replication":"https://pith.science/pith/FO6AXAZLP55MFPBNIM7JT23EKP/action/replication_record"}},"created_at":"2026-07-05T11:50:13.782398+00:00","updated_at":"2026-07-05T11:50:13.782398+00:00"}