{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FHE4BGGYIUITGQNNXURI7LPTKJ","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":"f9e15ed6e76e5ad40d917349b6f075f20062029ef5c359f27145f424b7eeaba0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-21T03:01:53Z","title_canon_sha256":"93c095879ffba5c50717fa051dc3b9093354ab005b75249b1913f1fdf2af8f5b"},"schema_version":"1.0","source":{"id":"2508.15190","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.15190","created_at":"2026-07-05T11:57:07Z"},{"alias_kind":"arxiv_version","alias_value":"2508.15190v1","created_at":"2026-07-05T11:57:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15190","created_at":"2026-07-05T11:57:07Z"},{"alias_kind":"pith_short_12","alias_value":"FHE4BGGYIUIT","created_at":"2026-07-05T11:57:07Z"},{"alias_kind":"pith_short_16","alias_value":"FHE4BGGYIUITGQNN","created_at":"2026-07-05T11:57:07Z"},{"alias_kind":"pith_short_8","alias_value":"FHE4BGGY","created_at":"2026-07-05T11:57:07Z"}],"graph_snapshots":[{"event_id":"sha256:4378aa96199f000e598e8a3ecca26f55a6b824f1dab1b4bb0f491382c107df7f","target":"graph","created_at":"2026-07-05T11:57:07Z","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/2508.15190/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenization plays a critical role in language modeling, yet existing approaches such as Byte-Pair Encoding (BPE) or WordPiece operate purely on frequency statistics, ignoring the underlying semantic structure of text. This leads to over-tokenization of semantically redundant spans and underutilization of contextual coherence, particularly in long-context scenarios. In this work, we propose \\textbf{SemToken}, a semantic-aware tokenization framework that jointly reduces token redundancy and improves computation efficiency. SemToken first extracts contextual semantic embeddings via lightweight e","authors_text":"Dong Liu, Yanxuan Yu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-21T03:01:53Z","title":"SemToken: Semantic-Aware Tokenization for Efficient Long-Context Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15190","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":"sha256:47fd60cc0754098e8d9d4d3eb11f41f7d44964c44378997ed6710c82e881415f","target":"record","created_at":"2026-07-05T11:57:07Z","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":"f9e15ed6e76e5ad40d917349b6f075f20062029ef5c359f27145f424b7eeaba0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-21T03:01:53Z","title_canon_sha256":"93c095879ffba5c50717fa051dc3b9093354ab005b75249b1913f1fdf2af8f5b"},"schema_version":"1.0","source":{"id":"2508.15190","kind":"arxiv","version":1}},"canonical_sha256":"29c9c098d845113341adbd228fadf3527191d02ad2b4d6896462de07c9375958","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29c9c098d845113341adbd228fadf3527191d02ad2b4d6896462de07c9375958","first_computed_at":"2026-07-05T11:57:07.997150Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:07.997150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Glq2/aDGhItfvIfj8SCxl4kQu1pkIFmFY+gHogbPvyq/UEL6xVW2vi76QB4oeECDa/LanDutCW/uoocqWNe+Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:07.997567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.15190","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47fd60cc0754098e8d9d4d3eb11f41f7d44964c44378997ed6710c82e881415f","sha256:4378aa96199f000e598e8a3ecca26f55a6b824f1dab1b4bb0f491382c107df7f"],"state_sha256":"9a0916aef97eb425fef26ba7876f52acdedda2a1ffa15fbd080763843124ac28"}