{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7RX6KD45OKBL5MPR2HMNQBUO3T","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":"ca14645f5ba8ece786cbf0a104d1d1a4d362a1159d54f5b7a7af16ea24929336","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T18:58:30Z","title_canon_sha256":"f17f6aa6e428ed245b5e39cf3fad65c1cb1b2380ba96fbcc4133023648a8695d"},"schema_version":"1.0","source":{"id":"2605.29000","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29000","created_at":"2026-05-29T01:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29000v1","created_at":"2026-05-29T01:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29000","created_at":"2026-05-29T01:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"7RX6KD45OKBL","created_at":"2026-05-29T01:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"7RX6KD45OKBL5MPR","created_at":"2026-05-29T01:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"7RX6KD45","created_at":"2026-05-29T01:04:43Z"}],"graph_snapshots":[{"event_id":"sha256:f28e8b3d6cab50443e59cd48bd0f7766e397a226bd2dc29f5f98f8b61f453a1d","target":"graph","created_at":"2026-05-29T01:04:43Z","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/2605.29000/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional lossless text compression preserves every byte, but its gains on natural language are often modest in realistic operating regimes. We study \\emph{lossy semantic text compression}, where the encoder strategically deletes parts of the text and a large language model (LLM) reconstructs the original content from the retained skeleton. We benchmark a progression of deletion strategies, including uniform step deletion, word-length-guided deletion (WordLen), word-frequency-guided deletion (WordFreq), LP-optimized deletion (Opt), entropy-based deletion using GPT-2 surprisal, and hybrid met","authors_text":"Junhong Tong, Jun Li, Yuchun Zou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T18:58:30Z","title":"Text-Preserving Lossy Text Compression: A Study of Strategic Deletion and LLM Reconstruction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29000","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:f1ba09d5708a4964be58d14a8df56334783254074693851ffb624a9ba4643b05","target":"record","created_at":"2026-05-29T01:04:43Z","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":"ca14645f5ba8ece786cbf0a104d1d1a4d362a1159d54f5b7a7af16ea24929336","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T18:58:30Z","title_canon_sha256":"f17f6aa6e428ed245b5e39cf3fad65c1cb1b2380ba96fbcc4133023648a8695d"},"schema_version":"1.0","source":{"id":"2605.29000","kind":"arxiv","version":1}},"canonical_sha256":"fc6fe50f9d7282beb1f1d1d8d8068edcc82855ab4b9c2f1ce208974e5f68ed80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc6fe50f9d7282beb1f1d1d8d8068edcc82855ab4b9c2f1ce208974e5f68ed80","first_computed_at":"2026-05-29T01:04:43.107622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:04:43.107622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MGyXoNgzqQUpkyvqPWd4OZqCgxMkAw9WXf8GdFtZvqpopOsBnu4GhODzJufY+Lspts8lqAWVUJ7exvPvjHcNDg==","signature_status":"signed_v1","signed_at":"2026-05-29T01:04:43.108097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29000","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1ba09d5708a4964be58d14a8df56334783254074693851ffb624a9ba4643b05","sha256:f28e8b3d6cab50443e59cd48bd0f7766e397a226bd2dc29f5f98f8b61f453a1d"],"state_sha256":"0484e913271ce02c75b3d4fc047b22b731d68206e90b893b5434d8bfd57429ea"}