{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3HNIKVINV7VQZE7AFWIOB7HU4Q","short_pith_number":"pith:3HNIKVIN","canonical_record":{"source":{"id":"2605.24541","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T12:14:04Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"6844f158ddba285b890205ab5fbe3305925aa23751bd0863c2659c84b0cfcd0f","abstract_canon_sha256":"aaf897daa7650d05564b2130a127b598aebfa630947011219aa1e90c10dc00d9"},"schema_version":"1.0"},"canonical_sha256":"d9da85550dafeb0c93e02d90e0fcf4e425cd74429f940b2986417e2eed69ab0e","source":{"kind":"arxiv","id":"2605.24541","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24541","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24541v1","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24541","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"3HNIKVINV7VQ","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"pith_short_16","alias_value":"3HNIKVINV7VQZE7A","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"pith_short_8","alias_value":"3HNIKVIN","created_at":"2026-05-26T01:03:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3HNIKVINV7VQZE7AFWIOB7HU4Q","target":"record","payload":{"canonical_record":{"source":{"id":"2605.24541","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T12:14:04Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"6844f158ddba285b890205ab5fbe3305925aa23751bd0863c2659c84b0cfcd0f","abstract_canon_sha256":"aaf897daa7650d05564b2130a127b598aebfa630947011219aa1e90c10dc00d9"},"schema_version":"1.0"},"canonical_sha256":"d9da85550dafeb0c93e02d90e0fcf4e425cd74429f940b2986417e2eed69ab0e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:45.447139Z","signature_b64":"AjH9SdjFyXDKnMWQGq02GrwgRdg8pnNlVLaC4excbIvoYATqncWj5vBvTBXvrYlifAd21o9Ahi56gBbFM2tqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9da85550dafeb0c93e02d90e0fcf4e425cd74429f940b2986417e2eed69ab0e","last_reissued_at":"2026-05-26T01:03:45.446114Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:45.446114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.24541","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tzzKqjFSIJ6w4zgWxNofD3wE8kodBO0NKwGFr2CW4wdG6F264L8B6R7kzYSMkUIzKWCPUJnqLLZOuzM+zoUfBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T09:24:04.205637Z"},"content_sha256":"6e125b7c140e9a30e0a1314220c0f3fae50704193e010141ec520e262ef88b88","schema_version":"1.0","event_id":"sha256:6e125b7c140e9a30e0a1314220c0f3fae50704193e010141ec520e262ef88b88"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3HNIKVINV7VQZE7AFWIOB7HU4Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SemanticZip: A Pilot Framework for Lossy Text Compression with LLMs as Semantic Decompressors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.LG","authors_text":"Natalia Trukhina, Vadim Vashkelis","submitted_at":"2026-05-23T12:14:04Z","abstract_excerpt":"Text compression for large language model (LLM) systems is usually framed as token deletion, retrieval, summarization, or exact reconstruction. We study a more aggressive but explicitly lossy setting: compress text into compact codes that an LLM can expand into task-relevant meaning. We call this setting SemanticZip. Unlike lossless compression, SemanticZip does not require byte-identical reconstruction; unlike ordinary summarization, it treats model-based decompression as part of the codec and evaluates whether task-relevant semantic commitments are recovered.\n  This paper is a pilot framewor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24541","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/2605.24541/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uiBNOBcwWZjAjIOeHV/6kQiRurFOcGnCIA4eVDm1Ok6Gh7zTaQr2YFv009AxYnMvOTtbycYVdY/z8E4+sOVgAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T09:24:04.206011Z"},"content_sha256":"2f9dc046d8746c8062fbd0b401668a040ebf4d592ef7848f5ca474aca193dba0","schema_version":"1.0","event_id":"sha256:2f9dc046d8746c8062fbd0b401668a040ebf4d592ef7848f5ca474aca193dba0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3HNIKVINV7VQZE7AFWIOB7HU4Q/bundle.json","state_url":"https://pith.science/pith/3HNIKVINV7VQZE7AFWIOB7HU4Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3HNIKVINV7VQZE7AFWIOB7HU4Q/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-02T09:24:04Z","links":{"resolver":"https://pith.science/pith/3HNIKVINV7VQZE7AFWIOB7HU4Q","bundle":"https://pith.science/pith/3HNIKVINV7VQZE7AFWIOB7HU4Q/bundle.json","state":"https://pith.science/pith/3HNIKVINV7VQZE7AFWIOB7HU4Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3HNIKVINV7VQZE7AFWIOB7HU4Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3HNIKVINV7VQZE7AFWIOB7HU4Q","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":"aaf897daa7650d05564b2130a127b598aebfa630947011219aa1e90c10dc00d9","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T12:14:04Z","title_canon_sha256":"6844f158ddba285b890205ab5fbe3305925aa23751bd0863c2659c84b0cfcd0f"},"schema_version":"1.0","source":{"id":"2605.24541","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24541","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24541v1","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24541","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"3HNIKVINV7VQ","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"pith_short_16","alias_value":"3HNIKVINV7VQZE7A","created_at":"2026-05-26T01:03:45Z"},{"alias_kind":"pith_short_8","alias_value":"3HNIKVIN","created_at":"2026-05-26T01:03:45Z"}],"graph_snapshots":[{"event_id":"sha256:2f9dc046d8746c8062fbd0b401668a040ebf4d592ef7848f5ca474aca193dba0","target":"graph","created_at":"2026-05-26T01:03:45Z","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/2605.24541/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text compression for large language model (LLM) systems is usually framed as token deletion, retrieval, summarization, or exact reconstruction. We study a more aggressive but explicitly lossy setting: compress text into compact codes that an LLM can expand into task-relevant meaning. We call this setting SemanticZip. Unlike lossless compression, SemanticZip does not require byte-identical reconstruction; unlike ordinary summarization, it treats model-based decompression as part of the codec and evaluates whether task-relevant semantic commitments are recovered.\n  This paper is a pilot framewor","authors_text":"Natalia Trukhina, Vadim Vashkelis","cross_cats":["cs.AI","cs.CL","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T12:14:04Z","title":"SemanticZip: A Pilot Framework for Lossy Text Compression with LLMs as Semantic Decompressors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24541","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":"sha256:6e125b7c140e9a30e0a1314220c0f3fae50704193e010141ec520e262ef88b88","target":"record","created_at":"2026-05-26T01:03:45Z","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":"aaf897daa7650d05564b2130a127b598aebfa630947011219aa1e90c10dc00d9","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T12:14:04Z","title_canon_sha256":"6844f158ddba285b890205ab5fbe3305925aa23751bd0863c2659c84b0cfcd0f"},"schema_version":"1.0","source":{"id":"2605.24541","kind":"arxiv","version":1}},"canonical_sha256":"d9da85550dafeb0c93e02d90e0fcf4e425cd74429f940b2986417e2eed69ab0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9da85550dafeb0c93e02d90e0fcf4e425cd74429f940b2986417e2eed69ab0e","first_computed_at":"2026-05-26T01:03:45.446114Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:45.446114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AjH9SdjFyXDKnMWQGq02GrwgRdg8pnNlVLaC4excbIvoYATqncWj5vBvTBXvrYlifAd21o9Ahi56gBbFM2tqCQ==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:45.447139Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24541","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e125b7c140e9a30e0a1314220c0f3fae50704193e010141ec520e262ef88b88","sha256:2f9dc046d8746c8062fbd0b401668a040ebf4d592ef7848f5ca474aca193dba0"],"state_sha256":"780a8252dda79d0471332ee8a83c20ac92ea6afa81d4c87a8b766ab68b2a185a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R95k4NChUftJeeJYXt0jV9XpLGFx4s5nQpofaJ4Irz5yynpmGPA0MfS1t4ZCDixyrVFeRq6CqK2Vtkc95i4rDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T09:24:04.207994Z","bundle_sha256":"422bab98b2d00085fc830752d9ce3272627f751751ba456ed7cb99150b0a199a"}}