{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ERYGFKUUZ47GQGKGUXGHTWCCQ5","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":"9bd41a6c99e898a7b511773153088ae40518e5f2e9d8f32741f787878e9255dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T13:09:23Z","title_canon_sha256":"5ffbee1a67cba92b3e07192107503c33b795307f09b4ee5261737c58e5d351fc"},"schema_version":"1.0","source":{"id":"2405.17146","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17146","created_at":"2026-07-05T08:23:40Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17146v1","created_at":"2026-07-05T08:23:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17146","created_at":"2026-07-05T08:23:40Z"},{"alias_kind":"pith_short_12","alias_value":"ERYGFKUUZ47G","created_at":"2026-07-05T08:23:40Z"},{"alias_kind":"pith_short_16","alias_value":"ERYGFKUUZ47GQGKG","created_at":"2026-07-05T08:23:40Z"},{"alias_kind":"pith_short_8","alias_value":"ERYGFKUU","created_at":"2026-07-05T08:23:40Z"}],"graph_snapshots":[{"event_id":"sha256:385701c1944d3481514a38a788fc492a978c3c61e0a6efa65b80333b4478d9d9","target":"graph","created_at":"2026-07-05T08:23:40Z","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/2405.17146/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study investigates whether Compressed-Language Models (CLMs), i.e. language models operating on raw byte streams from Compressed File Formats~(CFFs), can understand files compressed by CFFs. We focus on the JPEG format as a representative CFF, given its commonality and its representativeness of key concepts in compression, such as entropy coding and run-length encoding. We test if CLMs understand the JPEG format by probing their capabilities to perform along three axes: recognition of inherent file properties, handling of files with anomalies, and generation of new files. Our findings dem","authors_text":"Alejandro Pardo, Bernard Ghanem, Hani Itani, Juan C. P\\'erez, Juan Leon-Alcazar, Mattia Soldan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T13:09:23Z","title":"Compressed-Language Models for Understanding Compressed File Formats: a JPEG Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17146","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":"sha256:90d33af8636b312510c9028b0ba7c818a50292532427b85f5bb84a21bac404f1","target":"record","created_at":"2026-07-05T08:23:40Z","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":"9bd41a6c99e898a7b511773153088ae40518e5f2e9d8f32741f787878e9255dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T13:09:23Z","title_canon_sha256":"5ffbee1a67cba92b3e07192107503c33b795307f09b4ee5261737c58e5d351fc"},"schema_version":"1.0","source":{"id":"2405.17146","kind":"arxiv","version":1}},"canonical_sha256":"247062aa94cf3e681946a5cc79d8428742cf12d0efe531f3dcaefae8cd8a63f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"247062aa94cf3e681946a5cc79d8428742cf12d0efe531f3dcaefae8cd8a63f6","first_computed_at":"2026-07-05T08:23:40.504310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:40.504310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hajGI7W53tD9fYHx1fwf/XixW9TmUrLsYhYzRBoQw76QrBQeMK6zADEPqHf/RXRTObkBgkOLNPsiNI0wMiwLAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:40.504715Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17146","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90d33af8636b312510c9028b0ba7c818a50292532427b85f5bb84a21bac404f1","sha256:385701c1944d3481514a38a788fc492a978c3c61e0a6efa65b80333b4478d9d9"],"state_sha256":"c5c2e1fb09620578271db035d061eb19a63950fc4253836e23141d65f17593d6"}