{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ERYGFKUUZ47GQGKGUXGHTWCCQ5","short_pith_number":"pith:ERYGFKUU","schema_version":"1.0","canonical_sha256":"247062aa94cf3e681946a5cc79d8428742cf12d0efe531f3dcaefae8cd8a63f6","source":{"kind":"arxiv","id":"2405.17146","version":1},"attestation_state":"computed","paper":{"title":"Compressed-Language Models for Understanding Compressed File Formats: a JPEG Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alejandro Pardo, Bernard Ghanem, Hani Itani, Juan C. P\\'erez, Juan Leon-Alcazar, Mattia Soldan","submitted_at":"2024-05-27T13:09:23Z","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"},"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":"2405.17146","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T13:09:23Z","cross_cats_sorted":[],"title_canon_sha256":"5ffbee1a67cba92b3e07192107503c33b795307f09b4ee5261737c58e5d351fc","abstract_canon_sha256":"9bd41a6c99e898a7b511773153088ae40518e5f2e9d8f32741f787878e9255dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:40.504715Z","signature_b64":"hajGI7W53tD9fYHx1fwf/XixW9TmUrLsYhYzRBoQw76QrBQeMK6zADEPqHf/RXRTObkBgkOLNPsiNI0wMiwLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"247062aa94cf3e681946a5cc79d8428742cf12d0efe531f3dcaefae8cd8a63f6","last_reissued_at":"2026-07-05T08:23:40.504310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:40.504310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compressed-Language Models for Understanding Compressed File Formats: a JPEG Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alejandro Pardo, Bernard Ghanem, Hani Itani, Juan C. P\\'erez, Juan Leon-Alcazar, Mattia Soldan","submitted_at":"2024-05-27T13:09:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17146","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/2405.17146/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":"2405.17146","created_at":"2026-07-05T08:23:40.504370+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17146v1","created_at":"2026-07-05T08:23:40.504370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17146","created_at":"2026-07-05T08:23:40.504370+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERYGFKUUZ47G","created_at":"2026-07-05T08:23:40.504370+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERYGFKUUZ47GQGKG","created_at":"2026-07-05T08:23:40.504370+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERYGFKUU","created_at":"2026-07-05T08:23:40.504370+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/ERYGFKUUZ47GQGKGUXGHTWCCQ5","json":"https://pith.science/pith/ERYGFKUUZ47GQGKGUXGHTWCCQ5.json","graph_json":"https://pith.science/api/pith-number/ERYGFKUUZ47GQGKGUXGHTWCCQ5/graph.json","events_json":"https://pith.science/api/pith-number/ERYGFKUUZ47GQGKGUXGHTWCCQ5/events.json","paper":"https://pith.science/paper/ERYGFKUU"},"agent_actions":{"view_html":"https://pith.science/pith/ERYGFKUUZ47GQGKGUXGHTWCCQ5","download_json":"https://pith.science/pith/ERYGFKUUZ47GQGKGUXGHTWCCQ5.json","view_paper":"https://pith.science/paper/ERYGFKUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17146&json=true","fetch_graph":"https://pith.science/api/pith-number/ERYGFKUUZ47GQGKGUXGHTWCCQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/ERYGFKUUZ47GQGKGUXGHTWCCQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERYGFKUUZ47GQGKGUXGHTWCCQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERYGFKUUZ47GQGKGUXGHTWCCQ5/action/storage_attestation","attest_author":"https://pith.science/pith/ERYGFKUUZ47GQGKGUXGHTWCCQ5/action/author_attestation","sign_citation":"https://pith.science/pith/ERYGFKUUZ47GQGKGUXGHTWCCQ5/action/citation_signature","submit_replication":"https://pith.science/pith/ERYGFKUUZ47GQGKGUXGHTWCCQ5/action/replication_record"}},"created_at":"2026-07-05T08:23:40.504370+00:00","updated_at":"2026-07-05T08:23:40.504370+00:00"}