{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3BJJFFCQKQGMP3QL2WIBBB2GXJ","short_pith_number":"pith:3BJJFFCQ","schema_version":"1.0","canonical_sha256":"d852929450540cc7ee0bd590108746ba6d2067f8e408c310454d7da8f6c73ce4","source":{"kind":"arxiv","id":"2509.05169","version":1},"attestation_state":"computed","paper":{"title":"Exploring Autoregressive Vision Foundation Models for Image Compression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Huu-Tai Phung, Wen-Hsiao Peng, Yen-Kuan Ho, Yu-Hsiang Lin","submitted_at":"2025-09-05T15:09:49Z","abstract_excerpt":"This work presents the first attempt to repurpose vision foundation models (VFMs) as image codecs, aiming to explore their generation capability for low-rate image compression. VFMs are widely employed in both conditional and unconditional generation scenarios across diverse downstream tasks, e.g., physical AI applications. Many VFMs employ an encoder-decoder architecture similar to that of end-to-end learned image codecs and learn an autoregressive (AR) model to perform next-token prediction. To enable compression, we repurpose the AR model in VFM for entropy coding the next token based on pr"},"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":"2509.05169","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.IV","submitted_at":"2025-09-05T15:09:49Z","cross_cats_sorted":[],"title_canon_sha256":"d5b3df70c22aada426f2c02e32fc81014be935b44cc5a097d8de1357eabd4050","abstract_canon_sha256":"6d87f4d6cddcd041ac287cf93c59304e046e95ab9b4265a635449dfa7c033ef2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:37.214703Z","signature_b64":"ws0GqDi/fIVtLxvZs6DtBoLdUi3WM8l++0VP2H0UXTe58v5L+B1Ogd7LEiChSkL//sHeAEe9rmXTAbD4Z4siCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d852929450540cc7ee0bd590108746ba6d2067f8e408c310454d7da8f6c73ce4","last_reissued_at":"2026-07-05T12:05:37.214184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:37.214184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Autoregressive Vision Foundation Models for Image Compression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Huu-Tai Phung, Wen-Hsiao Peng, Yen-Kuan Ho, Yu-Hsiang Lin","submitted_at":"2025-09-05T15:09:49Z","abstract_excerpt":"This work presents the first attempt to repurpose vision foundation models (VFMs) as image codecs, aiming to explore their generation capability for low-rate image compression. VFMs are widely employed in both conditional and unconditional generation scenarios across diverse downstream tasks, e.g., physical AI applications. Many VFMs employ an encoder-decoder architecture similar to that of end-to-end learned image codecs and learn an autoregressive (AR) model to perform next-token prediction. To enable compression, we repurpose the AR model in VFM for entropy coding the next token based on pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05169","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/2509.05169/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":"2509.05169","created_at":"2026-07-05T12:05:37.214249+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05169v1","created_at":"2026-07-05T12:05:37.214249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05169","created_at":"2026-07-05T12:05:37.214249+00:00"},{"alias_kind":"pith_short_12","alias_value":"3BJJFFCQKQGM","created_at":"2026-07-05T12:05:37.214249+00:00"},{"alias_kind":"pith_short_16","alias_value":"3BJJFFCQKQGMP3QL","created_at":"2026-07-05T12:05:37.214249+00:00"},{"alias_kind":"pith_short_8","alias_value":"3BJJFFCQ","created_at":"2026-07-05T12:05:37.214249+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/3BJJFFCQKQGMP3QL2WIBBB2GXJ","json":"https://pith.science/pith/3BJJFFCQKQGMP3QL2WIBBB2GXJ.json","graph_json":"https://pith.science/api/pith-number/3BJJFFCQKQGMP3QL2WIBBB2GXJ/graph.json","events_json":"https://pith.science/api/pith-number/3BJJFFCQKQGMP3QL2WIBBB2GXJ/events.json","paper":"https://pith.science/paper/3BJJFFCQ"},"agent_actions":{"view_html":"https://pith.science/pith/3BJJFFCQKQGMP3QL2WIBBB2GXJ","download_json":"https://pith.science/pith/3BJJFFCQKQGMP3QL2WIBBB2GXJ.json","view_paper":"https://pith.science/paper/3BJJFFCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05169&json=true","fetch_graph":"https://pith.science/api/pith-number/3BJJFFCQKQGMP3QL2WIBBB2GXJ/graph.json","fetch_events":"https://pith.science/api/pith-number/3BJJFFCQKQGMP3QL2WIBBB2GXJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3BJJFFCQKQGMP3QL2WIBBB2GXJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3BJJFFCQKQGMP3QL2WIBBB2GXJ/action/storage_attestation","attest_author":"https://pith.science/pith/3BJJFFCQKQGMP3QL2WIBBB2GXJ/action/author_attestation","sign_citation":"https://pith.science/pith/3BJJFFCQKQGMP3QL2WIBBB2GXJ/action/citation_signature","submit_replication":"https://pith.science/pith/3BJJFFCQKQGMP3QL2WIBBB2GXJ/action/replication_record"}},"created_at":"2026-07-05T12:05:37.214249+00:00","updated_at":"2026-07-05T12:05:37.214249+00:00"}