{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AKFGYZRMVS7MD3H7PQ6PEMJH2I","short_pith_number":"pith:AKFGYZRM","schema_version":"1.0","canonical_sha256":"028a6c662cacbec1ecff7c3cf23127d22c2f22498097e64a45a2b4fdf2ed5507","source":{"kind":"arxiv","id":"2402.16749","version":3},"attestation_state":"computed","paper":{"title":"MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.IV"],"primary_cat":"cs.CV","authors_text":"Chunyi Li, Donghui Feng, Guangtao Zhai, Guo Lu, Haoning Wu, Weisi Lin, Wenjun Zhang, Xiaohong Liu, Zicheng Zhang","submitted_at":"2024-02-26T17:11:11Z","abstract_excerpt":"With the evolution of storage and communication protocols, ultra-low bitrate image compression has become a highly demanding topic. However, existing compression algorithms must sacrifice either consistency with the ground truth or perceptual quality at ultra-low bitrate. In recent years, the rapid development of the Large Multimodal Model (LMM) has made it possible to balance these two goals. To solve this problem, this paper proposes a method called Multimodal Image Semantic Compression (MISC), which consists of an LMM encoder for extracting the semantic information of the image, a map encod"},"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":"2402.16749","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-26T17:11:11Z","cross_cats_sorted":["cs.AI","eess.IV"],"title_canon_sha256":"2253892d775595c3e6ada9b9aaf777856a6b5f1e93322ca91f4d4fd2aec1921f","abstract_canon_sha256":"a19711e0a1bf9b422cc7d3c95020765e765f0b6259348317e202033ecc70a068"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:55.386868Z","signature_b64":"Kr3snGAx9FBX5Ye27JgB0K6MxiTE1NU2xAOwszqmhHtYVCbHs6x6UdilaUjiG5MYSrTJshrnOf5b6nf6HiTxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"028a6c662cacbec1ecff7c3cf23127d22c2f22498097e64a45a2b4fdf2ed5507","last_reissued_at":"2026-07-05T08:08:55.386407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:55.386407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.IV"],"primary_cat":"cs.CV","authors_text":"Chunyi Li, Donghui Feng, Guangtao Zhai, Guo Lu, Haoning Wu, Weisi Lin, Wenjun Zhang, Xiaohong Liu, Zicheng Zhang","submitted_at":"2024-02-26T17:11:11Z","abstract_excerpt":"With the evolution of storage and communication protocols, ultra-low bitrate image compression has become a highly demanding topic. However, existing compression algorithms must sacrifice either consistency with the ground truth or perceptual quality at ultra-low bitrate. In recent years, the rapid development of the Large Multimodal Model (LMM) has made it possible to balance these two goals. To solve this problem, this paper proposes a method called Multimodal Image Semantic Compression (MISC), which consists of an LMM encoder for extracting the semantic information of the image, a map encod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16749","kind":"arxiv","version":3},"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/2402.16749/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":"2402.16749","created_at":"2026-07-05T08:08:55.386462+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16749v3","created_at":"2026-07-05T08:08:55.386462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16749","created_at":"2026-07-05T08:08:55.386462+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKFGYZRMVS7M","created_at":"2026-07-05T08:08:55.386462+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKFGYZRMVS7MD3H7","created_at":"2026-07-05T08:08:55.386462+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKFGYZRM","created_at":"2026-07-05T08:08:55.386462+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.18158","citing_title":"Semantics Disentanglement and Composition for Universal Image Coding with Efficiently LLM Reasoning and Generative Diffusion","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AKFGYZRMVS7MD3H7PQ6PEMJH2I","json":"https://pith.science/pith/AKFGYZRMVS7MD3H7PQ6PEMJH2I.json","graph_json":"https://pith.science/api/pith-number/AKFGYZRMVS7MD3H7PQ6PEMJH2I/graph.json","events_json":"https://pith.science/api/pith-number/AKFGYZRMVS7MD3H7PQ6PEMJH2I/events.json","paper":"https://pith.science/paper/AKFGYZRM"},"agent_actions":{"view_html":"https://pith.science/pith/AKFGYZRMVS7MD3H7PQ6PEMJH2I","download_json":"https://pith.science/pith/AKFGYZRMVS7MD3H7PQ6PEMJH2I.json","view_paper":"https://pith.science/paper/AKFGYZRM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16749&json=true","fetch_graph":"https://pith.science/api/pith-number/AKFGYZRMVS7MD3H7PQ6PEMJH2I/graph.json","fetch_events":"https://pith.science/api/pith-number/AKFGYZRMVS7MD3H7PQ6PEMJH2I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKFGYZRMVS7MD3H7PQ6PEMJH2I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKFGYZRMVS7MD3H7PQ6PEMJH2I/action/storage_attestation","attest_author":"https://pith.science/pith/AKFGYZRMVS7MD3H7PQ6PEMJH2I/action/author_attestation","sign_citation":"https://pith.science/pith/AKFGYZRMVS7MD3H7PQ6PEMJH2I/action/citation_signature","submit_replication":"https://pith.science/pith/AKFGYZRMVS7MD3H7PQ6PEMJH2I/action/replication_record"}},"created_at":"2026-07-05T08:08:55.386462+00:00","updated_at":"2026-07-05T08:08:55.386462+00:00"}