{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GUD5CXISKW52EIGHTVUYJ7Y5GW","short_pith_number":"pith:GUD5CXIS","schema_version":"1.0","canonical_sha256":"3507d15d1255bba220c79d6984ff1d35904b32ee0c09fa06c72d404d377fd5fc","source":{"kind":"arxiv","id":"2405.15413","version":3},"attestation_state":"computed","paper":{"title":"MambaVC: Learned Visual Compression with Selective State Spaces","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CV","cs.IT","math.IT"],"primary_cat":"eess.IV","authors_text":"Baoyi An, Bin Chen, Jinpeng Wang, Shiyu Qin, Shutao Xia, Tao Dai, Tianci Luo, Yaowei Wang, Yimin Zhou","submitted_at":"2024-05-24T10:24:30Z","abstract_excerpt":"Learned visual compression is an important and active task in multimedia. Existing approaches have explored various CNN- and Transformer-based designs to model content distribution and eliminate redundancy, where balancing efficacy (i.e., rate-distortion trade-off) and efficiency remains a challenge. Recently, state-space models (SSMs) have shown promise due to their long-range modeling capacity and efficiency. Inspired by this, we take the first step to explore SSMs for visual compression. We introduce MambaVC, a simple, strong and efficient compression network based on SSM. MambaVC develops "},"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":"2405.15413","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.IV","submitted_at":"2024-05-24T10:24:30Z","cross_cats_sorted":["cs.CV","cs.IT","math.IT"],"title_canon_sha256":"9adbde5161b3025d9c2535cb39eb2acbca3e0849cafccf58a052c97af5d6f865","abstract_canon_sha256":"8b8fd8dc769da9178d08ab3a14a3f38973a9840b37009c13950a284e699d78f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:06.433991Z","signature_b64":"mM1SEDrefEcEwSJGxTaCrrT6erxSbQ9oVNvxpe6r6kQ9oso51AmwRVqvxaOtGACaLa9gCZlaDB5xzgXv3AucBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3507d15d1255bba220c79d6984ff1d35904b32ee0c09fa06c72d404d377fd5fc","last_reissued_at":"2026-07-05T08:24:06.433454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:06.433454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MambaVC: Learned Visual Compression with Selective State Spaces","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CV","cs.IT","math.IT"],"primary_cat":"eess.IV","authors_text":"Baoyi An, Bin Chen, Jinpeng Wang, Shiyu Qin, Shutao Xia, Tao Dai, Tianci Luo, Yaowei Wang, Yimin Zhou","submitted_at":"2024-05-24T10:24:30Z","abstract_excerpt":"Learned visual compression is an important and active task in multimedia. Existing approaches have explored various CNN- and Transformer-based designs to model content distribution and eliminate redundancy, where balancing efficacy (i.e., rate-distortion trade-off) and efficiency remains a challenge. Recently, state-space models (SSMs) have shown promise due to their long-range modeling capacity and efficiency. Inspired by this, we take the first step to explore SSMs for visual compression. We introduce MambaVC, a simple, strong and efficient compression network based on SSM. MambaVC develops "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15413","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/2405.15413/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":"2405.15413","created_at":"2026-07-05T08:24:06.433515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15413v3","created_at":"2026-07-05T08:24:06.433515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15413","created_at":"2026-07-05T08:24:06.433515+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUD5CXISKW52","created_at":"2026-07-05T08:24:06.433515+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUD5CXISKW52EIGH","created_at":"2026-07-05T08:24:06.433515+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUD5CXIS","created_at":"2026-07-05T08:24:06.433515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00111","citing_title":"ChWDTA: Channel-wise Wavelet-Domain Transformer Attention and Entropy Modeling for Learned Image Compression","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20151","citing_title":"A Compact Hybrid Convolution--Frequency State Space Network for Learned Image Compression","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2601.22002","citing_title":"Understanding Rate-Distortion Performance in Distributed Transformer Inference","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04560","citing_title":"SAMIC: A Lightweight Semantic-Aware Mamba for Efficient Perceptual Image Compression","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GUD5CXISKW52EIGHTVUYJ7Y5GW","json":"https://pith.science/pith/GUD5CXISKW52EIGHTVUYJ7Y5GW.json","graph_json":"https://pith.science/api/pith-number/GUD5CXISKW52EIGHTVUYJ7Y5GW/graph.json","events_json":"https://pith.science/api/pith-number/GUD5CXISKW52EIGHTVUYJ7Y5GW/events.json","paper":"https://pith.science/paper/GUD5CXIS"},"agent_actions":{"view_html":"https://pith.science/pith/GUD5CXISKW52EIGHTVUYJ7Y5GW","download_json":"https://pith.science/pith/GUD5CXISKW52EIGHTVUYJ7Y5GW.json","view_paper":"https://pith.science/paper/GUD5CXIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15413&json=true","fetch_graph":"https://pith.science/api/pith-number/GUD5CXISKW52EIGHTVUYJ7Y5GW/graph.json","fetch_events":"https://pith.science/api/pith-number/GUD5CXISKW52EIGHTVUYJ7Y5GW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUD5CXISKW52EIGHTVUYJ7Y5GW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUD5CXISKW52EIGHTVUYJ7Y5GW/action/storage_attestation","attest_author":"https://pith.science/pith/GUD5CXISKW52EIGHTVUYJ7Y5GW/action/author_attestation","sign_citation":"https://pith.science/pith/GUD5CXISKW52EIGHTVUYJ7Y5GW/action/citation_signature","submit_replication":"https://pith.science/pith/GUD5CXISKW52EIGHTVUYJ7Y5GW/action/replication_record"}},"created_at":"2026-07-05T08:24:06.433515+00:00","updated_at":"2026-07-05T08:24:06.433515+00:00"}