{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UYSVFQ3PCVVJVIRIN4WBTCBBRW","short_pith_number":"pith:UYSVFQ3P","schema_version":"1.0","canonical_sha256":"a62552c36f156a9aa2286f2c1988218d9ca683803f02122a5544dd986f841ac2","source":{"kind":"arxiv","id":"2505.22438","version":1},"attestation_state":"computed","paper":{"title":"Synonymous Variational Inference for Perceptual Image Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","eess.IV","math.IT"],"primary_cat":"cs.IT","authors_text":"Changshuo Wang, Jin Xu, Kai Niu, Ping Zhang, Zijian Liang","submitted_at":"2025-05-28T15:03:27Z","abstract_excerpt":"Recent contributions of semantic information theory reveal the set-element relationship between semantic and syntactic information, represented as synonymous relationships. In this paper, we propose a synonymous variational inference (SVI) method based on this synonymity viewpoint to re-analyze the perceptual image compression problem. It takes perceptual similarity as a typical synonymous criterion to build an ideal synonymous set (Synset), and approximate the posterior of its latent synonymous representation with a parametric density by minimizing a partial semantic KL divergence. This analy"},"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":"2505.22438","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2025-05-28T15:03:27Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","eess.IV","math.IT"],"title_canon_sha256":"9458ae1a54a36383d24f3a22618d6bd0f245b5b6fde32f562ba06a6d6c7202e5","abstract_canon_sha256":"e733fe2cb35635924deb8784461da05f6dcf4dba8eb98c6e4b341f15e65d1aca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:24.080596Z","signature_b64":"pzdfi+DUYhFHcDRAjVxn7/8p8wLJQ5ebnJAdX+i5opEkf6eAKDNlo6SeNQqY5LlEYqKUWlbmIAPNiKu1pUYMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a62552c36f156a9aa2286f2c1988218d9ca683803f02122a5544dd986f841ac2","last_reissued_at":"2026-07-05T11:11:24.080087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:24.080087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synonymous Variational Inference for Perceptual Image Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","eess.IV","math.IT"],"primary_cat":"cs.IT","authors_text":"Changshuo Wang, Jin Xu, Kai Niu, Ping Zhang, Zijian Liang","submitted_at":"2025-05-28T15:03:27Z","abstract_excerpt":"Recent contributions of semantic information theory reveal the set-element relationship between semantic and syntactic information, represented as synonymous relationships. In this paper, we propose a synonymous variational inference (SVI) method based on this synonymity viewpoint to re-analyze the perceptual image compression problem. It takes perceptual similarity as a typical synonymous criterion to build an ideal synonymous set (Synset), and approximate the posterior of its latent synonymous representation with a parametric density by minimizing a partial semantic KL divergence. This analy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22438","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/2505.22438/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":"2505.22438","created_at":"2026-07-05T11:11:24.080147+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22438v1","created_at":"2026-07-05T11:11:24.080147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22438","created_at":"2026-07-05T11:11:24.080147+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYSVFQ3PCVVJ","created_at":"2026-07-05T11:11:24.080147+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYSVFQ3PCVVJVIRI","created_at":"2026-07-05T11:11:24.080147+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYSVFQ3P","created_at":"2026-07-05T11:11:24.080147+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10546","citing_title":"Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UYSVFQ3PCVVJVIRIN4WBTCBBRW","json":"https://pith.science/pith/UYSVFQ3PCVVJVIRIN4WBTCBBRW.json","graph_json":"https://pith.science/api/pith-number/UYSVFQ3PCVVJVIRIN4WBTCBBRW/graph.json","events_json":"https://pith.science/api/pith-number/UYSVFQ3PCVVJVIRIN4WBTCBBRW/events.json","paper":"https://pith.science/paper/UYSVFQ3P"},"agent_actions":{"view_html":"https://pith.science/pith/UYSVFQ3PCVVJVIRIN4WBTCBBRW","download_json":"https://pith.science/pith/UYSVFQ3PCVVJVIRIN4WBTCBBRW.json","view_paper":"https://pith.science/paper/UYSVFQ3P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22438&json=true","fetch_graph":"https://pith.science/api/pith-number/UYSVFQ3PCVVJVIRIN4WBTCBBRW/graph.json","fetch_events":"https://pith.science/api/pith-number/UYSVFQ3PCVVJVIRIN4WBTCBBRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYSVFQ3PCVVJVIRIN4WBTCBBRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYSVFQ3PCVVJVIRIN4WBTCBBRW/action/storage_attestation","attest_author":"https://pith.science/pith/UYSVFQ3PCVVJVIRIN4WBTCBBRW/action/author_attestation","sign_citation":"https://pith.science/pith/UYSVFQ3PCVVJVIRIN4WBTCBBRW/action/citation_signature","submit_replication":"https://pith.science/pith/UYSVFQ3PCVVJVIRIN4WBTCBBRW/action/replication_record"}},"created_at":"2026-07-05T11:11:24.080147+00:00","updated_at":"2026-07-05T11:11:24.080147+00:00"}