{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NPABLLZEYSZNTXLJZHII37PBSO","short_pith_number":"pith:NPABLLZE","schema_version":"1.0","canonical_sha256":"6bc015af24c4b2d9dd69c9d08dfde193adf5520306339bbcc24c25cdbb672837","source":{"kind":"arxiv","id":"1802.01436","version":2},"attestation_state":"computed","paper":{"title":"Variational image compression with a scale hyperprior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"eess.IV","authors_text":"David Minnen, Johannes Ball\\'e, Nick Johnston, Saurabh Singh, Sung Jin Hwang","submitted_at":"2018-02-01T00:42:29Z","abstract_excerpt":"We describe an end-to-end trainable model for image compression based on variational autoencoders. The model incorporates a hyperprior to effectively capture spatial dependencies in the latent representation. This hyperprior relates to side information, a concept universal to virtually all modern image codecs, but largely unexplored in image compression using artificial neural networks (ANNs). Unlike existing autoencoder compression methods, our model trains a complex prior jointly with the underlying autoencoder. We demonstrate that this model leads to state-of-the-art image compression when "},"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":"1802.01436","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2018-02-01T00:42:29Z","cross_cats_sorted":["cs.IT","math.IT"],"title_canon_sha256":"acbaad556cab0d65fc84ff78c3722a7477d3b1e448666441de3484b75c0eebb4","abstract_canon_sha256":"4bd472b8f1694364bb5a044234c8b9f62bbdf0013af1c6ab17b4cdbca626a7c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:10.921567Z","signature_b64":"JM/8iTGi/mthOlF6EzK0EzfFMyY/O7r1cLx87A71jW8wdMiiI3cWWSvO2eKpm0/ZwSi/N0hshK/2ods7iMoWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bc015af24c4b2d9dd69c9d08dfde193adf5520306339bbcc24c25cdbb672837","last_reissued_at":"2026-05-18T00:17:10.920828Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:10.920828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational image compression with a scale hyperprior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT"],"primary_cat":"eess.IV","authors_text":"David Minnen, Johannes Ball\\'e, Nick Johnston, Saurabh Singh, Sung Jin Hwang","submitted_at":"2018-02-01T00:42:29Z","abstract_excerpt":"We describe an end-to-end trainable model for image compression based on variational autoencoders. The model incorporates a hyperprior to effectively capture spatial dependencies in the latent representation. This hyperprior relates to side information, a concept universal to virtually all modern image codecs, but largely unexplored in image compression using artificial neural networks (ANNs). Unlike existing autoencoder compression methods, our model trains a complex prior jointly with the underlying autoencoder. We demonstrate that this model leads to state-of-the-art image compression when "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.01436","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1802.01436","created_at":"2026-05-18T00:17:10.920922+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.01436v2","created_at":"2026-05-18T00:17:10.920922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.01436","created_at":"2026-05-18T00:17:10.920922+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPABLLZEYSZN","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPABLLZEYSZNTXLJ","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPABLLZE","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"1907.02942","citing_title":"Deep Convolutional Compression for Massive MIMO CSI Feedback","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2512.20901","citing_title":"Benchmarking and Enhancing VLM for Compressed Image Understanding","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2411.12228","citing_title":"Robust Deep Joint Source-Channel Coding Enabled Distributed Image Transmission with Imperfect Channel State Information","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17499","citing_title":"t-gems: text-guided exit modules for decreasing clip image encoder","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2603.26571","citing_title":"GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08633","citing_title":"Transforming the Use of Earth Observation Data: Exascale Training of a Generative Compression Model with Historical Priors for up to 10,000x Data Reduction","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09479","citing_title":"ML-CLIPSim: Multi-Layer CLIP Similarity for Machine-Oriented Image Quality","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09646","citing_title":"\"Training robust watermarking model may hurt authentication!'' Exploring and Mitigating the Identity Leakage in Robust Watermarking","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25330","citing_title":"Generalizable 3D Gaussian Splatting enabled Semantic Coding for Real-Time Immersive Video Communications","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04560","citing_title":"SAMIC: A Lightweight Semantic-Aware Mamba for Efficient Perceptual Image Compression","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13500","citing_title":"Autoencoder-Based CSI Compression for Beyond Wi-Fi 8 Coordinated Beamforming","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13294","citing_title":"PAT-VCM: Plug-and-Play Auxiliary Tokens for Video Coding for Machines","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10546","citing_title":"Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPABLLZEYSZNTXLJZHII37PBSO","json":"https://pith.science/pith/NPABLLZEYSZNTXLJZHII37PBSO.json","graph_json":"https://pith.science/api/pith-number/NPABLLZEYSZNTXLJZHII37PBSO/graph.json","events_json":"https://pith.science/api/pith-number/NPABLLZEYSZNTXLJZHII37PBSO/events.json","paper":"https://pith.science/paper/NPABLLZE"},"agent_actions":{"view_html":"https://pith.science/pith/NPABLLZEYSZNTXLJZHII37PBSO","download_json":"https://pith.science/pith/NPABLLZEYSZNTXLJZHII37PBSO.json","view_paper":"https://pith.science/paper/NPABLLZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.01436&json=true","fetch_graph":"https://pith.science/api/pith-number/NPABLLZEYSZNTXLJZHII37PBSO/graph.json","fetch_events":"https://pith.science/api/pith-number/NPABLLZEYSZNTXLJZHII37PBSO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPABLLZEYSZNTXLJZHII37PBSO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPABLLZEYSZNTXLJZHII37PBSO/action/storage_attestation","attest_author":"https://pith.science/pith/NPABLLZEYSZNTXLJZHII37PBSO/action/author_attestation","sign_citation":"https://pith.science/pith/NPABLLZEYSZNTXLJZHII37PBSO/action/citation_signature","submit_replication":"https://pith.science/pith/NPABLLZEYSZNTXLJZHII37PBSO/action/replication_record"}},"created_at":"2026-05-18T00:17:10.920922+00:00","updated_at":"2026-05-18T00:17:10.920922+00:00"}