{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GNEUBXB54HVKKM7L2RZ56FHWVT","short_pith_number":"pith:GNEUBXB5","schema_version":"1.0","canonical_sha256":"334940dc3de1eaa533ebd473df14f6acd5affafe73b081cfcd99f9c4f2644f21","source":{"kind":"arxiv","id":"1703.00395","version":1},"attestation_state":"computed","paper":{"title":"Lossy Image Compression with Compressive Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"stat.ML","authors_text":"Andrew Cunningham, Ferenc Husz\\'ar, Lucas Theis, Wenzhe Shi","submitted_at":"2017-03-01T17:13:47Z","abstract_excerpt":"We propose a new approach to the problem of optimizing autoencoders for lossy image compression. New media formats, changing hardware technology, as well as diverse requirements and content types create a need for compression algorithms which are more flexible than existing codecs. Autoencoders have the potential to address this need, but are difficult to optimize directly due to the inherent non-differentiabilty of the compression loss. We here show that minimal changes to the loss are sufficient to train deep autoencoders competitive with JPEG 2000 and outperforming recently proposed approac"},"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":"1703.00395","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-01T17:13:47Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e6a82770d4c5ee56083245efbadbf60deae93c57fdb72ffac1ac7362aeb1a2fd","abstract_canon_sha256":"f2981a73443f09e6b6d3b7601f5f42c35ea0b050abc39bbd6c9946bf9844c2f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:43.077423Z","signature_b64":"yLFyyZchtBbWCPYFk0n+hfGPJLOzUX7eiVzWHnnsP8LVl4e+Rg1XO7esyfp4yR/mBbEkqIY5H5eBexLCMcxuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"334940dc3de1eaa533ebd473df14f6acd5affafe73b081cfcd99f9c4f2644f21","last_reissued_at":"2026-05-18T00:49:43.076875Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:43.076875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lossy Image Compression with Compressive Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"stat.ML","authors_text":"Andrew Cunningham, Ferenc Husz\\'ar, Lucas Theis, Wenzhe Shi","submitted_at":"2017-03-01T17:13:47Z","abstract_excerpt":"We propose a new approach to the problem of optimizing autoencoders for lossy image compression. New media formats, changing hardware technology, as well as diverse requirements and content types create a need for compression algorithms which are more flexible than existing codecs. Autoencoders have the potential to address this need, but are difficult to optimize directly due to the inherent non-differentiabilty of the compression loss. We here show that minimal changes to the loss are sufficient to train deep autoencoders competitive with JPEG 2000 and outperforming recently proposed approac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00395","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":""},"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":"1703.00395","created_at":"2026-05-18T00:49:43.076972+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.00395v1","created_at":"2026-05-18T00:49:43.076972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00395","created_at":"2026-05-18T00:49:43.076972+00:00"},{"alias_kind":"pith_short_12","alias_value":"GNEUBXB54HVK","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"GNEUBXB54HVKKM7L","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"GNEUBXB5","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.01714","citing_title":"A Deep Image Compression Framework for Face Recognition","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20672","citing_title":"LANCE: Locally Adaptive Neural Context Estimation for Overfitted Image Compression","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2309.15505","citing_title":"Finite Scalar Quantization: VQ-VAE Made Simple","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02726","citing_title":"Cool-chic 5.0: Faster Encoding and Inter-Feature Entropy Modeling for Overfitted Image Compression","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21984","citing_title":"Soft Anisotropic Diagrams for Differentiable Image Representation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GNEUBXB54HVKKM7L2RZ56FHWVT","json":"https://pith.science/pith/GNEUBXB54HVKKM7L2RZ56FHWVT.json","graph_json":"https://pith.science/api/pith-number/GNEUBXB54HVKKM7L2RZ56FHWVT/graph.json","events_json":"https://pith.science/api/pith-number/GNEUBXB54HVKKM7L2RZ56FHWVT/events.json","paper":"https://pith.science/paper/GNEUBXB5"},"agent_actions":{"view_html":"https://pith.science/pith/GNEUBXB54HVKKM7L2RZ56FHWVT","download_json":"https://pith.science/pith/GNEUBXB54HVKKM7L2RZ56FHWVT.json","view_paper":"https://pith.science/paper/GNEUBXB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.00395&json=true","fetch_graph":"https://pith.science/api/pith-number/GNEUBXB54HVKKM7L2RZ56FHWVT/graph.json","fetch_events":"https://pith.science/api/pith-number/GNEUBXB54HVKKM7L2RZ56FHWVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GNEUBXB54HVKKM7L2RZ56FHWVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GNEUBXB54HVKKM7L2RZ56FHWVT/action/storage_attestation","attest_author":"https://pith.science/pith/GNEUBXB54HVKKM7L2RZ56FHWVT/action/author_attestation","sign_citation":"https://pith.science/pith/GNEUBXB54HVKKM7L2RZ56FHWVT/action/citation_signature","submit_replication":"https://pith.science/pith/GNEUBXB54HVKKM7L2RZ56FHWVT/action/replication_record"}},"created_at":"2026-05-18T00:49:43.076972+00:00","updated_at":"2026-05-18T00:49:43.076972+00:00"}