{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:LXKR4N5RYMBUSVQZ5HMWND76QY","short_pith_number":"pith:LXKR4N5R","schema_version":"1.0","canonical_sha256":"5dd51e37b1c303495619e9d9668ffe861dcecba9d8a0022dd3c525be939aceda","source":{"kind":"arxiv","id":"1608.05148","version":2},"attestation_state":"computed","paper":{"title":"Full Resolution Image Compression with Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Damien Vincent, David Minnen, George Toderici, Joel Shor, Michele Covell, Nick Johnston, Sung Jin Hwang","submitted_at":"2016-08-18T01:05:09Z","abstract_excerpt":"This paper presents a set of full-resolution lossy image compression methods based on neural networks. Each of the architectures we describe can provide variable compression rates during deployment without requiring retraining of the network: each network need only be trained once. All of our architectures consist of a recurrent neural network (RNN)-based encoder and decoder, a binarizer, and a neural network for entropy coding. We compare RNN types (LSTM, associative LSTM) and introduce a new hybrid of GRU and ResNet. We also study \"one-shot\" versus additive reconstruction architectures and i"},"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":"1608.05148","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-18T01:05:09Z","cross_cats_sorted":[],"title_canon_sha256":"9f84b66aac3f192606acab3b92a4539a9784390a0cbec49798a747682b4f0dea","abstract_canon_sha256":"db05739e9be3c0029072d5c6c29fea8ab22174eb2aed49b6e3a6376858a1a367"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:46.677013Z","signature_b64":"1doADYKS+lnBbEk6luZAtGlfNi26Rkyb1c/MyCE8REV/GdK6z1jWEo00ENjbnKuJqm1bOQd/Juu1SAMkb3CXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dd51e37b1c303495619e9d9668ffe861dcecba9d8a0022dd3c525be939aceda","last_reissued_at":"2026-05-18T00:40:46.676433Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:46.676433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Full Resolution Image Compression with Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Damien Vincent, David Minnen, George Toderici, Joel Shor, Michele Covell, Nick Johnston, Sung Jin Hwang","submitted_at":"2016-08-18T01:05:09Z","abstract_excerpt":"This paper presents a set of full-resolution lossy image compression methods based on neural networks. Each of the architectures we describe can provide variable compression rates during deployment without requiring retraining of the network: each network need only be trained once. All of our architectures consist of a recurrent neural network (RNN)-based encoder and decoder, a binarizer, and a neural network for entropy coding. We compare RNN types (LSTM, associative LSTM) and introduce a new hybrid of GRU and ResNet. We also study \"one-shot\" versus additive reconstruction architectures and i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.05148","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":"1608.05148","created_at":"2026-05-18T00:40:46.676507+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.05148v2","created_at":"2026-05-18T00:40:46.676507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.05148","created_at":"2026-05-18T00:40:46.676507+00:00"},{"alias_kind":"pith_short_12","alias_value":"LXKR4N5RYMBU","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"LXKR4N5RYMBUSVQZ","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"LXKR4N5R","created_at":"2026-05-18T12:30:29.479603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LXKR4N5RYMBUSVQZ5HMWND76QY","json":"https://pith.science/pith/LXKR4N5RYMBUSVQZ5HMWND76QY.json","graph_json":"https://pith.science/api/pith-number/LXKR4N5RYMBUSVQZ5HMWND76QY/graph.json","events_json":"https://pith.science/api/pith-number/LXKR4N5RYMBUSVQZ5HMWND76QY/events.json","paper":"https://pith.science/paper/LXKR4N5R"},"agent_actions":{"view_html":"https://pith.science/pith/LXKR4N5RYMBUSVQZ5HMWND76QY","download_json":"https://pith.science/pith/LXKR4N5RYMBUSVQZ5HMWND76QY.json","view_paper":"https://pith.science/paper/LXKR4N5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.05148&json=true","fetch_graph":"https://pith.science/api/pith-number/LXKR4N5RYMBUSVQZ5HMWND76QY/graph.json","fetch_events":"https://pith.science/api/pith-number/LXKR4N5RYMBUSVQZ5HMWND76QY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LXKR4N5RYMBUSVQZ5HMWND76QY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LXKR4N5RYMBUSVQZ5HMWND76QY/action/storage_attestation","attest_author":"https://pith.science/pith/LXKR4N5RYMBUSVQZ5HMWND76QY/action/author_attestation","sign_citation":"https://pith.science/pith/LXKR4N5RYMBUSVQZ5HMWND76QY/action/citation_signature","submit_replication":"https://pith.science/pith/LXKR4N5RYMBUSVQZ5HMWND76QY/action/replication_record"}},"created_at":"2026-05-18T00:40:46.676507+00:00","updated_at":"2026-05-18T00:40:46.676507+00:00"}