{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YSGDLWIXRCQXZEIRUAN3DQAETV","short_pith_number":"pith:YSGDLWIX","schema_version":"1.0","canonical_sha256":"c48c35d91788a17c9111a01bb1c0049d71e4453a2aade59bc8c917afa2459b11","source":{"kind":"arxiv","id":"2109.14837","version":1},"attestation_state":"computed","paper":{"title":"End-to-End Image Compression with Probabilistic Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Cunhui Dong, Dong Liu, Feng Wu, Haichuan Ma, Li Li","submitted_at":"2021-09-30T04:07:09Z","abstract_excerpt":"Lossy image compression is a many-to-one process, thus one bitstream corresponds to multiple possible original images, especially at low bit rates. However, this nature was seldom considered in previous studies on image compression, which usually chose one possible image as reconstruction, e.g. the one with the maximal a posteriori probability. We propose a learned image compression framework to natively support probabilistic decoding. The compressed bitstream is decoded into a series of parameters that instantiate a pre-chosen distribution; then the distribution is used by the decoder to samp"},"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":"2109.14837","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2021-09-30T04:07:09Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ea90eb7a0205fa4da026807a28e7f282037461a77a37eb0a9eace32e0d82af4b","abstract_canon_sha256":"225d111aea835f2b0790f22d87f2594ed57f50c7f7a352842c1d41c7fe61b7f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:18:44.844997Z","signature_b64":"2K16h5KQtHQDf1P1CubyGP6TBasq2ZtMz0sagHIFZUPMAQH789F95WnJ5N+8Z38uh/7zb8iwzVZnn6b25wLFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c48c35d91788a17c9111a01bb1c0049d71e4453a2aade59bc8c917afa2459b11","last_reissued_at":"2026-07-05T03:18:44.844592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:18:44.844592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Image Compression with Probabilistic Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Cunhui Dong, Dong Liu, Feng Wu, Haichuan Ma, Li Li","submitted_at":"2021-09-30T04:07:09Z","abstract_excerpt":"Lossy image compression is a many-to-one process, thus one bitstream corresponds to multiple possible original images, especially at low bit rates. However, this nature was seldom considered in previous studies on image compression, which usually chose one possible image as reconstruction, e.g. the one with the maximal a posteriori probability. We propose a learned image compression framework to natively support probabilistic decoding. The compressed bitstream is decoded into a series of parameters that instantiate a pre-chosen distribution; then the distribution is used by the decoder to samp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.14837","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/2109.14837/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":"2109.14837","created_at":"2026-07-05T03:18:44.844654+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.14837v1","created_at":"2026-07-05T03:18:44.844654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.14837","created_at":"2026-07-05T03:18:44.844654+00:00"},{"alias_kind":"pith_short_12","alias_value":"YSGDLWIXRCQX","created_at":"2026-07-05T03:18:44.844654+00:00"},{"alias_kind":"pith_short_16","alias_value":"YSGDLWIXRCQXZEIR","created_at":"2026-07-05T03:18:44.844654+00:00"},{"alias_kind":"pith_short_8","alias_value":"YSGDLWIX","created_at":"2026-07-05T03:18:44.844654+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.12330","citing_title":"The Gap Between Principle and Practice of Lossy Image Coding","ref_index":66,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YSGDLWIXRCQXZEIRUAN3DQAETV","json":"https://pith.science/pith/YSGDLWIXRCQXZEIRUAN3DQAETV.json","graph_json":"https://pith.science/api/pith-number/YSGDLWIXRCQXZEIRUAN3DQAETV/graph.json","events_json":"https://pith.science/api/pith-number/YSGDLWIXRCQXZEIRUAN3DQAETV/events.json","paper":"https://pith.science/paper/YSGDLWIX"},"agent_actions":{"view_html":"https://pith.science/pith/YSGDLWIXRCQXZEIRUAN3DQAETV","download_json":"https://pith.science/pith/YSGDLWIXRCQXZEIRUAN3DQAETV.json","view_paper":"https://pith.science/paper/YSGDLWIX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.14837&json=true","fetch_graph":"https://pith.science/api/pith-number/YSGDLWIXRCQXZEIRUAN3DQAETV/graph.json","fetch_events":"https://pith.science/api/pith-number/YSGDLWIXRCQXZEIRUAN3DQAETV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YSGDLWIXRCQXZEIRUAN3DQAETV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YSGDLWIXRCQXZEIRUAN3DQAETV/action/storage_attestation","attest_author":"https://pith.science/pith/YSGDLWIXRCQXZEIRUAN3DQAETV/action/author_attestation","sign_citation":"https://pith.science/pith/YSGDLWIXRCQXZEIRUAN3DQAETV/action/citation_signature","submit_replication":"https://pith.science/pith/YSGDLWIXRCQXZEIRUAN3DQAETV/action/replication_record"}},"created_at":"2026-07-05T03:18:44.844654+00:00","updated_at":"2026-07-05T03:18:44.844654+00:00"}