{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2F4PHJUKM2UI7AAVYN2SXU3M4O","short_pith_number":"pith:2F4PHJUK","schema_version":"1.0","canonical_sha256":"d178f3a68a66a88f8015c3752bd36ce3b2d8770c3608c4f87dd1e0ad55565085","source":{"kind":"arxiv","id":"2504.16586","version":1},"attestation_state":"computed","paper":{"title":"Learning Switchable Priors for Neural Image Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Dong Liu, Haotian Zhang, Li Li, Yuqi Li","submitted_at":"2025-04-23T10:06:58Z","abstract_excerpt":"Neural image compression (NIC) usually adopts a predefined family of probabilistic distributions as the prior of the latent variables, and meanwhile relies on entropy models to estimate the parameters for the probabilistic family. More complex probabilistic distributions may fit the latent variables more accurately, but also incur higher complexity of the entropy models, limiting their practical value. To address this dilemma, we propose a solution to decouple the entropy model complexity from the prior distributions. We use a finite set of trainable priors that correspond to samples of the pa"},"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":"2504.16586","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-04-23T10:06:58Z","cross_cats_sorted":[],"title_canon_sha256":"c6d02167e291cb4d6a9650f87e086f52dfad0330fee2953574379c18ca796c08","abstract_canon_sha256":"adaf27be3e62ab5ab630f0dd3101f2a3a1a9652d4ccb267ec50792f1786545c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:01.834225Z","signature_b64":"5gNd3J8nkV8/4VMuxKBo0qCu1F3lQ9wXFSWbsMgSuzNgy/FsAxgE5xzHZ0D/ZkTLFG9h70LIMHmqTKbi0ne9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d178f3a68a66a88f8015c3752bd36ce3b2d8770c3608c4f87dd1e0ad55565085","last_reissued_at":"2026-07-05T10:53:01.833762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:01.833762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Switchable Priors for Neural Image Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Dong Liu, Haotian Zhang, Li Li, Yuqi Li","submitted_at":"2025-04-23T10:06:58Z","abstract_excerpt":"Neural image compression (NIC) usually adopts a predefined family of probabilistic distributions as the prior of the latent variables, and meanwhile relies on entropy models to estimate the parameters for the probabilistic family. More complex probabilistic distributions may fit the latent variables more accurately, but also incur higher complexity of the entropy models, limiting their practical value. To address this dilemma, we propose a solution to decouple the entropy model complexity from the prior distributions. We use a finite set of trainable priors that correspond to samples of the pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16586","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/2504.16586/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":"2504.16586","created_at":"2026-07-05T10:53:01.833820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16586v1","created_at":"2026-07-05T10:53:01.833820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16586","created_at":"2026-07-05T10:53:01.833820+00:00"},{"alias_kind":"pith_short_12","alias_value":"2F4PHJUKM2UI","created_at":"2026-07-05T10:53:01.833820+00:00"},{"alias_kind":"pith_short_16","alias_value":"2F4PHJUKM2UI7AAV","created_at":"2026-07-05T10:53:01.833820+00:00"},{"alias_kind":"pith_short_8","alias_value":"2F4PHJUK","created_at":"2026-07-05T10:53:01.833820+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/2F4PHJUKM2UI7AAVYN2SXU3M4O","json":"https://pith.science/pith/2F4PHJUKM2UI7AAVYN2SXU3M4O.json","graph_json":"https://pith.science/api/pith-number/2F4PHJUKM2UI7AAVYN2SXU3M4O/graph.json","events_json":"https://pith.science/api/pith-number/2F4PHJUKM2UI7AAVYN2SXU3M4O/events.json","paper":"https://pith.science/paper/2F4PHJUK"},"agent_actions":{"view_html":"https://pith.science/pith/2F4PHJUKM2UI7AAVYN2SXU3M4O","download_json":"https://pith.science/pith/2F4PHJUKM2UI7AAVYN2SXU3M4O.json","view_paper":"https://pith.science/paper/2F4PHJUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16586&json=true","fetch_graph":"https://pith.science/api/pith-number/2F4PHJUKM2UI7AAVYN2SXU3M4O/graph.json","fetch_events":"https://pith.science/api/pith-number/2F4PHJUKM2UI7AAVYN2SXU3M4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2F4PHJUKM2UI7AAVYN2SXU3M4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2F4PHJUKM2UI7AAVYN2SXU3M4O/action/storage_attestation","attest_author":"https://pith.science/pith/2F4PHJUKM2UI7AAVYN2SXU3M4O/action/author_attestation","sign_citation":"https://pith.science/pith/2F4PHJUKM2UI7AAVYN2SXU3M4O/action/citation_signature","submit_replication":"https://pith.science/pith/2F4PHJUKM2UI7AAVYN2SXU3M4O/action/replication_record"}},"created_at":"2026-07-05T10:53:01.833820+00:00","updated_at":"2026-07-05T10:53:01.833820+00:00"}