{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OUTME62DX7BCDLOEFYVLMZSGPU","short_pith_number":"pith:OUTME62D","schema_version":"1.0","canonical_sha256":"7526c27b43bfc221adc42e2ab666467d185ba8b1be342b39d4ba79f56dd0ed46","source":{"kind":"arxiv","id":"2506.01221","version":1},"attestation_state":"computed","paper":{"title":"Flexible Mixed Precision Quantization for Learned Image Compression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.IV","authors_text":"Fengqing Zhu, Md Adnan Faisal Hossain, Zhihao Duan","submitted_at":"2025-06-02T00:12:50Z","abstract_excerpt":"Despite its improvements in coding performance compared to traditional codecs, Learned Image Compression (LIC) suffers from large computational costs for storage and deployment. Model quantization offers an effective solution to reduce the computational complexity of LIC models. However, most existing works perform fixed-precision quantization which suffers from sub-optimal utilization of resources due to the varying sensitivity to quantization of different layers of a neural network. In this paper, we propose a Flexible Mixed Precision Quantization (FMPQ) method that assigns different bit-wid"},"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":"2506.01221","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.IV","submitted_at":"2025-06-02T00:12:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"14427402750aa931e4aca87c5a869ef618111f073a5da1f41b7e0c3803d51e1e","abstract_canon_sha256":"bd360df7d83eeeaf55ca4c0173400005733642db6cd04fb31813c11e0af52ef5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:48.295428Z","signature_b64":"r+SMGJy8cn5XG1nAs0qJJFVwvlr9sU/UrX15YiBOmCrmVKwuzUuUV45DJoM0taiGshcmiEqayAxYRKFh8zdCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7526c27b43bfc221adc42e2ab666467d185ba8b1be342b39d4ba79f56dd0ed46","last_reissued_at":"2026-07-05T11:13:48.294976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:48.294976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flexible Mixed Precision Quantization for Learned Image Compression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.IV","authors_text":"Fengqing Zhu, Md Adnan Faisal Hossain, Zhihao Duan","submitted_at":"2025-06-02T00:12:50Z","abstract_excerpt":"Despite its improvements in coding performance compared to traditional codecs, Learned Image Compression (LIC) suffers from large computational costs for storage and deployment. Model quantization offers an effective solution to reduce the computational complexity of LIC models. However, most existing works perform fixed-precision quantization which suffers from sub-optimal utilization of resources due to the varying sensitivity to quantization of different layers of a neural network. In this paper, we propose a Flexible Mixed Precision Quantization (FMPQ) method that assigns different bit-wid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01221","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/2506.01221/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":"2506.01221","created_at":"2026-07-05T11:13:48.295032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01221v1","created_at":"2026-07-05T11:13:48.295032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01221","created_at":"2026-07-05T11:13:48.295032+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUTME62DX7BC","created_at":"2026-07-05T11:13:48.295032+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUTME62DX7BCDLOE","created_at":"2026-07-05T11:13:48.295032+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUTME62D","created_at":"2026-07-05T11:13:48.295032+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/OUTME62DX7BCDLOEFYVLMZSGPU","json":"https://pith.science/pith/OUTME62DX7BCDLOEFYVLMZSGPU.json","graph_json":"https://pith.science/api/pith-number/OUTME62DX7BCDLOEFYVLMZSGPU/graph.json","events_json":"https://pith.science/api/pith-number/OUTME62DX7BCDLOEFYVLMZSGPU/events.json","paper":"https://pith.science/paper/OUTME62D"},"agent_actions":{"view_html":"https://pith.science/pith/OUTME62DX7BCDLOEFYVLMZSGPU","download_json":"https://pith.science/pith/OUTME62DX7BCDLOEFYVLMZSGPU.json","view_paper":"https://pith.science/paper/OUTME62D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01221&json=true","fetch_graph":"https://pith.science/api/pith-number/OUTME62DX7BCDLOEFYVLMZSGPU/graph.json","fetch_events":"https://pith.science/api/pith-number/OUTME62DX7BCDLOEFYVLMZSGPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUTME62DX7BCDLOEFYVLMZSGPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUTME62DX7BCDLOEFYVLMZSGPU/action/storage_attestation","attest_author":"https://pith.science/pith/OUTME62DX7BCDLOEFYVLMZSGPU/action/author_attestation","sign_citation":"https://pith.science/pith/OUTME62DX7BCDLOEFYVLMZSGPU/action/citation_signature","submit_replication":"https://pith.science/pith/OUTME62DX7BCDLOEFYVLMZSGPU/action/replication_record"}},"created_at":"2026-07-05T11:13:48.295032+00:00","updated_at":"2026-07-05T11:13:48.295032+00:00"}