{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WUYKHNNWIVECMBH2ZBVVZGASGJ","short_pith_number":"pith:WUYKHNNW","schema_version":"1.0","canonical_sha256":"b530a3b5b645482604fac86b5c98123277ad78a62085886a2404087622f74008","source":{"kind":"arxiv","id":"2111.10302","version":2},"attestation_state":"computed","paper":{"title":"Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Set","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Auke Wiggers, Johann Brehmer, Reza Pourreza, Taco S. Cohen, Ties van Rozendaal, Yunfan Zhang","submitted_at":"2021-11-19T16:25:34Z","abstract_excerpt":"We introduce a video compression algorithm based on instance-adaptive learning. On each video sequence to be transmitted, we finetune a pretrained compression model. The optimal parameters are transmitted to the receiver along with the latent code. By entropy-coding the parameter updates under a suitable mixture model prior, we ensure that the network parameters can be encoded efficiently. This instance-adaptive compression algorithm is agnostic about the choice of base model and has the potential to improve any neural video codec. On UVG, HEVC, and Xiph datasets, our codec improves the perfor"},"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":"2111.10302","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2021-11-19T16:25:34Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"367e590286fdce60a71df67cae2207f17017aaf7db7712dcbbbe81c899dd8eb6","abstract_canon_sha256":"ee6d8c2ec01de36784890b50f91dd2a8a06bfc8896ee36ba78ac0a746f9bf627"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:53.047979Z","signature_b64":"m9egvf1xumrc9yDIe+5xKrr3oSBRMwIW2OWzDWDJinV1PPW7nrrI4wyS9SEQPxgQ0AXQGNdFryrMtPsLEWUkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b530a3b5b645482604fac86b5c98123277ad78a62085886a2404087622f74008","last_reissued_at":"2026-07-05T06:23:53.047515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:53.047515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Set","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Auke Wiggers, Johann Brehmer, Reza Pourreza, Taco S. Cohen, Ties van Rozendaal, Yunfan Zhang","submitted_at":"2021-11-19T16:25:34Z","abstract_excerpt":"We introduce a video compression algorithm based on instance-adaptive learning. On each video sequence to be transmitted, we finetune a pretrained compression model. The optimal parameters are transmitted to the receiver along with the latent code. By entropy-coding the parameter updates under a suitable mixture model prior, we ensure that the network parameters can be encoded efficiently. This instance-adaptive compression algorithm is agnostic about the choice of base model and has the potential to improve any neural video codec. On UVG, HEVC, and Xiph datasets, our codec improves the perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10302","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.10302/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":"2111.10302","created_at":"2026-07-05T06:23:53.047570+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.10302v2","created_at":"2026-07-05T06:23:53.047570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10302","created_at":"2026-07-05T06:23:53.047570+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUYKHNNWIVEC","created_at":"2026-07-05T06:23:53.047570+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUYKHNNWIVECMBH2","created_at":"2026-07-05T06:23:53.047570+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUYKHNNW","created_at":"2026-07-05T06:23:53.047570+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.19442","citing_title":"MCUCoder: Adaptive Bitrate Learned Video Compression for IoT Devices","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WUYKHNNWIVECMBH2ZBVVZGASGJ","json":"https://pith.science/pith/WUYKHNNWIVECMBH2ZBVVZGASGJ.json","graph_json":"https://pith.science/api/pith-number/WUYKHNNWIVECMBH2ZBVVZGASGJ/graph.json","events_json":"https://pith.science/api/pith-number/WUYKHNNWIVECMBH2ZBVVZGASGJ/events.json","paper":"https://pith.science/paper/WUYKHNNW"},"agent_actions":{"view_html":"https://pith.science/pith/WUYKHNNWIVECMBH2ZBVVZGASGJ","download_json":"https://pith.science/pith/WUYKHNNWIVECMBH2ZBVVZGASGJ.json","view_paper":"https://pith.science/paper/WUYKHNNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.10302&json=true","fetch_graph":"https://pith.science/api/pith-number/WUYKHNNWIVECMBH2ZBVVZGASGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WUYKHNNWIVECMBH2ZBVVZGASGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUYKHNNWIVECMBH2ZBVVZGASGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUYKHNNWIVECMBH2ZBVVZGASGJ/action/storage_attestation","attest_author":"https://pith.science/pith/WUYKHNNWIVECMBH2ZBVVZGASGJ/action/author_attestation","sign_citation":"https://pith.science/pith/WUYKHNNWIVECMBH2ZBVVZGASGJ/action/citation_signature","submit_replication":"https://pith.science/pith/WUYKHNNWIVECMBH2ZBVVZGASGJ/action/replication_record"}},"created_at":"2026-07-05T06:23:53.047570+00:00","updated_at":"2026-07-05T06:23:53.047570+00:00"}