{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FBBTAO2UVXT2JPX4H4YGOKWUB7","short_pith_number":"pith:FBBTAO2U","schema_version":"1.0","canonical_sha256":"2843303b54ade7a4befc3f30672ad40fdff8603934af22f08d6f7a74b5b0a986","source":{"kind":"arxiv","id":"2111.01662","version":1},"attestation_state":"computed","paper":{"title":"OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chen Zhang, Fabio Maria Carlucci, Shifeng Zhang, Zhenguo Li","submitted_at":"2021-11-02T15:18:25Z","abstract_excerpt":"Explicit deep generative models (DGMs), e.g., VAEs and Normalizing Flows, have shown to offer an effective data modelling alternative for lossless compression. However, DGMs themselves normally require large storage space and thus contaminate the advantage brought by accurate data density estimation. To eliminate the requirement of saving separate models for different target datasets, we propose a novel setting that starts from a pretrained deep generative model and compresses the data batches while adapting the model with a dynamical system for only one epoch. We formalise this setting as tha"},"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":"2111.01662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-02T15:18:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fe884cbe6891511c9512f35216d90b8897c4bff9718af175d750476ff3c6a86b","abstract_canon_sha256":"31ad76005b98062dc7a43279d4e5c374699f3a61dc4c8b1f8d0b41e9daefc41a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:28:31.579560Z","signature_b64":"O7P++j4K85/2vPn2wzniB5Ddph+HIj0NgaUaT+c4OBTBkOcW2jk37WKFCTBbCmDGPV5vKkNqHi7Lgy9bC9kZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2843303b54ade7a4befc3f30672ad40fdff8603934af22f08d6f7a74b5b0a986","last_reissued_at":"2026-07-05T03:28:31.579080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:28:31.579080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OSOA: One-Shot Online Adaptation of Deep Generative Models for Lossless Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chen Zhang, Fabio Maria Carlucci, Shifeng Zhang, Zhenguo Li","submitted_at":"2021-11-02T15:18:25Z","abstract_excerpt":"Explicit deep generative models (DGMs), e.g., VAEs and Normalizing Flows, have shown to offer an effective data modelling alternative for lossless compression. However, DGMs themselves normally require large storage space and thus contaminate the advantage brought by accurate data density estimation. To eliminate the requirement of saving separate models for different target datasets, we propose a novel setting that starts from a pretrained deep generative model and compresses the data batches while adapting the model with a dynamical system for only one epoch. We formalise this setting as tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.01662","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/2111.01662/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":"2111.01662","created_at":"2026-07-05T03:28:31.579138+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.01662v1","created_at":"2026-07-05T03:28:31.579138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.01662","created_at":"2026-07-05T03:28:31.579138+00:00"},{"alias_kind":"pith_short_12","alias_value":"FBBTAO2UVXT2","created_at":"2026-07-05T03:28:31.579138+00:00"},{"alias_kind":"pith_short_16","alias_value":"FBBTAO2UVXT2JPX4","created_at":"2026-07-05T03:28:31.579138+00:00"},{"alias_kind":"pith_short_8","alias_value":"FBBTAO2U","created_at":"2026-07-05T03:28:31.579138+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/FBBTAO2UVXT2JPX4H4YGOKWUB7","json":"https://pith.science/pith/FBBTAO2UVXT2JPX4H4YGOKWUB7.json","graph_json":"https://pith.science/api/pith-number/FBBTAO2UVXT2JPX4H4YGOKWUB7/graph.json","events_json":"https://pith.science/api/pith-number/FBBTAO2UVXT2JPX4H4YGOKWUB7/events.json","paper":"https://pith.science/paper/FBBTAO2U"},"agent_actions":{"view_html":"https://pith.science/pith/FBBTAO2UVXT2JPX4H4YGOKWUB7","download_json":"https://pith.science/pith/FBBTAO2UVXT2JPX4H4YGOKWUB7.json","view_paper":"https://pith.science/paper/FBBTAO2U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.01662&json=true","fetch_graph":"https://pith.science/api/pith-number/FBBTAO2UVXT2JPX4H4YGOKWUB7/graph.json","fetch_events":"https://pith.science/api/pith-number/FBBTAO2UVXT2JPX4H4YGOKWUB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FBBTAO2UVXT2JPX4H4YGOKWUB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FBBTAO2UVXT2JPX4H4YGOKWUB7/action/storage_attestation","attest_author":"https://pith.science/pith/FBBTAO2UVXT2JPX4H4YGOKWUB7/action/author_attestation","sign_citation":"https://pith.science/pith/FBBTAO2UVXT2JPX4H4YGOKWUB7/action/citation_signature","submit_replication":"https://pith.science/pith/FBBTAO2UVXT2JPX4H4YGOKWUB7/action/replication_record"}},"created_at":"2026-07-05T03:28:31.579138+00:00","updated_at":"2026-07-05T03:28:31.579138+00:00"}