{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ADU3X7QPOK623LAUBMVGNYOO6Z","short_pith_number":"pith:ADU3X7QP","schema_version":"1.0","canonical_sha256":"00e9bbfe0f72bdadac140b2a66e1cef65bf3c2dfd072e0af14a01ce74ac1dd28","source":{"kind":"arxiv","id":"2607.19437","version":1},"attestation_state":"computed","paper":{"title":"Group-of-Latents: Perceptual Video Compression at Extreme Bitrates via Masked Latent Generative Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM"],"primary_cat":"eess.IV","authors_text":"Fei Zhao, Huizhu Jia, Jian Tang, Jinchang Xu, Peidong Jia, Rui Ma, Shanghang Zhang, Shaokang Wang, Siyuan Qian, Xiaodong Xie, Xiaozhu Ju, Zhijian Hao","submitted_at":"2026-07-21T06:36:32Z","abstract_excerpt":"Most existing video compression algorithms follow a paradigm of transformation and quantization, optimizing the trade-off between distortion and bitrate. However, extremely low-bitrate compression remains an underexplored frontier where perceptual quality optimization under severely constrained coding resources has not been adequately addressed. In this paper, we propose a unified generative framework that leverages pre-trained Diffusion Transformer (DiT) priors to achieve high perceptual quality at extremely low bitrates. We first introduce a flexible Group-of-Latents (GoL) strategy within th"},"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":"2607.19437","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2026-07-21T06:36:32Z","cross_cats_sorted":["cs.CV","cs.MM"],"title_canon_sha256":"2c044f5fa3c333783b3432b75d94c6db56077cfe6838c3c4d7a077a1a2622329","abstract_canon_sha256":"a23f47ab1d6422646b5c1b134cee9e3df63c8bb8dad3d58c36d2a237086c4120"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T00:23:49.874271Z","signature_b64":"TSLy4QozH1RW6ZPliLZHMAV+wD6iEFQyZDQDPqbUULd921JVh2TnHyMlTiMs+Qg6TPPojuP4zLZBaPPKCCZiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00e9bbfe0f72bdadac140b2a66e1cef65bf3c2dfd072e0af14a01ce74ac1dd28","last_reissued_at":"2026-07-23T00:23:49.873433Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T00:23:49.873433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Group-of-Latents: Perceptual Video Compression at Extreme Bitrates via Masked Latent Generative Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM"],"primary_cat":"eess.IV","authors_text":"Fei Zhao, Huizhu Jia, Jian Tang, Jinchang Xu, Peidong Jia, Rui Ma, Shanghang Zhang, Shaokang Wang, Siyuan Qian, Xiaodong Xie, Xiaozhu Ju, Zhijian Hao","submitted_at":"2026-07-21T06:36:32Z","abstract_excerpt":"Most existing video compression algorithms follow a paradigm of transformation and quantization, optimizing the trade-off between distortion and bitrate. However, extremely low-bitrate compression remains an underexplored frontier where perceptual quality optimization under severely constrained coding resources has not been adequately addressed. In this paper, we propose a unified generative framework that leverages pre-trained Diffusion Transformer (DiT) priors to achieve high perceptual quality at extremely low bitrates. We first introduce a flexible Group-of-Latents (GoL) strategy within th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19437","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/2607.19437/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":"2607.19437","created_at":"2026-07-23T00:23:49.873874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.19437v1","created_at":"2026-07-23T00:23:49.873874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19437","created_at":"2026-07-23T00:23:49.873874+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADU3X7QPOK62","created_at":"2026-07-23T00:23:49.873874+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADU3X7QPOK623LAU","created_at":"2026-07-23T00:23:49.873874+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADU3X7QP","created_at":"2026-07-23T00:23:49.873874+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/ADU3X7QPOK623LAUBMVGNYOO6Z","json":"https://pith.science/pith/ADU3X7QPOK623LAUBMVGNYOO6Z.json","graph_json":"https://pith.science/api/pith-number/ADU3X7QPOK623LAUBMVGNYOO6Z/graph.json","events_json":"https://pith.science/api/pith-number/ADU3X7QPOK623LAUBMVGNYOO6Z/events.json","paper":"https://pith.science/paper/ADU3X7QP"},"agent_actions":{"view_html":"https://pith.science/pith/ADU3X7QPOK623LAUBMVGNYOO6Z","download_json":"https://pith.science/pith/ADU3X7QPOK623LAUBMVGNYOO6Z.json","view_paper":"https://pith.science/paper/ADU3X7QP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.19437&json=true","fetch_graph":"https://pith.science/api/pith-number/ADU3X7QPOK623LAUBMVGNYOO6Z/graph.json","fetch_events":"https://pith.science/api/pith-number/ADU3X7QPOK623LAUBMVGNYOO6Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADU3X7QPOK623LAUBMVGNYOO6Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADU3X7QPOK623LAUBMVGNYOO6Z/action/storage_attestation","attest_author":"https://pith.science/pith/ADU3X7QPOK623LAUBMVGNYOO6Z/action/author_attestation","sign_citation":"https://pith.science/pith/ADU3X7QPOK623LAUBMVGNYOO6Z/action/citation_signature","submit_replication":"https://pith.science/pith/ADU3X7QPOK623LAUBMVGNYOO6Z/action/replication_record"}},"created_at":"2026-07-23T00:23:49.873874+00:00","updated_at":"2026-07-23T00:23:49.873874+00:00"}