{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W4ZT7NG3T7IR2OPGTUZYTM56AX","short_pith_number":"pith:W4ZT7NG3","schema_version":"1.0","canonical_sha256":"b7333fb4db9fd11d39e69d3389b3be05c2512f754f9eda686e1454953d0d4dde","source":{"kind":"arxiv","id":"2506.07136","version":1},"attestation_state":"computed","paper":{"title":"Hi-VAE: Efficient Video Autoencoding with Global and Detailed Motion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Gong, Changqing Zou, Chen Wei, Donglin Di, Hao Li, Huaize Liu, Qiyuan Zhang, Wenzhang Sun","submitted_at":"2025-06-08T13:30:11Z","abstract_excerpt":"Recent breakthroughs in video autoencoders (Video AEs) have advanced video generation, but existing methods fail to efficiently model spatio-temporal redundancies in dynamics, resulting in suboptimal compression factors. This shortfall leads to excessive training costs for downstream tasks. To address this, we introduce Hi-VAE, an efficient video autoencoding framework that hierarchically encode coarse-to-fine motion representations of video dynamics and formulate the decoding process as a conditional generation task. Specifically, Hi-VAE decomposes video dynamics into two latent spaces: Globa"},"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":"2506.07136","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-08T13:30:11Z","cross_cats_sorted":[],"title_canon_sha256":"edadb498a8918e74d14023d3d0406dacfdf6d2963fb69315b45a6b68e60a4a1a","abstract_canon_sha256":"bf56d63049306a3344344098fe0352bd1d9b03f001fe13f5b909588a0fb5dbd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:02.214403Z","signature_b64":"WUkinC32WJKa8APhzZp6Ly11GN6DJjSd8pJ9zoTtE9lTWzwOfa9aE4JL3pFxQ+yP2AovlHo6yzh+emayb3RgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7333fb4db9fd11d39e69d3389b3be05c2512f754f9eda686e1454953d0d4dde","last_reissued_at":"2026-07-05T11:18:02.213859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:02.213859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hi-VAE: Efficient Video Autoencoding with Global and Detailed Motion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Gong, Changqing Zou, Chen Wei, Donglin Di, Hao Li, Huaize Liu, Qiyuan Zhang, Wenzhang Sun","submitted_at":"2025-06-08T13:30:11Z","abstract_excerpt":"Recent breakthroughs in video autoencoders (Video AEs) have advanced video generation, but existing methods fail to efficiently model spatio-temporal redundancies in dynamics, resulting in suboptimal compression factors. This shortfall leads to excessive training costs for downstream tasks. To address this, we introduce Hi-VAE, an efficient video autoencoding framework that hierarchically encode coarse-to-fine motion representations of video dynamics and formulate the decoding process as a conditional generation task. Specifically, Hi-VAE decomposes video dynamics into two latent spaces: Globa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07136","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/2506.07136/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":"2506.07136","created_at":"2026-07-05T11:18:02.213919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07136v1","created_at":"2026-07-05T11:18:02.213919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07136","created_at":"2026-07-05T11:18:02.213919+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4ZT7NG3T7IR","created_at":"2026-07-05T11:18:02.213919+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4ZT7NG3T7IR2OPG","created_at":"2026-07-05T11:18:02.213919+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4ZT7NG3","created_at":"2026-07-05T11:18:02.213919+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17590","citing_title":"TivTok: Broadcasting Time-Invariant Tokens for Scalable Video Tokenization","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16479","citing_title":"Latent-Compressed Variational Autoencoder for Video Diffusion Models","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15911","citing_title":"Efficient Video Diffusion Models: Advancements and Challenges","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W4ZT7NG3T7IR2OPGTUZYTM56AX","json":"https://pith.science/pith/W4ZT7NG3T7IR2OPGTUZYTM56AX.json","graph_json":"https://pith.science/api/pith-number/W4ZT7NG3T7IR2OPGTUZYTM56AX/graph.json","events_json":"https://pith.science/api/pith-number/W4ZT7NG3T7IR2OPGTUZYTM56AX/events.json","paper":"https://pith.science/paper/W4ZT7NG3"},"agent_actions":{"view_html":"https://pith.science/pith/W4ZT7NG3T7IR2OPGTUZYTM56AX","download_json":"https://pith.science/pith/W4ZT7NG3T7IR2OPGTUZYTM56AX.json","view_paper":"https://pith.science/paper/W4ZT7NG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07136&json=true","fetch_graph":"https://pith.science/api/pith-number/W4ZT7NG3T7IR2OPGTUZYTM56AX/graph.json","fetch_events":"https://pith.science/api/pith-number/W4ZT7NG3T7IR2OPGTUZYTM56AX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4ZT7NG3T7IR2OPGTUZYTM56AX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4ZT7NG3T7IR2OPGTUZYTM56AX/action/storage_attestation","attest_author":"https://pith.science/pith/W4ZT7NG3T7IR2OPGTUZYTM56AX/action/author_attestation","sign_citation":"https://pith.science/pith/W4ZT7NG3T7IR2OPGTUZYTM56AX/action/citation_signature","submit_replication":"https://pith.science/pith/W4ZT7NG3T7IR2OPGTUZYTM56AX/action/replication_record"}},"created_at":"2026-07-05T11:18:02.213919+00:00","updated_at":"2026-07-05T11:18:02.213919+00:00"}