{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6R2WLQZYN3IQJ4DRUYKRKC3VBP","short_pith_number":"pith:6R2WLQZY","schema_version":"1.0","canonical_sha256":"f47565c3386ed104f071a615150b750bdb7699f9c6b30fbde96b6896802a40a8","source":{"kind":"arxiv","id":"2312.05856","version":3},"attestation_state":"computed","paper":{"title":"A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Xu, Dongxu Yue, Maomao Li, Tianyu Yang, Yu Li, Yunfei Liu, Zhihui Lin","submitted_at":"2023-12-10T11:20:18Z","abstract_excerpt":"This paper presents a video inversion approach for zero-shot video editing, which models the input video with low-rank representation during the inversion process. The existing video editing methods usually apply the typical 2D DDIM inversion or naive spatial-temporal DDIM inversion before editing, which leverages time-varying representation for each frame to derive noisy latent. Unlike most existing approaches, we propose a Spatial-Temporal Expectation-Maximization (STEM) inversion, which formulates the dense video feature under an expectation-maximization manner and iteratively estimates a m"},"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":"2312.05856","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-10T11:20:18Z","cross_cats_sorted":[],"title_canon_sha256":"1c6a89c627eca6e77775742a1d33760292cfb885e21737c8ebb1d0a6dd7109a2","abstract_canon_sha256":"a6ba6f52719e6281565ccf71d7db7c282a7e5a3c07f3751cad119fd777d115da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:33.685166Z","signature_b64":"HZgtMxzY464G7QKr14C7pb2mjQp/edXPY9RP0BdPxRP9Hrk36EPwcvTBV8RFLnU2Q9NMJprRLBhkCxh6VsjVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f47565c3386ed104f071a615150b750bdb7699f9c6b30fbde96b6896802a40a8","last_reissued_at":"2026-07-05T08:33:33.684618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:33.684618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Xu, Dongxu Yue, Maomao Li, Tianyu Yang, Yu Li, Yunfei Liu, Zhihui Lin","submitted_at":"2023-12-10T11:20:18Z","abstract_excerpt":"This paper presents a video inversion approach for zero-shot video editing, which models the input video with low-rank representation during the inversion process. The existing video editing methods usually apply the typical 2D DDIM inversion or naive spatial-temporal DDIM inversion before editing, which leverages time-varying representation for each frame to derive noisy latent. Unlike most existing approaches, we propose a Spatial-Temporal Expectation-Maximization (STEM) inversion, which formulates the dense video feature under an expectation-maximization manner and iteratively estimates a m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05856","kind":"arxiv","version":3},"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/2312.05856/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":"2312.05856","created_at":"2026-07-05T08:33:33.684697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.05856v3","created_at":"2026-07-05T08:33:33.684697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05856","created_at":"2026-07-05T08:33:33.684697+00:00"},{"alias_kind":"pith_short_12","alias_value":"6R2WLQZYN3IQ","created_at":"2026-07-05T08:33:33.684697+00:00"},{"alias_kind":"pith_short_16","alias_value":"6R2WLQZYN3IQJ4DR","created_at":"2026-07-05T08:33:33.684697+00:00"},{"alias_kind":"pith_short_8","alias_value":"6R2WLQZY","created_at":"2026-07-05T08:33:33.684697+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/6R2WLQZYN3IQJ4DRUYKRKC3VBP","json":"https://pith.science/pith/6R2WLQZYN3IQJ4DRUYKRKC3VBP.json","graph_json":"https://pith.science/api/pith-number/6R2WLQZYN3IQJ4DRUYKRKC3VBP/graph.json","events_json":"https://pith.science/api/pith-number/6R2WLQZYN3IQJ4DRUYKRKC3VBP/events.json","paper":"https://pith.science/paper/6R2WLQZY"},"agent_actions":{"view_html":"https://pith.science/pith/6R2WLQZYN3IQJ4DRUYKRKC3VBP","download_json":"https://pith.science/pith/6R2WLQZYN3IQJ4DRUYKRKC3VBP.json","view_paper":"https://pith.science/paper/6R2WLQZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.05856&json=true","fetch_graph":"https://pith.science/api/pith-number/6R2WLQZYN3IQJ4DRUYKRKC3VBP/graph.json","fetch_events":"https://pith.science/api/pith-number/6R2WLQZYN3IQJ4DRUYKRKC3VBP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6R2WLQZYN3IQJ4DRUYKRKC3VBP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6R2WLQZYN3IQJ4DRUYKRKC3VBP/action/storage_attestation","attest_author":"https://pith.science/pith/6R2WLQZYN3IQJ4DRUYKRKC3VBP/action/author_attestation","sign_citation":"https://pith.science/pith/6R2WLQZYN3IQJ4DRUYKRKC3VBP/action/citation_signature","submit_replication":"https://pith.science/pith/6R2WLQZYN3IQJ4DRUYKRKC3VBP/action/replication_record"}},"created_at":"2026-07-05T08:33:33.684697+00:00","updated_at":"2026-07-05T08:33:33.684697+00:00"}