{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2MMWD7RJDKFFYKDWSAP4J5QELB","short_pith_number":"pith:2MMWD7RJ","schema_version":"1.0","canonical_sha256":"d31961fe291a8a5c2876901fc4f604585828f97e30562a08ceedc042fc9604c3","source":{"kind":"arxiv","id":"2605.18748","version":1},"attestation_state":"computed","paper":{"title":"Aurora: Unified Video Editing with a Tool-Using Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Hua, Jiebo Luo, Wei Xiong, Yongsheng Yu, Zhenghong Zhou, Zhiyuan Xiao, Ziyun Zeng","submitted_at":"2026-05-18T17:59:03Z","abstract_excerpt":"Recent video editing models have converged on a unified conditioning design: a single diffusion transformer jointly consumes text, source video, and reference images, and one set of weights covers replacement, removal, style transfer, and reference-driven insertion. The design is flexible, but it assumes that the user already provides model-ready text, reference images, and spatial grounding for local edits, which real requests often omit. We present Aurora, an agentic video editing framework that pairs a tool-augmented vision-language model (VLM) agent with a unified video diffusion transform"},"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":"2605.18748","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T17:59:03Z","cross_cats_sorted":[],"title_canon_sha256":"0c1fc9db7daa2ec7e20c02c67612537b39c2ce75f36f551b9191e5f96579e526","abstract_canon_sha256":"4a5cff9a55a09e8a9087f5a19242eeb2bf88b00f687fdf1472c8a75ca82a7443"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:19.253656Z","signature_b64":"4I75AEGQg30szrRlTteHBjMJFYpoOJ94ZqpgCHMwq/vBL+hyT8CbKzzuRU4hlbFy0bhUAY5zKOdvk+YU8sC5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d31961fe291a8a5c2876901fc4f604585828f97e30562a08ceedc042fc9604c3","last_reissued_at":"2026-05-20T00:06:19.252801Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:19.252801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aurora: Unified Video Editing with a Tool-Using Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Hua, Jiebo Luo, Wei Xiong, Yongsheng Yu, Zhenghong Zhou, Zhiyuan Xiao, Ziyun Zeng","submitted_at":"2026-05-18T17:59:03Z","abstract_excerpt":"Recent video editing models have converged on a unified conditioning design: a single diffusion transformer jointly consumes text, source video, and reference images, and one set of weights covers replacement, removal, style transfer, and reference-driven insertion. The design is flexible, but it assumes that the user already provides model-ready text, reference images, and spatial grounding for local edits, which real requests often omit. We present Aurora, an agentic video editing framework that pairs a tool-augmented vision-language model (VLM) agent with a unified video diffusion transform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18748","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/2605.18748/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:58.984432Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"095cc046e9c3c41c8a9d4f818a05713263f928932e4df8368d12dea2a3fa284e"},"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":"2605.18748","created_at":"2026-05-20T00:06:19.252930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18748v1","created_at":"2026-05-20T00:06:19.252930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18748","created_at":"2026-05-20T00:06:19.252930+00:00"},{"alias_kind":"pith_short_12","alias_value":"2MMWD7RJDKFF","created_at":"2026-05-20T00:06:19.252930+00:00"},{"alias_kind":"pith_short_16","alias_value":"2MMWD7RJDKFFYKDW","created_at":"2026-05-20T00:06:19.252930+00:00"},{"alias_kind":"pith_short_8","alias_value":"2MMWD7RJ","created_at":"2026-05-20T00:06:19.252930+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/2MMWD7RJDKFFYKDWSAP4J5QELB","json":"https://pith.science/pith/2MMWD7RJDKFFYKDWSAP4J5QELB.json","graph_json":"https://pith.science/api/pith-number/2MMWD7RJDKFFYKDWSAP4J5QELB/graph.json","events_json":"https://pith.science/api/pith-number/2MMWD7RJDKFFYKDWSAP4J5QELB/events.json","paper":"https://pith.science/paper/2MMWD7RJ"},"agent_actions":{"view_html":"https://pith.science/pith/2MMWD7RJDKFFYKDWSAP4J5QELB","download_json":"https://pith.science/pith/2MMWD7RJDKFFYKDWSAP4J5QELB.json","view_paper":"https://pith.science/paper/2MMWD7RJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18748&json=true","fetch_graph":"https://pith.science/api/pith-number/2MMWD7RJDKFFYKDWSAP4J5QELB/graph.json","fetch_events":"https://pith.science/api/pith-number/2MMWD7RJDKFFYKDWSAP4J5QELB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2MMWD7RJDKFFYKDWSAP4J5QELB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2MMWD7RJDKFFYKDWSAP4J5QELB/action/storage_attestation","attest_author":"https://pith.science/pith/2MMWD7RJDKFFYKDWSAP4J5QELB/action/author_attestation","sign_citation":"https://pith.science/pith/2MMWD7RJDKFFYKDWSAP4J5QELB/action/citation_signature","submit_replication":"https://pith.science/pith/2MMWD7RJDKFFYKDWSAP4J5QELB/action/replication_record"}},"created_at":"2026-05-20T00:06:19.252930+00:00","updated_at":"2026-05-20T00:06:19.252930+00:00"}