{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OUNREVCFOCUESLQCIZUOFHXSTE","short_pith_number":"pith:OUNREVCF","schema_version":"1.0","canonical_sha256":"751b12544570a8492e024668e29ef29903b607804f253a76ed04f5c9cc452d90","source":{"kind":"arxiv","id":"2412.05263","version":2},"attestation_state":"computed","paper":{"title":"Mind the Time: Temporally-Controlled Multi-Event Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Igor Gilitschenski, Ivan Skorokhodov, Sergey Tulyakov, Varnith Chordia, Willi Menapace, Yuwei Fang, Ziyi Wu","submitted_at":"2024-12-06T18:52:20Z","abstract_excerpt":"Real-world videos consist of sequences of events. Generating such sequences with precise temporal control is infeasible with existing video generators that rely on a single paragraph of text as input. When tasked with generating multiple events described using a single prompt, such methods often ignore some of the events or fail to arrange them in the correct order. To address this limitation, we present MinT, a multi-event video generator with temporal control. Our key insight is to bind each event to a specific period in the generated video, which allows the model to focus on one event at a "},"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":"2412.05263","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-06T18:52:20Z","cross_cats_sorted":[],"title_canon_sha256":"9828cb3c9e0c8e420236ece6bcdabe8984e31cf5eb5c895c1bbb5dade6f26243","abstract_canon_sha256":"a3fcfe2f5ea6c8e6a84b4b7963f7e28e8e239017781f904cd3edafe73bd7dc00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:42.129761Z","signature_b64":"1VatLt7xPV2y4y9+bqDg0GR71XITzA+cB6KnGfpLZJpYDfMX46Wep8wxBfuBqQOK6T6IdlaRYy+k0I2Sykg7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"751b12544570a8492e024668e29ef29903b607804f253a76ed04f5c9cc452d90","last_reissued_at":"2026-07-05T10:26:42.129265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:42.129265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mind the Time: Temporally-Controlled Multi-Event Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Igor Gilitschenski, Ivan Skorokhodov, Sergey Tulyakov, Varnith Chordia, Willi Menapace, Yuwei Fang, Ziyi Wu","submitted_at":"2024-12-06T18:52:20Z","abstract_excerpt":"Real-world videos consist of sequences of events. Generating such sequences with precise temporal control is infeasible with existing video generators that rely on a single paragraph of text as input. When tasked with generating multiple events described using a single prompt, such methods often ignore some of the events or fail to arrange them in the correct order. To address this limitation, we present MinT, a multi-event video generator with temporal control. Our key insight is to bind each event to a specific period in the generated video, which allows the model to focus on one event at a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05263","kind":"arxiv","version":2},"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/2412.05263/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":"2412.05263","created_at":"2026-07-05T10:26:42.129341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05263v2","created_at":"2026-07-05T10:26:42.129341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05263","created_at":"2026-07-05T10:26:42.129341+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUNREVCFOCUE","created_at":"2026-07-05T10:26:42.129341+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUNREVCFOCUESLQC","created_at":"2026-07-05T10:26:42.129341+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUNREVCF","created_at":"2026-07-05T10:26:42.129341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":90,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OUNREVCFOCUESLQCIZUOFHXSTE","json":"https://pith.science/pith/OUNREVCFOCUESLQCIZUOFHXSTE.json","graph_json":"https://pith.science/api/pith-number/OUNREVCFOCUESLQCIZUOFHXSTE/graph.json","events_json":"https://pith.science/api/pith-number/OUNREVCFOCUESLQCIZUOFHXSTE/events.json","paper":"https://pith.science/paper/OUNREVCF"},"agent_actions":{"view_html":"https://pith.science/pith/OUNREVCFOCUESLQCIZUOFHXSTE","download_json":"https://pith.science/pith/OUNREVCFOCUESLQCIZUOFHXSTE.json","view_paper":"https://pith.science/paper/OUNREVCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05263&json=true","fetch_graph":"https://pith.science/api/pith-number/OUNREVCFOCUESLQCIZUOFHXSTE/graph.json","fetch_events":"https://pith.science/api/pith-number/OUNREVCFOCUESLQCIZUOFHXSTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUNREVCFOCUESLQCIZUOFHXSTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUNREVCFOCUESLQCIZUOFHXSTE/action/storage_attestation","attest_author":"https://pith.science/pith/OUNREVCFOCUESLQCIZUOFHXSTE/action/author_attestation","sign_citation":"https://pith.science/pith/OUNREVCFOCUESLQCIZUOFHXSTE/action/citation_signature","submit_replication":"https://pith.science/pith/OUNREVCFOCUESLQCIZUOFHXSTE/action/replication_record"}},"created_at":"2026-07-05T10:26:42.129341+00:00","updated_at":"2026-07-05T10:26:42.129341+00:00"}