{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GVFYMUA5GWG7QLE3H55L7DDSAG","short_pith_number":"pith:GVFYMUA5","schema_version":"1.0","canonical_sha256":"354b86501d358df82c9b3f7abf8c720191498fc4c104c7bfa1eb2c27e261335d","source":{"kind":"arxiv","id":"2212.04655","version":3},"attestation_state":"computed","paper":{"title":"MIMO Is All You Need : A Strong Multi-In-Multi-Out Baseline for Video Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaofeng Chen, Mengcheng Lan, Qian Chen, Shuguang Cui, Shuliang Ning, Xiaoguang Han, Xunlai Chen, Yanran Li","submitted_at":"2022-12-09T03:57:13Z","abstract_excerpt":"The mainstream of the existing approaches for video prediction builds up their models based on a Single-In-Single-Out (SISO) architecture, which takes the current frame as input to predict the next frame in a recursive manner. This way often leads to severe performance degradation when they try to extrapolate a longer period of future, thus limiting the practical use of the prediction model. Alternatively, a Multi-In-Multi-Out (MIMO) architecture that outputs all the future frames at one shot naturally breaks the recursive manner and therefore prevents error accumulation. However, only a few 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":"2212.04655","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-09T03:57:13Z","cross_cats_sorted":[],"title_canon_sha256":"d48926952f1954f3d2d772766cd08a4282c369bca1c554284911502892ad740e","abstract_canon_sha256":"03c8f4a0a041ff3de37c957927a11313d6a1c6d0761c96678a22465570276951"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:56.847735Z","signature_b64":"Z8XBm2hWrJ79QDTfLQ2uXAvF9IWNP3lE0kGtu2/AvNBKb6Kt1cXP9Dh44e2Qks+hoFtthmjbXiPaETCn+P+zBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"354b86501d358df82c9b3f7abf8c720191498fc4c104c7bfa1eb2c27e261335d","last_reissued_at":"2026-07-05T06:14:56.847270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:56.847270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIMO Is All You Need : A Strong Multi-In-Multi-Out Baseline for Video Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaofeng Chen, Mengcheng Lan, Qian Chen, Shuguang Cui, Shuliang Ning, Xiaoguang Han, Xunlai Chen, Yanran Li","submitted_at":"2022-12-09T03:57:13Z","abstract_excerpt":"The mainstream of the existing approaches for video prediction builds up their models based on a Single-In-Single-Out (SISO) architecture, which takes the current frame as input to predict the next frame in a recursive manner. This way often leads to severe performance degradation when they try to extrapolate a longer period of future, thus limiting the practical use of the prediction model. Alternatively, a Multi-In-Multi-Out (MIMO) architecture that outputs all the future frames at one shot naturally breaks the recursive manner and therefore prevents error accumulation. However, only a few M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04655","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/2212.04655/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":"2212.04655","created_at":"2026-07-05T06:14:56.847322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.04655v3","created_at":"2026-07-05T06:14:56.847322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04655","created_at":"2026-07-05T06:14:56.847322+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVFYMUA5GWG7","created_at":"2026-07-05T06:14:56.847322+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVFYMUA5GWG7QLE3","created_at":"2026-07-05T06:14:56.847322+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVFYMUA5","created_at":"2026-07-05T06:14:56.847322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13772","citing_title":"An Efficient Occupancy World Model via Decoupled Dynamic Flow and Image-assisted Training","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVFYMUA5GWG7QLE3H55L7DDSAG","json":"https://pith.science/pith/GVFYMUA5GWG7QLE3H55L7DDSAG.json","graph_json":"https://pith.science/api/pith-number/GVFYMUA5GWG7QLE3H55L7DDSAG/graph.json","events_json":"https://pith.science/api/pith-number/GVFYMUA5GWG7QLE3H55L7DDSAG/events.json","paper":"https://pith.science/paper/GVFYMUA5"},"agent_actions":{"view_html":"https://pith.science/pith/GVFYMUA5GWG7QLE3H55L7DDSAG","download_json":"https://pith.science/pith/GVFYMUA5GWG7QLE3H55L7DDSAG.json","view_paper":"https://pith.science/paper/GVFYMUA5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.04655&json=true","fetch_graph":"https://pith.science/api/pith-number/GVFYMUA5GWG7QLE3H55L7DDSAG/graph.json","fetch_events":"https://pith.science/api/pith-number/GVFYMUA5GWG7QLE3H55L7DDSAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVFYMUA5GWG7QLE3H55L7DDSAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVFYMUA5GWG7QLE3H55L7DDSAG/action/storage_attestation","attest_author":"https://pith.science/pith/GVFYMUA5GWG7QLE3H55L7DDSAG/action/author_attestation","sign_citation":"https://pith.science/pith/GVFYMUA5GWG7QLE3H55L7DDSAG/action/citation_signature","submit_replication":"https://pith.science/pith/GVFYMUA5GWG7QLE3H55L7DDSAG/action/replication_record"}},"created_at":"2026-07-05T06:14:56.847322+00:00","updated_at":"2026-07-05T06:14:56.847322+00:00"}