{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6MUVKKY2XJKESC4TITDEPU6PTO","short_pith_number":"pith:6MUVKKY2","schema_version":"1.0","canonical_sha256":"f329552b1aba54490b9344c647d3cf9ba4ad9753dff8ce0fab65e1b400c7031f","source":{"kind":"arxiv","id":"2504.16082","version":1},"attestation_state":"computed","paper":{"title":"MR. Video: \"MapReduce\" is the Principle for Long Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yu-Xiong Wang, Ziqi Pang","submitted_at":"2025-04-22T17:59:41Z","abstract_excerpt":"We propose MR. Video, an agentic long video understanding framework that demonstrates the simple yet effective MapReduce principle for processing long videos: (1) Map: independently and densely perceiving short video clips, and (2) Reduce: jointly aggregating information from all clips. Compared with sequence-to-sequence vision-language models (VLMs), MR. Video performs detailed short video perception without being limited by context length. Compared with existing video agents that typically rely on sequential key segment selection, the Map operation enables simpler and more scalable sequence "},"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":"2504.16082","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T17:59:41Z","cross_cats_sorted":[],"title_canon_sha256":"7919336318e866f9cbb22a49f45d178e169d584060ded63fb422bf21961e4731","abstract_canon_sha256":"a5c7a74923e4056d180d9331dd9fae48e58d060bb763000bde07a3ac0de79e0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:35.225821Z","signature_b64":"amGFHyNSwXPExZF5rPqeOZWNmIhQhaDtrolrBs+4X9+FddIy/zbdRu6v3C6zLkA3+5j4G2rLyzlhwZ8IgJQgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f329552b1aba54490b9344c647d3cf9ba4ad9753dff8ce0fab65e1b400c7031f","last_reissued_at":"2026-07-05T10:52:35.225376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:35.225376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MR. Video: \"MapReduce\" is the Principle for Long Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yu-Xiong Wang, Ziqi Pang","submitted_at":"2025-04-22T17:59:41Z","abstract_excerpt":"We propose MR. Video, an agentic long video understanding framework that demonstrates the simple yet effective MapReduce principle for processing long videos: (1) Map: independently and densely perceiving short video clips, and (2) Reduce: jointly aggregating information from all clips. Compared with sequence-to-sequence vision-language models (VLMs), MR. Video performs detailed short video perception without being limited by context length. Compared with existing video agents that typically rely on sequential key segment selection, the Map operation enables simpler and more scalable sequence "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16082","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/2504.16082/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":"2504.16082","created_at":"2026-07-05T10:52:35.225435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16082v1","created_at":"2026-07-05T10:52:35.225435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16082","created_at":"2026-07-05T10:52:35.225435+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MUVKKY2XJKE","created_at":"2026-07-05T10:52:35.225435+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MUVKKY2XJKESC4T","created_at":"2026-07-05T10:52:35.225435+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MUVKKY2","created_at":"2026-07-05T10:52:35.225435+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06532","citing_title":"GOPAgen: Motion-Aware and Efficient Agentic Long-Video Understanding with Structural Memory and Hierarchical Reasoning","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2406.08035","citing_title":"LVBench: An Extreme Long Video Understanding Benchmark","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00444","citing_title":"Scaling Video Understanding via Compact Latent Multi-Agent Collaboration","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04372","citing_title":"Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6MUVKKY2XJKESC4TITDEPU6PTO","json":"https://pith.science/pith/6MUVKKY2XJKESC4TITDEPU6PTO.json","graph_json":"https://pith.science/api/pith-number/6MUVKKY2XJKESC4TITDEPU6PTO/graph.json","events_json":"https://pith.science/api/pith-number/6MUVKKY2XJKESC4TITDEPU6PTO/events.json","paper":"https://pith.science/paper/6MUVKKY2"},"agent_actions":{"view_html":"https://pith.science/pith/6MUVKKY2XJKESC4TITDEPU6PTO","download_json":"https://pith.science/pith/6MUVKKY2XJKESC4TITDEPU6PTO.json","view_paper":"https://pith.science/paper/6MUVKKY2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16082&json=true","fetch_graph":"https://pith.science/api/pith-number/6MUVKKY2XJKESC4TITDEPU6PTO/graph.json","fetch_events":"https://pith.science/api/pith-number/6MUVKKY2XJKESC4TITDEPU6PTO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MUVKKY2XJKESC4TITDEPU6PTO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MUVKKY2XJKESC4TITDEPU6PTO/action/storage_attestation","attest_author":"https://pith.science/pith/6MUVKKY2XJKESC4TITDEPU6PTO/action/author_attestation","sign_citation":"https://pith.science/pith/6MUVKKY2XJKESC4TITDEPU6PTO/action/citation_signature","submit_replication":"https://pith.science/pith/6MUVKKY2XJKESC4TITDEPU6PTO/action/replication_record"}},"created_at":"2026-07-05T10:52:35.225435+00:00","updated_at":"2026-07-05T10:52:35.225435+00:00"}