{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LLOMJ5UBXS66G4HSOETXFSH2S7","short_pith_number":"pith:LLOMJ5UB","schema_version":"1.0","canonical_sha256":"5adcc4f681bcbde370f2712772c8fa97ed46fbcf21d20e72b63a891a6efbb385","source":{"kind":"arxiv","id":"2411.13683","version":1},"attestation_state":"computed","paper":{"title":"Extending Video Masked Autoencoders to 128 frames","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boqing Gong, Chaitra Hegde, Eirikur Agustsson, Leonid Sigal, Luke Friedman, Mikhail Sirotenko, Ming-Hsuan Yang, Nitesh Bharadwaj Gundavarapu, Raghav Goyal, Sagar M. Waghmare, Tobias Weyand","submitted_at":"2024-11-20T20:00:38Z","abstract_excerpt":"Video understanding has witnessed significant progress with recent video foundation models demonstrating strong performance owing to self-supervised pre-training objectives; Masked Autoencoders (MAE) being the design of choice. Nevertheless, the majority of prior works that leverage MAE pre-training have focused on relatively short video representations (16 / 32 frames in length) largely due to hardware memory and compute limitations that scale poorly with video length due to the dense memory-intensive self-attention decoding. One natural strategy to address these challenges is to subsample to"},"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":"2411.13683","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-20T20:00:38Z","cross_cats_sorted":[],"title_canon_sha256":"2145ae222e20b2eb52ea6fc9cdf27f77dee5931e02af9e203339d15eb7f965e1","abstract_canon_sha256":"907dc9397c30b88271bf2efaaf581b0b0739e08bf93d189727d4e19590b4cbb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:35.474103Z","signature_b64":"Uo1FPPcIbATJjZ2wTHgKwjDa8NrIDHe+8qKSjDZONw8iKk6sV4doWiHBiXyJXQ1bdBBJW78/xNhRyn2sodf+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5adcc4f681bcbde370f2712772c8fa97ed46fbcf21d20e72b63a891a6efbb385","last_reissued_at":"2026-07-05T09:38:35.473634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:35.473634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extending Video Masked Autoencoders to 128 frames","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Boqing Gong, Chaitra Hegde, Eirikur Agustsson, Leonid Sigal, Luke Friedman, Mikhail Sirotenko, Ming-Hsuan Yang, Nitesh Bharadwaj Gundavarapu, Raghav Goyal, Sagar M. Waghmare, Tobias Weyand","submitted_at":"2024-11-20T20:00:38Z","abstract_excerpt":"Video understanding has witnessed significant progress with recent video foundation models demonstrating strong performance owing to self-supervised pre-training objectives; Masked Autoencoders (MAE) being the design of choice. Nevertheless, the majority of prior works that leverage MAE pre-training have focused on relatively short video representations (16 / 32 frames in length) largely due to hardware memory and compute limitations that scale poorly with video length due to the dense memory-intensive self-attention decoding. One natural strategy to address these challenges is to subsample to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13683","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/2411.13683/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":"2411.13683","created_at":"2026-07-05T09:38:35.473691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13683v1","created_at":"2026-07-05T09:38:35.473691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13683","created_at":"2026-07-05T09:38:35.473691+00:00"},{"alias_kind":"pith_short_12","alias_value":"LLOMJ5UBXS66","created_at":"2026-07-05T09:38:35.473691+00:00"},{"alias_kind":"pith_short_16","alias_value":"LLOMJ5UBXS66G4HS","created_at":"2026-07-05T09:38:35.473691+00:00"},{"alias_kind":"pith_short_8","alias_value":"LLOMJ5UB","created_at":"2026-07-05T09:38:35.473691+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/LLOMJ5UBXS66G4HSOETXFSH2S7","json":"https://pith.science/pith/LLOMJ5UBXS66G4HSOETXFSH2S7.json","graph_json":"https://pith.science/api/pith-number/LLOMJ5UBXS66G4HSOETXFSH2S7/graph.json","events_json":"https://pith.science/api/pith-number/LLOMJ5UBXS66G4HSOETXFSH2S7/events.json","paper":"https://pith.science/paper/LLOMJ5UB"},"agent_actions":{"view_html":"https://pith.science/pith/LLOMJ5UBXS66G4HSOETXFSH2S7","download_json":"https://pith.science/pith/LLOMJ5UBXS66G4HSOETXFSH2S7.json","view_paper":"https://pith.science/paper/LLOMJ5UB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13683&json=true","fetch_graph":"https://pith.science/api/pith-number/LLOMJ5UBXS66G4HSOETXFSH2S7/graph.json","fetch_events":"https://pith.science/api/pith-number/LLOMJ5UBXS66G4HSOETXFSH2S7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LLOMJ5UBXS66G4HSOETXFSH2S7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LLOMJ5UBXS66G4HSOETXFSH2S7/action/storage_attestation","attest_author":"https://pith.science/pith/LLOMJ5UBXS66G4HSOETXFSH2S7/action/author_attestation","sign_citation":"https://pith.science/pith/LLOMJ5UBXS66G4HSOETXFSH2S7/action/citation_signature","submit_replication":"https://pith.science/pith/LLOMJ5UBXS66G4HSOETXFSH2S7/action/replication_record"}},"created_at":"2026-07-05T09:38:35.473691+00:00","updated_at":"2026-07-05T09:38:35.473691+00:00"}