{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2I3YEXXCNZYICQU55LG5MU6GWP","short_pith_number":"pith:2I3YEXXC","schema_version":"1.0","canonical_sha256":"d237825ee26e7081429deacdd653c6b3eeab88baeec5bec5ebd40b8cf091c950","source":{"kind":"arxiv","id":"2004.04730","version":1},"attestation_state":"computed","paper":{"title":"X3D: Expanding Architectures for Efficient Video Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christoph Feichtenhofer","submitted_at":"2020-04-09T17:59:47Z","abstract_excerpt":"This paper presents X3D, a family of efficient video networks that progressively expand a tiny 2D image classification architecture along multiple network axes, in space, time, width and depth. Inspired by feature selection methods in machine learning, a simple stepwise network expansion approach is employed that expands a single axis in each step, such that good accuracy to complexity trade-off is achieved. To expand X3D to a specific target complexity, we perform progressive forward expansion followed by backward contraction. X3D achieves state-of-the-art performance while requiring 4.8x and"},"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":"2004.04730","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-09T17:59:47Z","cross_cats_sorted":[],"title_canon_sha256":"26cc9da6bdf09c73ef6a8ab2e21e85820ecb33c2e250551805a0ebe577b97487","abstract_canon_sha256":"cb3e984797dccda76b5aadb08b659f399462bd481711b3429d349012ed3aa952"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:10.733911Z","signature_b64":"Hrk0ql/nhgMRAG+2JRm4I/LhYfT+S5Mad1YSHxEkAdeUAlaAiO2/Wu9rvyYOWMT/8c7Apbe8mnhP9wcDytvQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d237825ee26e7081429deacdd653c6b3eeab88baeec5bec5ebd40b8cf091c950","last_reissued_at":"2026-07-05T00:54:10.733464Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:10.733464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"X3D: Expanding Architectures for Efficient Video Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christoph Feichtenhofer","submitted_at":"2020-04-09T17:59:47Z","abstract_excerpt":"This paper presents X3D, a family of efficient video networks that progressively expand a tiny 2D image classification architecture along multiple network axes, in space, time, width and depth. Inspired by feature selection methods in machine learning, a simple stepwise network expansion approach is employed that expands a single axis in each step, such that good accuracy to complexity trade-off is achieved. To expand X3D to a specific target complexity, we perform progressive forward expansion followed by backward contraction. X3D achieves state-of-the-art performance while requiring 4.8x and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.04730","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/2004.04730/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":"2004.04730","created_at":"2026-07-05T00:54:10.733521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.04730v1","created_at":"2026-07-05T00:54:10.733521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.04730","created_at":"2026-07-05T00:54:10.733521+00:00"},{"alias_kind":"pith_short_12","alias_value":"2I3YEXXCNZYI","created_at":"2026-07-05T00:54:10.733521+00:00"},{"alias_kind":"pith_short_16","alias_value":"2I3YEXXCNZYICQU5","created_at":"2026-07-05T00:54:10.733521+00:00"},{"alias_kind":"pith_short_8","alias_value":"2I3YEXXC","created_at":"2026-07-05T00:54:10.733521+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22200","citing_title":"OSS: Open Suturing Skills Vision-Based Assessment Challenge 2024-2025","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17133","citing_title":"CAM-VFD: Cross-Attention Multimodal Video Forgery Detection","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2I3YEXXCNZYICQU55LG5MU6GWP","json":"https://pith.science/pith/2I3YEXXCNZYICQU55LG5MU6GWP.json","graph_json":"https://pith.science/api/pith-number/2I3YEXXCNZYICQU55LG5MU6GWP/graph.json","events_json":"https://pith.science/api/pith-number/2I3YEXXCNZYICQU55LG5MU6GWP/events.json","paper":"https://pith.science/paper/2I3YEXXC"},"agent_actions":{"view_html":"https://pith.science/pith/2I3YEXXCNZYICQU55LG5MU6GWP","download_json":"https://pith.science/pith/2I3YEXXCNZYICQU55LG5MU6GWP.json","view_paper":"https://pith.science/paper/2I3YEXXC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.04730&json=true","fetch_graph":"https://pith.science/api/pith-number/2I3YEXXCNZYICQU55LG5MU6GWP/graph.json","fetch_events":"https://pith.science/api/pith-number/2I3YEXXCNZYICQU55LG5MU6GWP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2I3YEXXCNZYICQU55LG5MU6GWP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2I3YEXXCNZYICQU55LG5MU6GWP/action/storage_attestation","attest_author":"https://pith.science/pith/2I3YEXXCNZYICQU55LG5MU6GWP/action/author_attestation","sign_citation":"https://pith.science/pith/2I3YEXXCNZYICQU55LG5MU6GWP/action/citation_signature","submit_replication":"https://pith.science/pith/2I3YEXXCNZYICQU55LG5MU6GWP/action/replication_record"}},"created_at":"2026-07-05T00:54:10.733521+00:00","updated_at":"2026-07-05T00:54:10.733521+00:00"}