{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UFXD7LH3RHLX5ZGQESX3LICRW2","short_pith_number":"pith:UFXD7LH3","schema_version":"1.0","canonical_sha256":"a16e3facfb89d77ee4d024afb5a051b6b6924bdb29fcd08ec581f3b7e5064fdb","source":{"kind":"arxiv","id":"2203.03990","version":4},"attestation_state":"computed","paper":{"title":"Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zheng, Jingfei Xia, Mingchen Zhuge, Shun Fan, TianTian Geng, Yuantai Wei, Zhenyu He","submitted_at":"2022-03-08T10:36:55Z","abstract_excerpt":"Figure skating scoring is challenging because it requires judging the technical moves of the players as well as their coordination with the background music. Most learning-based methods cannot solve it well for two reasons: 1) each move in figure skating changes quickly, hence simply applying traditional frame sampling will lose a lot of valuable information, especially in 3 to 5 minutes long videos; 2) prior methods rarely considered the critical audio-visual relationship in their models. Due to these reasons, we introduce a novel architecture, named Skating-Mixer. It extends the MLP framewor"},"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":"2203.03990","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-08T10:36:55Z","cross_cats_sorted":[],"title_canon_sha256":"6033fce59e7353e22ac4444b8c14852bbe76c4d12ad1b4e521cc1352efa03e9d","abstract_canon_sha256":"e782adbd3272e2f0cb09c9467e86994392cf53c92de51b9b3531d5feede89f58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:04.435041Z","signature_b64":"V5Wt/uJUscSmbDaXRinOdQrQARP0uJpoPH7Gloxvy6GQnKvcylHcT8YFCnUMYC1DuVjipON8omM1LhyiwrzcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a16e3facfb89d77ee4d024afb5a051b6b6924bdb29fcd08ec581f3b7e5064fdb","last_reissued_at":"2026-07-05T05:26:04.434605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:04.434605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zheng, Jingfei Xia, Mingchen Zhuge, Shun Fan, TianTian Geng, Yuantai Wei, Zhenyu He","submitted_at":"2022-03-08T10:36:55Z","abstract_excerpt":"Figure skating scoring is challenging because it requires judging the technical moves of the players as well as their coordination with the background music. Most learning-based methods cannot solve it well for two reasons: 1) each move in figure skating changes quickly, hence simply applying traditional frame sampling will lose a lot of valuable information, especially in 3 to 5 minutes long videos; 2) prior methods rarely considered the critical audio-visual relationship in their models. Due to these reasons, we introduce a novel architecture, named Skating-Mixer. It extends the MLP framewor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.03990","kind":"arxiv","version":4},"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/2203.03990/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":"2203.03990","created_at":"2026-07-05T05:26:04.434662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.03990v4","created_at":"2026-07-05T05:26:04.434662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.03990","created_at":"2026-07-05T05:26:04.434662+00:00"},{"alias_kind":"pith_short_12","alias_value":"UFXD7LH3RHLX","created_at":"2026-07-05T05:26:04.434662+00:00"},{"alias_kind":"pith_short_16","alias_value":"UFXD7LH3RHLX5ZGQ","created_at":"2026-07-05T05:26:04.434662+00:00"},{"alias_kind":"pith_short_8","alias_value":"UFXD7LH3","created_at":"2026-07-05T05:26:04.434662+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10281","citing_title":"VIFSS: View-Invariant and Figure Skating-Specific Pose Representation Learning for Temporal Action Segmentation","ref_index":77,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UFXD7LH3RHLX5ZGQESX3LICRW2","json":"https://pith.science/pith/UFXD7LH3RHLX5ZGQESX3LICRW2.json","graph_json":"https://pith.science/api/pith-number/UFXD7LH3RHLX5ZGQESX3LICRW2/graph.json","events_json":"https://pith.science/api/pith-number/UFXD7LH3RHLX5ZGQESX3LICRW2/events.json","paper":"https://pith.science/paper/UFXD7LH3"},"agent_actions":{"view_html":"https://pith.science/pith/UFXD7LH3RHLX5ZGQESX3LICRW2","download_json":"https://pith.science/pith/UFXD7LH3RHLX5ZGQESX3LICRW2.json","view_paper":"https://pith.science/paper/UFXD7LH3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.03990&json=true","fetch_graph":"https://pith.science/api/pith-number/UFXD7LH3RHLX5ZGQESX3LICRW2/graph.json","fetch_events":"https://pith.science/api/pith-number/UFXD7LH3RHLX5ZGQESX3LICRW2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UFXD7LH3RHLX5ZGQESX3LICRW2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UFXD7LH3RHLX5ZGQESX3LICRW2/action/storage_attestation","attest_author":"https://pith.science/pith/UFXD7LH3RHLX5ZGQESX3LICRW2/action/author_attestation","sign_citation":"https://pith.science/pith/UFXD7LH3RHLX5ZGQESX3LICRW2/action/citation_signature","submit_replication":"https://pith.science/pith/UFXD7LH3RHLX5ZGQESX3LICRW2/action/replication_record"}},"created_at":"2026-07-05T05:26:04.434662+00:00","updated_at":"2026-07-05T05:26:04.434662+00:00"}