{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CNDML4GYYGSKVLB42QWKOLA2MB","short_pith_number":"pith:CNDML4GY","schema_version":"1.0","canonical_sha256":"1346c5f0d8c1a4aaac3cd42ca72c1a607d8ebd0462af02f44db96cfe7871f34b","source":{"kind":"arxiv","id":"2507.00950","version":1},"attestation_state":"computed","paper":{"title":"MVP: Winning Solution to SMP Challenge 2025 Video Track","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"(2) La Trobe University, Australia), China, Junqing Yu (1), Liliang Ye (1), Melbourne, Technology, Wei Yang (1), Wuhan, Yafeng Wu (1), Yi-Ping Phoebe Chen (2), Yunyao Zhang (1), Zikai Song (1) ((1) Huazhong University of Science","submitted_at":"2025-07-01T16:52:20Z","abstract_excerpt":"Social media platforms serve as central hubs for content dissemination, opinion expression, and public engagement across diverse modalities. Accurately predicting the popularity of social media videos enables valuable applications in content recommendation, trend detection, and audience engagement. In this paper, we present Multimodal Video Predictor (MVP), our winning solution to the Video Track of the SMP Challenge 2025. MVP constructs expressive post representations by integrating deep video features extracted from pretrained models with user metadata and contextual information. The framewo"},"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":"2507.00950","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T16:52:20Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"89d627155d38beda7414c05a1c87fd6bbe576076669c1885e7daadfce436c92c","abstract_canon_sha256":"26c02caec4aa371f9d04660a796f9cb8e7699c02d56418d0e1ffb2d7ac3c62b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:18.411561Z","signature_b64":"XdaWY77RAxPTSTuSIfgSURrG8Ewos802MxjMTGvAU32KYR8e8xenQM+Vob9AO3100Wq1mUMOvDYeJE1QQBumCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1346c5f0d8c1a4aaac3cd42ca72c1a607d8ebd0462af02f44db96cfe7871f34b","last_reissued_at":"2026-07-05T11:30:18.411009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:18.411009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVP: Winning Solution to SMP Challenge 2025 Video Track","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"(2) La Trobe University, Australia), China, Junqing Yu (1), Liliang Ye (1), Melbourne, Technology, Wei Yang (1), Wuhan, Yafeng Wu (1), Yi-Ping Phoebe Chen (2), Yunyao Zhang (1), Zikai Song (1) ((1) Huazhong University of Science","submitted_at":"2025-07-01T16:52:20Z","abstract_excerpt":"Social media platforms serve as central hubs for content dissemination, opinion expression, and public engagement across diverse modalities. Accurately predicting the popularity of social media videos enables valuable applications in content recommendation, trend detection, and audience engagement. In this paper, we present Multimodal Video Predictor (MVP), our winning solution to the Video Track of the SMP Challenge 2025. MVP constructs expressive post representations by integrating deep video features extracted from pretrained models with user metadata and contextual information. The framewo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00950","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/2507.00950/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":"2507.00950","created_at":"2026-07-05T11:30:18.411076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00950v1","created_at":"2026-07-05T11:30:18.411076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00950","created_at":"2026-07-05T11:30:18.411076+00:00"},{"alias_kind":"pith_short_12","alias_value":"CNDML4GYYGSK","created_at":"2026-07-05T11:30:18.411076+00:00"},{"alias_kind":"pith_short_16","alias_value":"CNDML4GYYGSKVLB4","created_at":"2026-07-05T11:30:18.411076+00:00"},{"alias_kind":"pith_short_8","alias_value":"CNDML4GY","created_at":"2026-07-05T11:30:18.411076+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03444","citing_title":"PRISM: Synergizing Vision Foundation Models via Self-organized Expert Specialization","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24765","citing_title":"Semantic-Aware Logical Reasoning via a Semiotic Framework","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26707","citing_title":"CurEvo: Curriculum-Guided Self-Evolution for Video Understanding","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26353","citing_title":"GateMOT: Q-Gated Attention for Dense Object Tracking","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26252","citing_title":"OmniTrend: Content-Context Modeling for Scalable Social Popularity Prediction","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25614","citing_title":"HotComment: A Benchmark for Evaluating Popularity of Online Comments","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19386","citing_title":"Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval","ref_index":122,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11041","citing_title":"From Topology to Trajectory: LLM-Driven World Models For Supply Chain Resilience","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20358","citing_title":"ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CNDML4GYYGSKVLB42QWKOLA2MB","json":"https://pith.science/pith/CNDML4GYYGSKVLB42QWKOLA2MB.json","graph_json":"https://pith.science/api/pith-number/CNDML4GYYGSKVLB42QWKOLA2MB/graph.json","events_json":"https://pith.science/api/pith-number/CNDML4GYYGSKVLB42QWKOLA2MB/events.json","paper":"https://pith.science/paper/CNDML4GY"},"agent_actions":{"view_html":"https://pith.science/pith/CNDML4GYYGSKVLB42QWKOLA2MB","download_json":"https://pith.science/pith/CNDML4GYYGSKVLB42QWKOLA2MB.json","view_paper":"https://pith.science/paper/CNDML4GY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00950&json=true","fetch_graph":"https://pith.science/api/pith-number/CNDML4GYYGSKVLB42QWKOLA2MB/graph.json","fetch_events":"https://pith.science/api/pith-number/CNDML4GYYGSKVLB42QWKOLA2MB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CNDML4GYYGSKVLB42QWKOLA2MB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CNDML4GYYGSKVLB42QWKOLA2MB/action/storage_attestation","attest_author":"https://pith.science/pith/CNDML4GYYGSKVLB42QWKOLA2MB/action/author_attestation","sign_citation":"https://pith.science/pith/CNDML4GYYGSKVLB42QWKOLA2MB/action/citation_signature","submit_replication":"https://pith.science/pith/CNDML4GYYGSKVLB42QWKOLA2MB/action/replication_record"}},"created_at":"2026-07-05T11:30:18.411076+00:00","updated_at":"2026-07-05T11:30:18.411076+00:00"}