{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LN5MITOSOMAIMG4KBSAVTYJYBU","short_pith_number":"pith:LN5MITOS","schema_version":"1.0","canonical_sha256":"5b7ac44dd27300861b8a0c8159e1380d068b5d550a61e5be0cc0b96f47210ab0","source":{"kind":"arxiv","id":"2605.28229","version":1},"attestation_state":"computed","paper":{"title":"VidPrism: Heterogeneous Mixture of Experts for Image-to-Video Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chuanming Wang, Huadong Ma, Rui Lin","submitted_at":"2026-05-27T09:43:06Z","abstract_excerpt":"With the rapid development of pre-training technologies, adapting large-scale Vision-Language Models (VLMs) for video understanding \\emph{\\ie} image-to-video transfer learning has become a dominant paradigm. To achieve superior performance, it raises as an effective strategy among recent advances to employ Mixture-of-Experts (MoE) to enhance VLMs' temporal modeling capabilities. However, conventional MoE designs suffer from expert homogenization, where all experts act as identical generalists, inefficiently learning spatio-temporal features from undifferentiated video streams. To overcome this"},"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":"2605.28229","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T09:43:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"983a4a5ac6cfeeefb6c378d975b18f4a938a38d669e6912c7a5a0a05612e5a9f","abstract_canon_sha256":"ca1799606c272a15d8c97686985c1505f502ea680e5d6b7a71ee56fb77dd9a26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:03.287427Z","signature_b64":"PRVdoWA+RTHx22ONUcpn/KR3ZGr1uXCvAgjDnltosAFpQv9uqfAUQbn8dP6KVxbITd8bfwAEQVCCfBY0LPL/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b7ac44dd27300861b8a0c8159e1380d068b5d550a61e5be0cc0b96f47210ab0","last_reissued_at":"2026-05-28T01:05:03.287007Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:03.287007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VidPrism: Heterogeneous Mixture of Experts for Image-to-Video Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chuanming Wang, Huadong Ma, Rui Lin","submitted_at":"2026-05-27T09:43:06Z","abstract_excerpt":"With the rapid development of pre-training technologies, adapting large-scale Vision-Language Models (VLMs) for video understanding \\emph{\\ie} image-to-video transfer learning has become a dominant paradigm. To achieve superior performance, it raises as an effective strategy among recent advances to employ Mixture-of-Experts (MoE) to enhance VLMs' temporal modeling capabilities. However, conventional MoE designs suffer from expert homogenization, where all experts act as identical generalists, inefficiently learning spatio-temporal features from undifferentiated video streams. To overcome this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28229","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/2605.28229/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":"2605.28229","created_at":"2026-05-28T01:05:03.287057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28229v1","created_at":"2026-05-28T01:05:03.287057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28229","created_at":"2026-05-28T01:05:03.287057+00:00"},{"alias_kind":"pith_short_12","alias_value":"LN5MITOSOMAI","created_at":"2026-05-28T01:05:03.287057+00:00"},{"alias_kind":"pith_short_16","alias_value":"LN5MITOSOMAIMG4K","created_at":"2026-05-28T01:05:03.287057+00:00"},{"alias_kind":"pith_short_8","alias_value":"LN5MITOS","created_at":"2026-05-28T01:05:03.287057+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/LN5MITOSOMAIMG4KBSAVTYJYBU","json":"https://pith.science/pith/LN5MITOSOMAIMG4KBSAVTYJYBU.json","graph_json":"https://pith.science/api/pith-number/LN5MITOSOMAIMG4KBSAVTYJYBU/graph.json","events_json":"https://pith.science/api/pith-number/LN5MITOSOMAIMG4KBSAVTYJYBU/events.json","paper":"https://pith.science/paper/LN5MITOS"},"agent_actions":{"view_html":"https://pith.science/pith/LN5MITOSOMAIMG4KBSAVTYJYBU","download_json":"https://pith.science/pith/LN5MITOSOMAIMG4KBSAVTYJYBU.json","view_paper":"https://pith.science/paper/LN5MITOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28229&json=true","fetch_graph":"https://pith.science/api/pith-number/LN5MITOSOMAIMG4KBSAVTYJYBU/graph.json","fetch_events":"https://pith.science/api/pith-number/LN5MITOSOMAIMG4KBSAVTYJYBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LN5MITOSOMAIMG4KBSAVTYJYBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LN5MITOSOMAIMG4KBSAVTYJYBU/action/storage_attestation","attest_author":"https://pith.science/pith/LN5MITOSOMAIMG4KBSAVTYJYBU/action/author_attestation","sign_citation":"https://pith.science/pith/LN5MITOSOMAIMG4KBSAVTYJYBU/action/citation_signature","submit_replication":"https://pith.science/pith/LN5MITOSOMAIMG4KBSAVTYJYBU/action/replication_record"}},"created_at":"2026-05-28T01:05:03.287057+00:00","updated_at":"2026-05-28T01:05:03.287057+00:00"}