{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X7UIQARNXRZCWUGBGFHPRPWV5O","short_pith_number":"pith:X7UIQARN","schema_version":"1.0","canonical_sha256":"bfe888022dbc722b50c1314ef8bed5ebb3157d3750a0acaefa9a9ba1f8273aa6","source":{"kind":"arxiv","id":"2506.12724","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Modality Scheduling for Multimodal Large Models via Confidence, Uncertainty, and Semantic Consistency","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anika Rao, Hana Satou, Hiroshi Tanaka, Michael Johnson, Sofia Garc\\'ia","submitted_at":"2025-06-15T05:15:52Z","abstract_excerpt":"Multimodal Large Models (MLLMs) have achieved remarkable progress in vision-language understanding and generation tasks. However, existing MLLMs typically rely on static modality fusion strategies, which treat all modalities equally regardless of their instance-level reliability or semantic contribution. This often leads to suboptimal performance, especially in scenarios with noisy, missing, or misaligned modalities.\n  In this paper, we propose Dynamic Modality Scheduling (DMS), a novel framework that adaptively adjusts the contribution of each modality at a per-sample level. DMS evaluates eac"},"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":"2506.12724","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-15T05:15:52Z","cross_cats_sorted":[],"title_canon_sha256":"4256a482ec6dc3f7358beb518264fda122ba60d9243571d559564a539fdf5d7e","abstract_canon_sha256":"25a254d9585041927fbcdd3542c2473ee957146130d64a78c5786c2301b938a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:58.351899Z","signature_b64":"/JuCQtilJDtAnfmeCK0oBgMw/Jjn7CSiec6BGut61pairpvnxp16AA4NgDIBLUF4HGHRQ0DwEJG7MvZR3DI5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfe888022dbc722b50c1314ef8bed5ebb3157d3750a0acaefa9a9ba1f8273aa6","last_reissued_at":"2026-07-05T11:21:58.351476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:58.351476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Modality Scheduling for Multimodal Large Models via Confidence, Uncertainty, and Semantic Consistency","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anika Rao, Hana Satou, Hiroshi Tanaka, Michael Johnson, Sofia Garc\\'ia","submitted_at":"2025-06-15T05:15:52Z","abstract_excerpt":"Multimodal Large Models (MLLMs) have achieved remarkable progress in vision-language understanding and generation tasks. However, existing MLLMs typically rely on static modality fusion strategies, which treat all modalities equally regardless of their instance-level reliability or semantic contribution. This often leads to suboptimal performance, especially in scenarios with noisy, missing, or misaligned modalities.\n  In this paper, we propose Dynamic Modality Scheduling (DMS), a novel framework that adaptively adjusts the contribution of each modality at a per-sample level. DMS evaluates eac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12724","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/2506.12724/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":"2506.12724","created_at":"2026-07-05T11:21:58.351536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12724v1","created_at":"2026-07-05T11:21:58.351536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12724","created_at":"2026-07-05T11:21:58.351536+00:00"},{"alias_kind":"pith_short_12","alias_value":"X7UIQARNXRZC","created_at":"2026-07-05T11:21:58.351536+00:00"},{"alias_kind":"pith_short_16","alias_value":"X7UIQARNXRZCWUGB","created_at":"2026-07-05T11:21:58.351536+00:00"},{"alias_kind":"pith_short_8","alias_value":"X7UIQARN","created_at":"2026-07-05T11:21:58.351536+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/X7UIQARNXRZCWUGBGFHPRPWV5O","json":"https://pith.science/pith/X7UIQARNXRZCWUGBGFHPRPWV5O.json","graph_json":"https://pith.science/api/pith-number/X7UIQARNXRZCWUGBGFHPRPWV5O/graph.json","events_json":"https://pith.science/api/pith-number/X7UIQARNXRZCWUGBGFHPRPWV5O/events.json","paper":"https://pith.science/paper/X7UIQARN"},"agent_actions":{"view_html":"https://pith.science/pith/X7UIQARNXRZCWUGBGFHPRPWV5O","download_json":"https://pith.science/pith/X7UIQARNXRZCWUGBGFHPRPWV5O.json","view_paper":"https://pith.science/paper/X7UIQARN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12724&json=true","fetch_graph":"https://pith.science/api/pith-number/X7UIQARNXRZCWUGBGFHPRPWV5O/graph.json","fetch_events":"https://pith.science/api/pith-number/X7UIQARNXRZCWUGBGFHPRPWV5O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X7UIQARNXRZCWUGBGFHPRPWV5O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X7UIQARNXRZCWUGBGFHPRPWV5O/action/storage_attestation","attest_author":"https://pith.science/pith/X7UIQARNXRZCWUGBGFHPRPWV5O/action/author_attestation","sign_citation":"https://pith.science/pith/X7UIQARNXRZCWUGBGFHPRPWV5O/action/citation_signature","submit_replication":"https://pith.science/pith/X7UIQARNXRZCWUGBGFHPRPWV5O/action/replication_record"}},"created_at":"2026-07-05T11:21:58.351536+00:00","updated_at":"2026-07-05T11:21:58.351536+00:00"}