{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ABVPT6UI4CYHTSTX7MQYQ7XVDA","short_pith_number":"pith:ABVPT6UI","schema_version":"1.0","canonical_sha256":"006af9fa88e0b079ca77fb21887ef5183692839ac44408262d3a21a3f966ff38","source":{"kind":"arxiv","id":"2607.18716","version":1},"attestation_state":"computed","paper":{"title":"Continual Video-MLLM Adaptation over Evolving Domains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianwei Yin, Jingcai Guo, Meixing Shi, Rui Cheng, Yuxiang Cai, Zhi Chen","submitted_at":"2026-07-21T05:16:36Z","abstract_excerpt":"Video multimodal large language models have shown strong capability in video understanding, yet their adaptation to sequentially evolving domains remains underexplored. In real-world deployments, video data often arrives continuously from heterogeneous domains, requiring the model to acquire new domain-specific knowledge without overwriting previously learned capabilities. Existing continual learning methods typically rely on shared adaptation spaces, which can induce severe cross-domain interference and catastrophic forgetting. We propose Distribution-Aware Expert Routing, a parameter-efficie"},"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":"2607.18716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-21T05:16:36Z","cross_cats_sorted":[],"title_canon_sha256":"5c1d74e2002c6b009114b223c85890ce2d90c704168e3a0708a7c73450012e03","abstract_canon_sha256":"7b9cd4587633d556232d488dcfa938219fb112378284cfe5ac8de8144048f30e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:23:08.060152Z","signature_b64":"z1G6KBSW4tTLJn9bKATf1WWCnliOphGAOj/lR73xLIRlGskKFTdNaOOKnIq5BhKC3P92XOsVPuo2XS3T0wStDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"006af9fa88e0b079ca77fb21887ef5183692839ac44408262d3a21a3f966ff38","last_reissued_at":"2026-07-22T01:23:08.059304Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:23:08.059304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Video-MLLM Adaptation over Evolving Domains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianwei Yin, Jingcai Guo, Meixing Shi, Rui Cheng, Yuxiang Cai, Zhi Chen","submitted_at":"2026-07-21T05:16:36Z","abstract_excerpt":"Video multimodal large language models have shown strong capability in video understanding, yet their adaptation to sequentially evolving domains remains underexplored. In real-world deployments, video data often arrives continuously from heterogeneous domains, requiring the model to acquire new domain-specific knowledge without overwriting previously learned capabilities. Existing continual learning methods typically rely on shared adaptation spaces, which can induce severe cross-domain interference and catastrophic forgetting. We propose Distribution-Aware Expert Routing, a parameter-efficie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18716","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/2607.18716/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":"2607.18716","created_at":"2026-07-22T01:23:08.059747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18716v1","created_at":"2026-07-22T01:23:08.059747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18716","created_at":"2026-07-22T01:23:08.059747+00:00"},{"alias_kind":"pith_short_12","alias_value":"ABVPT6UI4CYH","created_at":"2026-07-22T01:23:08.059747+00:00"},{"alias_kind":"pith_short_16","alias_value":"ABVPT6UI4CYHTSTX","created_at":"2026-07-22T01:23:08.059747+00:00"},{"alias_kind":"pith_short_8","alias_value":"ABVPT6UI","created_at":"2026-07-22T01:23:08.059747+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/ABVPT6UI4CYHTSTX7MQYQ7XVDA","json":"https://pith.science/pith/ABVPT6UI4CYHTSTX7MQYQ7XVDA.json","graph_json":"https://pith.science/api/pith-number/ABVPT6UI4CYHTSTX7MQYQ7XVDA/graph.json","events_json":"https://pith.science/api/pith-number/ABVPT6UI4CYHTSTX7MQYQ7XVDA/events.json","paper":"https://pith.science/paper/ABVPT6UI"},"agent_actions":{"view_html":"https://pith.science/pith/ABVPT6UI4CYHTSTX7MQYQ7XVDA","download_json":"https://pith.science/pith/ABVPT6UI4CYHTSTX7MQYQ7XVDA.json","view_paper":"https://pith.science/paper/ABVPT6UI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18716&json=true","fetch_graph":"https://pith.science/api/pith-number/ABVPT6UI4CYHTSTX7MQYQ7XVDA/graph.json","fetch_events":"https://pith.science/api/pith-number/ABVPT6UI4CYHTSTX7MQYQ7XVDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ABVPT6UI4CYHTSTX7MQYQ7XVDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ABVPT6UI4CYHTSTX7MQYQ7XVDA/action/storage_attestation","attest_author":"https://pith.science/pith/ABVPT6UI4CYHTSTX7MQYQ7XVDA/action/author_attestation","sign_citation":"https://pith.science/pith/ABVPT6UI4CYHTSTX7MQYQ7XVDA/action/citation_signature","submit_replication":"https://pith.science/pith/ABVPT6UI4CYHTSTX7MQYQ7XVDA/action/replication_record"}},"created_at":"2026-07-22T01:23:08.059747+00:00","updated_at":"2026-07-22T01:23:08.059747+00:00"}