{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X6OOKQ7J5NV4RQHRNYML6OXBUG","short_pith_number":"pith:X6OOKQ7J","schema_version":"1.0","canonical_sha256":"bf9ce543e9eb6bc8c0f16e18bf3ae1a1952ac3bc78ed8fb01a6538ffdd4f00db","source":{"kind":"arxiv","id":"2407.08672","version":1},"attestation_state":"computed","paper":{"title":"NODE-Adapter: Neural Ordinary Differential Equations for Better Vision-Language Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angelica I.Aviles-Rivero, Carola-Bibiane Sch\\\"onlieb, Chun-Wun Cheng, Ke Yu, Yi Zhang, Zhihai He","submitted_at":"2024-07-11T17:04:19Z","abstract_excerpt":"In this paper, we consider the problem of prototype-based vision-language reasoning problem. We observe that existing methods encounter three major challenges: 1) escalating resource demands and prolonging training times, 2) contending with excessive learnable parameters, and 3) fine-tuning based only on a single modality. These challenges will hinder their capability to adapt Vision-Language Models (VLMs) to downstream tasks. Motivated by this critical observation, we propose a novel method called NODE-Adapter, which utilizes Neural Ordinary Differential Equations for better vision-language r"},"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":"2407.08672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-11T17:04:19Z","cross_cats_sorted":[],"title_canon_sha256":"667ea3eca8d1632d3d25fa5ee4d324fee2a63cbeb6e6c95c08f8a0b2783e3404","abstract_canon_sha256":"90b77e031b9dbe090e41044e130735681d24c2a2fbbd8f44a7178acbb02a3743"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:51.418099Z","signature_b64":"R+vHMavQIbUCXZwjk13jzFb99kULK3MjF3haE3w1967MSWWS6Y1QR1DKCUvJdHiNLb/TMGYbqmSlZu20wGDBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf9ce543e9eb6bc8c0f16e18bf3ae1a1952ac3bc78ed8fb01a6538ffdd4f00db","last_reissued_at":"2026-07-05T08:42:51.417755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:51.417755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NODE-Adapter: Neural Ordinary Differential Equations for Better Vision-Language Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angelica I.Aviles-Rivero, Carola-Bibiane Sch\\\"onlieb, Chun-Wun Cheng, Ke Yu, Yi Zhang, Zhihai He","submitted_at":"2024-07-11T17:04:19Z","abstract_excerpt":"In this paper, we consider the problem of prototype-based vision-language reasoning problem. We observe that existing methods encounter three major challenges: 1) escalating resource demands and prolonging training times, 2) contending with excessive learnable parameters, and 3) fine-tuning based only on a single modality. These challenges will hinder their capability to adapt Vision-Language Models (VLMs) to downstream tasks. Motivated by this critical observation, we propose a novel method called NODE-Adapter, which utilizes Neural Ordinary Differential Equations for better vision-language r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08672","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/2407.08672/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":"2407.08672","created_at":"2026-07-05T08:42:51.417810+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.08672v1","created_at":"2026-07-05T08:42:51.417810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08672","created_at":"2026-07-05T08:42:51.417810+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6OOKQ7J5NV4","created_at":"2026-07-05T08:42:51.417810+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6OOKQ7J5NV4RQHR","created_at":"2026-07-05T08:42:51.417810+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6OOKQ7J","created_at":"2026-07-05T08:42:51.417810+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01225","citing_title":"Multi-Cache Enhanced Prototype Learning for Test-Time Generalization of Vision-Language Models","ref_index":76,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6OOKQ7J5NV4RQHRNYML6OXBUG","json":"https://pith.science/pith/X6OOKQ7J5NV4RQHRNYML6OXBUG.json","graph_json":"https://pith.science/api/pith-number/X6OOKQ7J5NV4RQHRNYML6OXBUG/graph.json","events_json":"https://pith.science/api/pith-number/X6OOKQ7J5NV4RQHRNYML6OXBUG/events.json","paper":"https://pith.science/paper/X6OOKQ7J"},"agent_actions":{"view_html":"https://pith.science/pith/X6OOKQ7J5NV4RQHRNYML6OXBUG","download_json":"https://pith.science/pith/X6OOKQ7J5NV4RQHRNYML6OXBUG.json","view_paper":"https://pith.science/paper/X6OOKQ7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.08672&json=true","fetch_graph":"https://pith.science/api/pith-number/X6OOKQ7J5NV4RQHRNYML6OXBUG/graph.json","fetch_events":"https://pith.science/api/pith-number/X6OOKQ7J5NV4RQHRNYML6OXBUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6OOKQ7J5NV4RQHRNYML6OXBUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6OOKQ7J5NV4RQHRNYML6OXBUG/action/storage_attestation","attest_author":"https://pith.science/pith/X6OOKQ7J5NV4RQHRNYML6OXBUG/action/author_attestation","sign_citation":"https://pith.science/pith/X6OOKQ7J5NV4RQHRNYML6OXBUG/action/citation_signature","submit_replication":"https://pith.science/pith/X6OOKQ7J5NV4RQHRNYML6OXBUG/action/replication_record"}},"created_at":"2026-07-05T08:42:51.417810+00:00","updated_at":"2026-07-05T08:42:51.417810+00:00"}