{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RS5B2QQBKQVON6E67FENKFLJAH","short_pith_number":"pith:RS5B2QQB","schema_version":"1.0","canonical_sha256":"8cba1d4201542ae6f89ef948d5156901c3ba5b6baeee661890af346210fd390a","source":{"kind":"arxiv","id":"2410.07854","version":1},"attestation_state":"computed","paper":{"title":"HeGraphAdapter: Tuning Multi-Modal Vision-Language Models with Heterogeneous Graph Adapter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bo Jiang, Jin Tang, Qin Xu, Xiao Wang, Yumiao Zhao","submitted_at":"2024-10-10T12:20:58Z","abstract_excerpt":"Adapter-based tuning methods have shown significant potential in transferring knowledge from pre-trained Vision-Language Models to the downstream tasks. However, after reviewing existing adapters, we find they generally fail to fully explore the interactions between different modalities in constructing task-specific knowledge. Also, existing works usually only focus on similarity matching between positive text prompts, making it challenging to distinguish the classes with high similar visual contents. To address these issues, in this paper, we propose a novel Heterogeneous Graph Adapter to ach"},"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":"2410.07854","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T12:20:58Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"df30e0a4c1be41658d19982052b58e772dc0042b67c82d0f62c23a5a8494e075","abstract_canon_sha256":"8a7118aa2e94227bed792b140472813bc4e3d3ee6d07f6bb4e9aefdc4789c3f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:45.100608Z","signature_b64":"XNuzLnscscsCsD8CI/lRr1qeNHLGWjQd8BPScsJZUcmVrB1GwMeKOe4IjT5CioW+gVLWMWVAALo7owo37KzgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cba1d4201542ae6f89ef948d5156901c3ba5b6baeee661890af346210fd390a","last_reissued_at":"2026-07-05T09:18:45.099947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:45.099947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HeGraphAdapter: Tuning Multi-Modal Vision-Language Models with Heterogeneous Graph Adapter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bo Jiang, Jin Tang, Qin Xu, Xiao Wang, Yumiao Zhao","submitted_at":"2024-10-10T12:20:58Z","abstract_excerpt":"Adapter-based tuning methods have shown significant potential in transferring knowledge from pre-trained Vision-Language Models to the downstream tasks. However, after reviewing existing adapters, we find they generally fail to fully explore the interactions between different modalities in constructing task-specific knowledge. Also, existing works usually only focus on similarity matching between positive text prompts, making it challenging to distinguish the classes with high similar visual contents. To address these issues, in this paper, we propose a novel Heterogeneous Graph Adapter to ach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07854","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/2410.07854/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":"2410.07854","created_at":"2026-07-05T09:18:45.100038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07854v1","created_at":"2026-07-05T09:18:45.100038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07854","created_at":"2026-07-05T09:18:45.100038+00:00"},{"alias_kind":"pith_short_12","alias_value":"RS5B2QQBKQVO","created_at":"2026-07-05T09:18:45.100038+00:00"},{"alias_kind":"pith_short_16","alias_value":"RS5B2QQBKQVON6E6","created_at":"2026-07-05T09:18:45.100038+00:00"},{"alias_kind":"pith_short_8","alias_value":"RS5B2QQB","created_at":"2026-07-05T09:18:45.100038+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10355","citing_title":"Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RS5B2QQBKQVON6E67FENKFLJAH","json":"https://pith.science/pith/RS5B2QQBKQVON6E67FENKFLJAH.json","graph_json":"https://pith.science/api/pith-number/RS5B2QQBKQVON6E67FENKFLJAH/graph.json","events_json":"https://pith.science/api/pith-number/RS5B2QQBKQVON6E67FENKFLJAH/events.json","paper":"https://pith.science/paper/RS5B2QQB"},"agent_actions":{"view_html":"https://pith.science/pith/RS5B2QQBKQVON6E67FENKFLJAH","download_json":"https://pith.science/pith/RS5B2QQBKQVON6E67FENKFLJAH.json","view_paper":"https://pith.science/paper/RS5B2QQB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07854&json=true","fetch_graph":"https://pith.science/api/pith-number/RS5B2QQBKQVON6E67FENKFLJAH/graph.json","fetch_events":"https://pith.science/api/pith-number/RS5B2QQBKQVON6E67FENKFLJAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RS5B2QQBKQVON6E67FENKFLJAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RS5B2QQBKQVON6E67FENKFLJAH/action/storage_attestation","attest_author":"https://pith.science/pith/RS5B2QQBKQVON6E67FENKFLJAH/action/author_attestation","sign_citation":"https://pith.science/pith/RS5B2QQBKQVON6E67FENKFLJAH/action/citation_signature","submit_replication":"https://pith.science/pith/RS5B2QQBKQVON6E67FENKFLJAH/action/replication_record"}},"created_at":"2026-07-05T09:18:45.100038+00:00","updated_at":"2026-07-05T09:18:45.100038+00:00"}