{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W6CST7XD7XTSXXD4KCNVFSPH5T","short_pith_number":"pith:W6CST7XD","schema_version":"1.0","canonical_sha256":"b78529fee3fde72bdc7c509b52c9e7ecdcc98fb90db6375614dfd2d9ebcc7447","source":{"kind":"arxiv","id":"2507.23543","version":2},"attestation_state":"computed","paper":{"title":"ART: Adaptive Relation Tuning for Generalized Relation Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gopika Sudhakaran, Hikaru Shindo, Kristian Kersting, Patrick Schramowski, Simone Schaub-Meyer, Stefan Roth","submitted_at":"2025-07-31T13:34:06Z","abstract_excerpt":"Visual relation detection (VRD) is the task of identifying the relationships between objects in a scene. VRD models trained solely on relation detection data struggle to generalize beyond the relations on which they are trained. While prompt tuning has been used to adapt vision-language models (VLMs) for VRD, it uses handcrafted prompts and struggles with novel or complex relations. We argue that instruction tuning offers a more effective solution by fine-tuning VLMs on diverse instructional data. We thus introduce ART, an Adaptive Relation Tuning framework that adapts VLMs for VRD through ins"},"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":"2507.23543","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-31T13:34:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d29735a968a70dc4a7414ddfe2a9a80c24f052a26f232441e1f1b1e25fb3da5a","abstract_canon_sha256":"b690dd21ae42d1336e0c48701ffe43f27ab5c0a033135eae6e2a50bb611ce0e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:39.082261Z","signature_b64":"Aa9URQHegnLHmmsqrLWSoOoG7zC1k0d4SwC2bzApBC5Dn+c6bjvFlnYH/934ACtjiVUfzqLhbcu9Ilq/IMh9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b78529fee3fde72bdc7c509b52c9e7ecdcc98fb90db6375614dfd2d9ebcc7447","last_reissued_at":"2026-07-05T11:50:39.081581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:39.081581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ART: Adaptive Relation Tuning for Generalized Relation Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Gopika Sudhakaran, Hikaru Shindo, Kristian Kersting, Patrick Schramowski, Simone Schaub-Meyer, Stefan Roth","submitted_at":"2025-07-31T13:34:06Z","abstract_excerpt":"Visual relation detection (VRD) is the task of identifying the relationships between objects in a scene. VRD models trained solely on relation detection data struggle to generalize beyond the relations on which they are trained. While prompt tuning has been used to adapt vision-language models (VLMs) for VRD, it uses handcrafted prompts and struggles with novel or complex relations. We argue that instruction tuning offers a more effective solution by fine-tuning VLMs on diverse instructional data. We thus introduce ART, an Adaptive Relation Tuning framework that adapts VLMs for VRD through ins"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23543","kind":"arxiv","version":2},"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/2507.23543/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":"2507.23543","created_at":"2026-07-05T11:50:39.081645+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.23543v2","created_at":"2026-07-05T11:50:39.081645+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23543","created_at":"2026-07-05T11:50:39.081645+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6CST7XD7XTS","created_at":"2026-07-05T11:50:39.081645+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6CST7XD7XTSXXD4","created_at":"2026-07-05T11:50:39.081645+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6CST7XD","created_at":"2026-07-05T11:50:39.081645+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/W6CST7XD7XTSXXD4KCNVFSPH5T","json":"https://pith.science/pith/W6CST7XD7XTSXXD4KCNVFSPH5T.json","graph_json":"https://pith.science/api/pith-number/W6CST7XD7XTSXXD4KCNVFSPH5T/graph.json","events_json":"https://pith.science/api/pith-number/W6CST7XD7XTSXXD4KCNVFSPH5T/events.json","paper":"https://pith.science/paper/W6CST7XD"},"agent_actions":{"view_html":"https://pith.science/pith/W6CST7XD7XTSXXD4KCNVFSPH5T","download_json":"https://pith.science/pith/W6CST7XD7XTSXXD4KCNVFSPH5T.json","view_paper":"https://pith.science/paper/W6CST7XD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.23543&json=true","fetch_graph":"https://pith.science/api/pith-number/W6CST7XD7XTSXXD4KCNVFSPH5T/graph.json","fetch_events":"https://pith.science/api/pith-number/W6CST7XD7XTSXXD4KCNVFSPH5T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6CST7XD7XTSXXD4KCNVFSPH5T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6CST7XD7XTSXXD4KCNVFSPH5T/action/storage_attestation","attest_author":"https://pith.science/pith/W6CST7XD7XTSXXD4KCNVFSPH5T/action/author_attestation","sign_citation":"https://pith.science/pith/W6CST7XD7XTSXXD4KCNVFSPH5T/action/citation_signature","submit_replication":"https://pith.science/pith/W6CST7XD7XTSXXD4KCNVFSPH5T/action/replication_record"}},"created_at":"2026-07-05T11:50:39.081645+00:00","updated_at":"2026-07-05T11:50:39.081645+00:00"}