{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5TLEUUVKK2QQXLCA6IPLOAU6TO","short_pith_number":"pith:5TLEUUVK","schema_version":"1.0","canonical_sha256":"ecd64a52aa56a10bac40f21eb7029e9b92d4de53789f32cb91b33e552fc83ca2","source":{"kind":"arxiv","id":"2607.15374","version":1},"attestation_state":"computed","paper":{"title":"Reasoning-Guided Part-Level Visual Grounding via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anuj Karpatne, Chia-Wei Tang, Chris Thomas, Hani Alomari, Kazi Sajeed Mehrab, Najibul Haque Sarker, Zaber Ibn Abdul Hakim","submitted_at":"2026-07-16T18:18:31Z","abstract_excerpt":"Multimodal large language models (MLLMs) ground whole objects well from free-form language queries, but they struggle when the query names a part rather than the object. We trace this to a missing object-part hierarchy, since parts are localized in the same single step used for objects. We propose Object-Part Hierarchical Reflective Grounding (OP-HRG), a coarse-to-fine reasoning-guided grounding strategy that first localizes the parent object and then the part within it. A self-check then reflects on the result, with an extension to re-encode the predicted crop to inspect the region it is corr"},"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":"2607.15374","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-16T18:18:31Z","cross_cats_sorted":[],"title_canon_sha256":"dda3f5ba5ecc16b1c4650e9bea9ab2e43c979f0e292b44df065c8580e4a668d9","abstract_canon_sha256":"69e8c942f0c1e7150f833912dbdec31401cf8d81baa1593b6791137f98af49cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T00:18:29.977059Z","signature_b64":"Io7QXzF4rfmfdcVMFcdG4+HWmh3SU0S38qhUC/qSTrJVooM2Ar9SaLjZu20AcevSkvWGmqOLnniOdcGG0xOQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecd64a52aa56a10bac40f21eb7029e9b92d4de53789f32cb91b33e552fc83ca2","last_reissued_at":"2026-07-20T00:18:29.976260Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T00:18:29.976260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning-Guided Part-Level Visual Grounding via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anuj Karpatne, Chia-Wei Tang, Chris Thomas, Hani Alomari, Kazi Sajeed Mehrab, Najibul Haque Sarker, Zaber Ibn Abdul Hakim","submitted_at":"2026-07-16T18:18:31Z","abstract_excerpt":"Multimodal large language models (MLLMs) ground whole objects well from free-form language queries, but they struggle when the query names a part rather than the object. We trace this to a missing object-part hierarchy, since parts are localized in the same single step used for objects. We propose Object-Part Hierarchical Reflective Grounding (OP-HRG), a coarse-to-fine reasoning-guided grounding strategy that first localizes the parent object and then the part within it. A self-check then reflects on the result, with an extension to re-encode the predicted crop to inspect the region it is corr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15374","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/2607.15374/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":"2607.15374","created_at":"2026-07-20T00:18:29.976669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.15374v1","created_at":"2026-07-20T00:18:29.976669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15374","created_at":"2026-07-20T00:18:29.976669+00:00"},{"alias_kind":"pith_short_12","alias_value":"5TLEUUVKK2QQ","created_at":"2026-07-20T00:18:29.976669+00:00"},{"alias_kind":"pith_short_16","alias_value":"5TLEUUVKK2QQXLCA","created_at":"2026-07-20T00:18:29.976669+00:00"},{"alias_kind":"pith_short_8","alias_value":"5TLEUUVK","created_at":"2026-07-20T00:18:29.976669+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/5TLEUUVKK2QQXLCA6IPLOAU6TO","json":"https://pith.science/pith/5TLEUUVKK2QQXLCA6IPLOAU6TO.json","graph_json":"https://pith.science/api/pith-number/5TLEUUVKK2QQXLCA6IPLOAU6TO/graph.json","events_json":"https://pith.science/api/pith-number/5TLEUUVKK2QQXLCA6IPLOAU6TO/events.json","paper":"https://pith.science/paper/5TLEUUVK"},"agent_actions":{"view_html":"https://pith.science/pith/5TLEUUVKK2QQXLCA6IPLOAU6TO","download_json":"https://pith.science/pith/5TLEUUVKK2QQXLCA6IPLOAU6TO.json","view_paper":"https://pith.science/paper/5TLEUUVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.15374&json=true","fetch_graph":"https://pith.science/api/pith-number/5TLEUUVKK2QQXLCA6IPLOAU6TO/graph.json","fetch_events":"https://pith.science/api/pith-number/5TLEUUVKK2QQXLCA6IPLOAU6TO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5TLEUUVKK2QQXLCA6IPLOAU6TO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5TLEUUVKK2QQXLCA6IPLOAU6TO/action/storage_attestation","attest_author":"https://pith.science/pith/5TLEUUVKK2QQXLCA6IPLOAU6TO/action/author_attestation","sign_citation":"https://pith.science/pith/5TLEUUVKK2QQXLCA6IPLOAU6TO/action/citation_signature","submit_replication":"https://pith.science/pith/5TLEUUVKK2QQXLCA6IPLOAU6TO/action/replication_record"}},"created_at":"2026-07-20T00:18:29.976669+00:00","updated_at":"2026-07-20T00:18:29.976669+00:00"}