{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6UCR7T2OHSXYAJF7NLSZ27XSB7","short_pith_number":"pith:6UCR7T2O","schema_version":"1.0","canonical_sha256":"f5051fcf4e3caf8024bf6ae59d7ef20fea6012e959391e00346c7b3305120a6a","source":{"kind":"arxiv","id":"2604.27122","version":2},"attestation_state":"computed","paper":{"title":"InterPartAbility: Phrase-Region Grounding for Interpretable Text-to-Image Person Re-Identification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"InterPartAbility adds text-guided part matching and constrained attention to produce grounded explanations for text-to-image person re-identification.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aryan Shukla, Eric Granger, Maguelonne Heritier, Rajarshi Bhattacharya, Shakeeb Murtaza","submitted_at":"2026-04-29T19:18:36Z","abstract_excerpt":"Text-to-image person re-identification (TI-ReID) relies on natural-language text descriptions to retrieve top matching individuals from a gallery of reference images. While recent large vision-language models (VLMs) achieve strong retrieval performance, their decisions remain largely uninterpretable. Existing interpretability approaches in TI-ReID rely solely on slot-attention to highlight attended regions, but fail to reliably bind visual regions to semantically meaningful concepts, limiting interpretation to qualitative visualizations over a restricted vocabulary. This paper introduces Inter"},"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":"2604.27122","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-29T19:18:36Z","cross_cats_sorted":[],"title_canon_sha256":"48e6389300ec305dfb56b2519377797ca9f1e495f92af30107b86de1d01cbe23","abstract_canon_sha256":"7582f3912c9af52ceb054f810bc17d1ba8e1310e8a3323872b2231c289f839f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:38.864176Z","signature_b64":"DsVyKAnmNfIu8NfAf2EoDqFAsY0seT1G6YgkRj4nYNeNUZOjIPR9tzJ2uZQS2uBGKUOJZXeRHv9gnExwf00xBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5051fcf4e3caf8024bf6ae59d7ef20fea6012e959391e00346c7b3305120a6a","last_reissued_at":"2026-06-30T01:17:38.863579Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:38.863579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InterPartAbility: Phrase-Region Grounding for Interpretable Text-to-Image Person Re-Identification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"InterPartAbility adds text-guided part matching and constrained attention to produce grounded explanations for text-to-image person re-identification.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aryan Shukla, Eric Granger, Maguelonne Heritier, Rajarshi Bhattacharya, Shakeeb Murtaza","submitted_at":"2026-04-29T19:18:36Z","abstract_excerpt":"Text-to-image person re-identification (TI-ReID) relies on natural-language text descriptions to retrieve top matching individuals from a gallery of reference images. While recent large vision-language models (VLMs) achieve strong retrieval performance, their decisions remain largely uninterpretable. Existing interpretability approaches in TI-ReID rely solely on slot-attention to highlight attended regions, but fail to reliably bind visual regions to semantically meaningful concepts, limiting interpretation to qualitative visualizations over a restricted vocabulary. This paper introduces Inter"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Empirical results on challenging benchmarks like CUHK-PEDES and ICFG-PEDES show that InterPartAbility achieves state-of-the-art (SOTA) interpretability performance under these metrics, while sustaining competitive retrieval accuracy.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that the patch-phrase interaction module and constrained CLIP ViT self-attention reliably bind visual regions to semantically meaningful part phrases, which may not hold without further validation of the grounding quality.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"InterPartAbility performs explicit part-wise matching in text-to-image person re-identification via a patch-phrase interaction module to produce grounded explanations and achieves SOTA interpretability scores while maintaining competitive retrieval accuracy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"InterPartAbility adds text-guided part matching and constrained attention to produce grounded explanations for text-to-image person re-identification.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fd025ce786d0f9c4ececfdb396ee0f8a9e3a8bceac8c61bc052a49d30751550c"},"source":{"id":"2604.27122","kind":"arxiv","version":2},"verdict":{"id":"41d31c4f-1c71-4e4f-97ea-ca8d472c4539","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-07T09:25:00.195583Z","strongest_claim":"Empirical results on challenging benchmarks like CUHK-PEDES and ICFG-PEDES show that InterPartAbility achieves state-of-the-art (SOTA) interpretability performance under these metrics, while sustaining competitive retrieval accuracy.","one_line_summary":"InterPartAbility performs explicit part-wise matching in text-to-image person re-identification via a patch-phrase interaction module to produce grounded explanations and achieves SOTA interpretability scores while maintaining competitive retrieval accuracy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that the patch-phrase interaction module and constrained CLIP ViT self-attention reliably bind visual regions to semantically meaningful part phrases, which may not hold without further validation of the grounding quality.","pith_extraction_headline":"InterPartAbility adds text-guided part matching and constrained attention to produce grounded explanations for text-to-image person re-identification."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.27122/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T22:43:59.556510Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T19:33:34.214487Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"84072496d4463b0677dc00e59a503628e24a4f9f400a6f2c69d38bc4704c6695"},"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":"2604.27122","created_at":"2026-06-30T01:17:38.863652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.27122v2","created_at":"2026-06-30T01:17:38.863652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27122","created_at":"2026-06-30T01:17:38.863652+00:00"},{"alias_kind":"pith_short_12","alias_value":"6UCR7T2OHSXY","created_at":"2026-06-30T01:17:38.863652+00:00"},{"alias_kind":"pith_short_16","alias_value":"6UCR7T2OHSXYAJF7","created_at":"2026-06-30T01:17:38.863652+00:00"},{"alias_kind":"pith_short_8","alias_value":"6UCR7T2O","created_at":"2026-06-30T01:17:38.863652+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/6UCR7T2OHSXYAJF7NLSZ27XSB7","json":"https://pith.science/pith/6UCR7T2OHSXYAJF7NLSZ27XSB7.json","graph_json":"https://pith.science/api/pith-number/6UCR7T2OHSXYAJF7NLSZ27XSB7/graph.json","events_json":"https://pith.science/api/pith-number/6UCR7T2OHSXYAJF7NLSZ27XSB7/events.json","paper":"https://pith.science/paper/6UCR7T2O"},"agent_actions":{"view_html":"https://pith.science/pith/6UCR7T2OHSXYAJF7NLSZ27XSB7","download_json":"https://pith.science/pith/6UCR7T2OHSXYAJF7NLSZ27XSB7.json","view_paper":"https://pith.science/paper/6UCR7T2O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.27122&json=true","fetch_graph":"https://pith.science/api/pith-number/6UCR7T2OHSXYAJF7NLSZ27XSB7/graph.json","fetch_events":"https://pith.science/api/pith-number/6UCR7T2OHSXYAJF7NLSZ27XSB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6UCR7T2OHSXYAJF7NLSZ27XSB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6UCR7T2OHSXYAJF7NLSZ27XSB7/action/storage_attestation","attest_author":"https://pith.science/pith/6UCR7T2OHSXYAJF7NLSZ27XSB7/action/author_attestation","sign_citation":"https://pith.science/pith/6UCR7T2OHSXYAJF7NLSZ27XSB7/action/citation_signature","submit_replication":"https://pith.science/pith/6UCR7T2OHSXYAJF7NLSZ27XSB7/action/replication_record"}},"created_at":"2026-06-30T01:17:38.863652+00:00","updated_at":"2026-06-30T01:17:38.863652+00:00"}