{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6UCR7T2OHSXYAJF7NLSZ27XSB7","short_pith_number":"pith:6UCR7T2O","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"},"canonical_sha256":"f5051fcf4e3caf8024bf6ae59d7ef20fea6012e959391e00346c7b3305120a6a","source":{"kind":"arxiv","id":"2604.27122","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.27122","created_at":"2026-06-30T01:17:38Z"},{"alias_kind":"arxiv_version","alias_value":"2604.27122v2","created_at":"2026-06-30T01:17:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27122","created_at":"2026-06-30T01:17:38Z"},{"alias_kind":"pith_short_12","alias_value":"6UCR7T2OHSXY","created_at":"2026-06-30T01:17:38Z"},{"alias_kind":"pith_short_16","alias_value":"6UCR7T2OHSXYAJF7","created_at":"2026-06-30T01:17:38Z"},{"alias_kind":"pith_short_8","alias_value":"6UCR7T2O","created_at":"2026-06-30T01:17:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6UCR7T2OHSXYAJF7NLSZ27XSB7","target":"record","payload":{"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"},"canonical_sha256":"f5051fcf4e3caf8024bf6ae59d7ef20fea6012e959391e00346c7b3305120a6a","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"},"source_kind":"arxiv","source_id":"2604.27122","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T01:17:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M0WwjeNGvnRsibvC2lMf4riBGJjLwtmQAjpuxT9oVjsr4Wj5GnU8449p6ISCp+13JS+BwP/AO15jNgX1/EZmCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T01:45:04.717329Z"},"content_sha256":"2d194570c57bf10989cfbe047e477a67d7688ff3e3233d7fb8754db5e9ce88d6","schema_version":"1.0","event_id":"sha256:2d194570c57bf10989cfbe047e477a67d7688ff3e3233d7fb8754db5e9ce88d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6UCR7T2OHSXYAJF7NLSZ27XSB7","target":"graph","payload":{"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"},"verdict_id":"41d31c4f-1c71-4e4f-97ea-ca8d472c4539"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T01:17:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1O738OevXKw7gGvQh0oGNFDglFkGso+aKzeisT1ofjIbFdzidIMdNQhlxkSsBHgAJteOTO+2jC9SeLWy6ZsCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T01:45:04.717810Z"},"content_sha256":"5a718ed6e181c508868e3bdeb4c9059e833d220ef5851bfdc050fb76d1f20215","schema_version":"1.0","event_id":"sha256:5a718ed6e181c508868e3bdeb4c9059e833d220ef5851bfdc050fb76d1f20215"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6UCR7T2OHSXYAJF7NLSZ27XSB7/bundle.json","state_url":"https://pith.science/pith/6UCR7T2OHSXYAJF7NLSZ27XSB7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6UCR7T2OHSXYAJF7NLSZ27XSB7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-05T01:45:04Z","links":{"resolver":"https://pith.science/pith/6UCR7T2OHSXYAJF7NLSZ27XSB7","bundle":"https://pith.science/pith/6UCR7T2OHSXYAJF7NLSZ27XSB7/bundle.json","state":"https://pith.science/pith/6UCR7T2OHSXYAJF7NLSZ27XSB7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6UCR7T2OHSXYAJF7NLSZ27XSB7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6UCR7T2OHSXYAJF7NLSZ27XSB7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7582f3912c9af52ceb054f810bc17d1ba8e1310e8a3323872b2231c289f839f4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-29T19:18:36Z","title_canon_sha256":"48e6389300ec305dfb56b2519377797ca9f1e495f92af30107b86de1d01cbe23"},"schema_version":"1.0","source":{"id":"2604.27122","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.27122","created_at":"2026-06-30T01:17:38Z"},{"alias_kind":"arxiv_version","alias_value":"2604.27122v2","created_at":"2026-06-30T01:17:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.27122","created_at":"2026-06-30T01:17:38Z"},{"alias_kind":"pith_short_12","alias_value":"6UCR7T2OHSXY","created_at":"2026-06-30T01:17:38Z"},{"alias_kind":"pith_short_16","alias_value":"6UCR7T2OHSXYAJF7","created_at":"2026-06-30T01:17:38Z"},{"alias_kind":"pith_short_8","alias_value":"6UCR7T2O","created_at":"2026-06-30T01:17:38Z"}],"graph_snapshots":[{"event_id":"sha256:5a718ed6e181c508868e3bdeb4c9059e833d220ef5851bfdc050fb76d1f20215","target":"graph","created_at":"2026-06-30T01:17:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"InterPartAbility adds text-guided part matching and constrained attention to produce grounded explanations for text-to-image person re-identification."}],"snapshot_sha256":"fd025ce786d0f9c4ececfdb396ee0f8a9e3a8bceac8c61bc052a49d30751550c"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2604.27122/integrity.json","findings":[],"snapshot_sha256":"84072496d4463b0677dc00e59a503628e24a4f9f400a6f2c69d38bc4704c6695","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aryan Shukla, Eric Granger, Maguelonne Heritier, Rajarshi Bhattacharya, Shakeeb Murtaza","cross_cats":[],"headline":"InterPartAbility adds text-guided part matching and constrained attention to produce grounded explanations for text-to-image person re-identification.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-29T19:18:36Z","title":"InterPartAbility: Phrase-Region Grounding for Interpretable Text-to-Image Person Re-Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.27122","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-07T09:25:00.195583Z","id":"41d31c4f-1c71-4e4f-97ea-ca8d472c4539","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"InterPartAbility adds text-guided part matching and constrained attention to produce grounded explanations for text-to-image person re-identification.","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.","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."}},"verdict_id":"41d31c4f-1c71-4e4f-97ea-ca8d472c4539"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2d194570c57bf10989cfbe047e477a67d7688ff3e3233d7fb8754db5e9ce88d6","target":"record","created_at":"2026-06-30T01:17:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7582f3912c9af52ceb054f810bc17d1ba8e1310e8a3323872b2231c289f839f4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-29T19:18:36Z","title_canon_sha256":"48e6389300ec305dfb56b2519377797ca9f1e495f92af30107b86de1d01cbe23"},"schema_version":"1.0","source":{"id":"2604.27122","kind":"arxiv","version":2}},"canonical_sha256":"f5051fcf4e3caf8024bf6ae59d7ef20fea6012e959391e00346c7b3305120a6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5051fcf4e3caf8024bf6ae59d7ef20fea6012e959391e00346c7b3305120a6a","first_computed_at":"2026-06-30T01:17:38.863579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:17:38.863579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DsVyKAnmNfIu8NfAf2EoDqFAsY0seT1G6YgkRj4nYNeNUZOjIPR9tzJ2uZQS2uBGKUOJZXeRHv9gnExwf00xBg==","signature_status":"signed_v1","signed_at":"2026-06-30T01:17:38.864176Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.27122","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d194570c57bf10989cfbe047e477a67d7688ff3e3233d7fb8754db5e9ce88d6","sha256:5a718ed6e181c508868e3bdeb4c9059e833d220ef5851bfdc050fb76d1f20215"],"state_sha256":"a2d102efcccd3f3e7b50edad78d00c9b781b9f6f64d4e4c109e07e4e9801155d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pql67RhmUy7n5EB2/z5Jx43QUblsEEU0Rt8NlrIMZiMWVZVj2OtmsjsBd5quapNAMkXH7W2S8E8wIUSZuksFBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T01:45:04.720158Z","bundle_sha256":"8d7c2b0fffd718c39ea885d81e56c8cc3423b3d91236dc1b5527eb401407088a"}}