{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M7M2MWYU76IOANR2EAANEWB3D3","short_pith_number":"pith:M7M2MWYU","schema_version":"1.0","canonical_sha256":"67d9a65b14ff90e0363a2000d2583b1ed3c24deaece6201c4ab9c332fa6c07e5","source":{"kind":"arxiv","id":"2508.14280","version":1},"attestation_state":"computed","paper":{"title":"Multi-Rationale Explainable Object Recognition via Contrastive Conditional Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Rasekh, Sepehr Kazemi Ranjbar, Simon Gottschalk","submitted_at":"2025-08-19T21:28:12Z","abstract_excerpt":"Explainable object recognition using vision-language models such as CLIP involves predicting accurate category labels supported by rationales that justify the decision-making process. Existing methods typically rely on prompt-based conditioning, which suffers from limitations in CLIP's text encoder and provides weak conditioning on explanatory structures. Additionally, prior datasets are often restricted to single, and frequently noisy, rationales that fail to capture the full diversity of discriminative image features. In this work, we introduce a multi-rationale explainable object recognitio"},"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":"2508.14280","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-19T21:28:12Z","cross_cats_sorted":[],"title_canon_sha256":"f3bb428e40e9af06079087fa01fd6e5f3cf4ef1f37ef430db16e7fa38dcb75d4","abstract_canon_sha256":"0fc4d88bc769ffd614221d17a7fdfd70d81cd267429752b7c12b8882b3dd0447"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:29.286991Z","signature_b64":"kIMo6jzTCHgOthgY6gfIZBOSFwD5ceS2SKo39PKca7hb9/6I0TMtrcMZL3AzpNjfd6QDL41qEMtVSu5Km7itCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67d9a65b14ff90e0363a2000d2583b1ed3c24deaece6201c4ab9c332fa6c07e5","last_reissued_at":"2026-07-05T11:56:29.286512Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:29.286512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Rationale Explainable Object Recognition via Contrastive Conditional Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Rasekh, Sepehr Kazemi Ranjbar, Simon Gottschalk","submitted_at":"2025-08-19T21:28:12Z","abstract_excerpt":"Explainable object recognition using vision-language models such as CLIP involves predicting accurate category labels supported by rationales that justify the decision-making process. Existing methods typically rely on prompt-based conditioning, which suffers from limitations in CLIP's text encoder and provides weak conditioning on explanatory structures. Additionally, prior datasets are often restricted to single, and frequently noisy, rationales that fail to capture the full diversity of discriminative image features. In this work, we introduce a multi-rationale explainable object recognitio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14280","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/2508.14280/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":"2508.14280","created_at":"2026-07-05T11:56:29.286574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.14280v1","created_at":"2026-07-05T11:56:29.286574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14280","created_at":"2026-07-05T11:56:29.286574+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7M2MWYU76IO","created_at":"2026-07-05T11:56:29.286574+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7M2MWYU76IOANR2","created_at":"2026-07-05T11:56:29.286574+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7M2MWYU","created_at":"2026-07-05T11:56:29.286574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01333","citing_title":"OralMLLM-Bench: Evaluating Cognitive Capabilities of Multimodal Large Language Models in Dental Practice","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M7M2MWYU76IOANR2EAANEWB3D3","json":"https://pith.science/pith/M7M2MWYU76IOANR2EAANEWB3D3.json","graph_json":"https://pith.science/api/pith-number/M7M2MWYU76IOANR2EAANEWB3D3/graph.json","events_json":"https://pith.science/api/pith-number/M7M2MWYU76IOANR2EAANEWB3D3/events.json","paper":"https://pith.science/paper/M7M2MWYU"},"agent_actions":{"view_html":"https://pith.science/pith/M7M2MWYU76IOANR2EAANEWB3D3","download_json":"https://pith.science/pith/M7M2MWYU76IOANR2EAANEWB3D3.json","view_paper":"https://pith.science/paper/M7M2MWYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.14280&json=true","fetch_graph":"https://pith.science/api/pith-number/M7M2MWYU76IOANR2EAANEWB3D3/graph.json","fetch_events":"https://pith.science/api/pith-number/M7M2MWYU76IOANR2EAANEWB3D3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7M2MWYU76IOANR2EAANEWB3D3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7M2MWYU76IOANR2EAANEWB3D3/action/storage_attestation","attest_author":"https://pith.science/pith/M7M2MWYU76IOANR2EAANEWB3D3/action/author_attestation","sign_citation":"https://pith.science/pith/M7M2MWYU76IOANR2EAANEWB3D3/action/citation_signature","submit_replication":"https://pith.science/pith/M7M2MWYU76IOANR2EAANEWB3D3/action/replication_record"}},"created_at":"2026-07-05T11:56:29.286574+00:00","updated_at":"2026-07-05T11:56:29.286574+00:00"}