{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QE3AKRGFX7NBPMVEHY5QNA5W4O","short_pith_number":"pith:QE3AKRGF","schema_version":"1.0","canonical_sha256":"81360544c5bfda17b2a43e3b0683b6e393badd0ee4ec20b613ae38420b84b1a8","source":{"kind":"arxiv","id":"2606.26794","version":1},"attestation_state":"computed","paper":{"title":"ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Binzhu Xie, Jamal Bentahar, Mubarak Shah, Muzammal Naseer, Naufal Suryanto, Naveed Akhtar, Shi Qiu, Sicheng Zhang","submitted_at":"2026-06-25T09:27:54Z","abstract_excerpt":"CLIP and its variants are widely adopted visual backbones in multimodal systems, but their pretraining remains dominated by descriptive image-text alignment. As downstream applications increasingly demand visually grounded commonsense inference and compositional reasoning, it remains unclear whether CLIP-style encoders can support such reasoning without architectural changes. To address this, we present ReasonCLIP-58M, a continual pretraining framework that integrates large-scale reasoning supervision into CLIP-style models through our two-stage strategy, which progressively integrates reasoni"},"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":"2606.26794","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T09:27:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"44590efff6c098405eceb1dd6adc0d62533b85aadac18b91e9a1be6a2a2a5a56","abstract_canon_sha256":"0d651bb0ebebef9639a0cdc814ebe55082566f763402a3c27a39dc423ab35cf3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:59.913453Z","signature_b64":"C5mn98nwbV+SqoNSzTJrxrHnxe8A9yXtnHni8QnRwqU5+3gQNKSKRzUZYbnYhClmrZuDXCCVnmondsF9k2L0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81360544c5bfda17b2a43e3b0683b6e393badd0ee4ec20b613ae38420b84b1a8","last_reissued_at":"2026-06-26T01:15:59.913066Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:59.913066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Binzhu Xie, Jamal Bentahar, Mubarak Shah, Muzammal Naseer, Naufal Suryanto, Naveed Akhtar, Shi Qiu, Sicheng Zhang","submitted_at":"2026-06-25T09:27:54Z","abstract_excerpt":"CLIP and its variants are widely adopted visual backbones in multimodal systems, but their pretraining remains dominated by descriptive image-text alignment. As downstream applications increasingly demand visually grounded commonsense inference and compositional reasoning, it remains unclear whether CLIP-style encoders can support such reasoning without architectural changes. To address this, we present ReasonCLIP-58M, a continual pretraining framework that integrates large-scale reasoning supervision into CLIP-style models through our two-stage strategy, which progressively integrates reasoni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26794","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/2606.26794/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":"2606.26794","created_at":"2026-06-26T01:15:59.913116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26794v1","created_at":"2026-06-26T01:15:59.913116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26794","created_at":"2026-06-26T01:15:59.913116+00:00"},{"alias_kind":"pith_short_12","alias_value":"QE3AKRGFX7NB","created_at":"2026-06-26T01:15:59.913116+00:00"},{"alias_kind":"pith_short_16","alias_value":"QE3AKRGFX7NBPMVE","created_at":"2026-06-26T01:15:59.913116+00:00"},{"alias_kind":"pith_short_8","alias_value":"QE3AKRGF","created_at":"2026-06-26T01:15:59.913116+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/QE3AKRGFX7NBPMVEHY5QNA5W4O","json":"https://pith.science/pith/QE3AKRGFX7NBPMVEHY5QNA5W4O.json","graph_json":"https://pith.science/api/pith-number/QE3AKRGFX7NBPMVEHY5QNA5W4O/graph.json","events_json":"https://pith.science/api/pith-number/QE3AKRGFX7NBPMVEHY5QNA5W4O/events.json","paper":"https://pith.science/paper/QE3AKRGF"},"agent_actions":{"view_html":"https://pith.science/pith/QE3AKRGFX7NBPMVEHY5QNA5W4O","download_json":"https://pith.science/pith/QE3AKRGFX7NBPMVEHY5QNA5W4O.json","view_paper":"https://pith.science/paper/QE3AKRGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26794&json=true","fetch_graph":"https://pith.science/api/pith-number/QE3AKRGFX7NBPMVEHY5QNA5W4O/graph.json","fetch_events":"https://pith.science/api/pith-number/QE3AKRGFX7NBPMVEHY5QNA5W4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QE3AKRGFX7NBPMVEHY5QNA5W4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QE3AKRGFX7NBPMVEHY5QNA5W4O/action/storage_attestation","attest_author":"https://pith.science/pith/QE3AKRGFX7NBPMVEHY5QNA5W4O/action/author_attestation","sign_citation":"https://pith.science/pith/QE3AKRGFX7NBPMVEHY5QNA5W4O/action/citation_signature","submit_replication":"https://pith.science/pith/QE3AKRGFX7NBPMVEHY5QNA5W4O/action/replication_record"}},"created_at":"2026-06-26T01:15:59.913116+00:00","updated_at":"2026-06-26T01:15:59.913116+00:00"}