{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R4RO2FJKOO6ZLKVRRTW6ZBEUEJ","short_pith_number":"pith:R4RO2FJK","schema_version":"1.0","canonical_sha256":"8f22ed152a73bd95aab18cedec84942245b48babd66f2462b898d76621484ae4","source":{"kind":"arxiv","id":"2603.00171","version":3},"attestation_state":"computed","paper":{"title":"LookWise: Knowing When and Where to Look for Fine-Grained Visual Reasoning in Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chengjun Xie, Hailong Huang, Haoxuan Che, Jie Zhang, Man Zhou, Xuanhua He, Xueheng Li, Yuxiang Shen, Zhenkun Gao","submitted_at":"2026-02-26T15:41:26Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) are shifting towards \"Thinking with Images\" by actively exploring image details. While effective, large-scale training is computationally expensive, which has spurred growing interest in lightweight, training-free solutions. However, existing training-free methods suffer from two flaws: perceptual redundancy from indiscriminate cropping, which increases computational cost and introduces noise; and a drift between semantic intent and spatial attention, which prevents accurate localization of user-focused regions. To address these challenges, we propose L"},"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":"2603.00171","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-26T15:41:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c1db13394f1436b0ebce806accfcc05626ffaa95dcdb96d75aa3f0048c872f5d","abstract_canon_sha256":"4ea4f3991ff9d86a188b9f038c6bc43a29312f43605a55d09b7362a305825bad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:44.281253Z","signature_b64":"cgDXWGLTo+7Crw3hzfdvG7x1z4ALh2lfvFxsDy5UPWozcX/+WuAaZGvkUdO8264ALUlbpEodzI1YQIZ/satlDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f22ed152a73bd95aab18cedec84942245b48babd66f2462b898d76621484ae4","last_reissued_at":"2026-06-02T01:03:44.280777Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:44.280777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LookWise: Knowing When and Where to Look for Fine-Grained Visual Reasoning in Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chengjun Xie, Hailong Huang, Haoxuan Che, Jie Zhang, Man Zhou, Xuanhua He, Xueheng Li, Yuxiang Shen, Zhenkun Gao","submitted_at":"2026-02-26T15:41:26Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) are shifting towards \"Thinking with Images\" by actively exploring image details. While effective, large-scale training is computationally expensive, which has spurred growing interest in lightweight, training-free solutions. However, existing training-free methods suffer from two flaws: perceptual redundancy from indiscriminate cropping, which increases computational cost and introduces noise; and a drift between semantic intent and spatial attention, which prevents accurate localization of user-focused regions. To address these challenges, we propose L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.00171","kind":"arxiv","version":3},"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/2603.00171/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":"2603.00171","created_at":"2026-06-02T01:03:44.280834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.00171v3","created_at":"2026-06-02T01:03:44.280834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.00171","created_at":"2026-06-02T01:03:44.280834+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4RO2FJKOO6Z","created_at":"2026-06-02T01:03:44.280834+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4RO2FJKOO6ZLKVR","created_at":"2026-06-02T01:03:44.280834+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4RO2FJK","created_at":"2026-06-02T01:03:44.280834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.11723","citing_title":"CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ","json":"https://pith.science/pith/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ.json","graph_json":"https://pith.science/api/pith-number/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ/graph.json","events_json":"https://pith.science/api/pith-number/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ/events.json","paper":"https://pith.science/paper/R4RO2FJK"},"agent_actions":{"view_html":"https://pith.science/pith/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ","download_json":"https://pith.science/pith/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ.json","view_paper":"https://pith.science/paper/R4RO2FJK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.00171&json=true","fetch_graph":"https://pith.science/api/pith-number/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ/action/storage_attestation","attest_author":"https://pith.science/pith/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ/action/author_attestation","sign_citation":"https://pith.science/pith/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ/action/citation_signature","submit_replication":"https://pith.science/pith/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ/action/replication_record"}},"created_at":"2026-06-02T01:03:44.280834+00:00","updated_at":"2026-06-02T01:03:44.280834+00:00"}