{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:S5ZPW33MKJPEPRDJALIFMVMT5Q","short_pith_number":"pith:S5ZPW33M","schema_version":"1.0","canonical_sha256":"9772fb6f6c525e47c46902d0565593ec0360c5a54e1ae81a78069cc85464f87c","source":{"kind":"arxiv","id":"2605.28160","version":1},"attestation_state":"computed","paper":{"title":"Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiayi Ji, Qian Chen, Rongrong Ji, Rui Zhao, Wujin Sun, Xiaoshuai Sun, Yang Zhang, Yidong Chen","submitted_at":"2026-05-27T08:43:13Z","abstract_excerpt":"Existing multimodal reasoning approaches predominantly follow two paradigms: converting visual inputs into text prior to reasoning, or performing end-to-end reasoning within a unified vision-language representation space. Despite their empirical progress, both paradigms suffer from fundamental structural limitations. The former relies on static visual-to-text conversion, which tends to compress and lose fine-grained visual details. The latter is prone to linguistic dominance induced by joint optimization and attention mechanisms, leading to systematically weakened faithfulness to visual eviden"},"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":"2605.28160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T08:43:13Z","cross_cats_sorted":[],"title_canon_sha256":"6924fffca588709c936b47ee90e6bde719e7b769bae4108a065c8980aa80e270","abstract_canon_sha256":"e3deb449be1c18b12d80a5044b6a0a4eec8e6a009ce0cb91a2f722b5915718e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:00.788088Z","signature_b64":"sd+1dWJHKiLU5qegc01Bne7+AFQ430ITPYVY1YDc+nUX/PTm6xLO7lBLUitviRKbcX2BOp90mT2FPrOoygS7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9772fb6f6c525e47c46902d0565593ec0360c5a54e1ae81a78069cc85464f87c","last_reissued_at":"2026-05-28T01:05:00.787598Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:00.787598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiayi Ji, Qian Chen, Rongrong Ji, Rui Zhao, Wujin Sun, Xiaoshuai Sun, Yang Zhang, Yidong Chen","submitted_at":"2026-05-27T08:43:13Z","abstract_excerpt":"Existing multimodal reasoning approaches predominantly follow two paradigms: converting visual inputs into text prior to reasoning, or performing end-to-end reasoning within a unified vision-language representation space. Despite their empirical progress, both paradigms suffer from fundamental structural limitations. The former relies on static visual-to-text conversion, which tends to compress and lose fine-grained visual details. The latter is prone to linguistic dominance induced by joint optimization and attention mechanisms, leading to systematically weakened faithfulness to visual eviden"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28160","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/2605.28160/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":"2605.28160","created_at":"2026-05-28T01:05:00.787675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28160v1","created_at":"2026-05-28T01:05:00.787675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28160","created_at":"2026-05-28T01:05:00.787675+00:00"},{"alias_kind":"pith_short_12","alias_value":"S5ZPW33MKJPE","created_at":"2026-05-28T01:05:00.787675+00:00"},{"alias_kind":"pith_short_16","alias_value":"S5ZPW33MKJPEPRDJ","created_at":"2026-05-28T01:05:00.787675+00:00"},{"alias_kind":"pith_short_8","alias_value":"S5ZPW33M","created_at":"2026-05-28T01:05:00.787675+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/S5ZPW33MKJPEPRDJALIFMVMT5Q","json":"https://pith.science/pith/S5ZPW33MKJPEPRDJALIFMVMT5Q.json","graph_json":"https://pith.science/api/pith-number/S5ZPW33MKJPEPRDJALIFMVMT5Q/graph.json","events_json":"https://pith.science/api/pith-number/S5ZPW33MKJPEPRDJALIFMVMT5Q/events.json","paper":"https://pith.science/paper/S5ZPW33M"},"agent_actions":{"view_html":"https://pith.science/pith/S5ZPW33MKJPEPRDJALIFMVMT5Q","download_json":"https://pith.science/pith/S5ZPW33MKJPEPRDJALIFMVMT5Q.json","view_paper":"https://pith.science/paper/S5ZPW33M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28160&json=true","fetch_graph":"https://pith.science/api/pith-number/S5ZPW33MKJPEPRDJALIFMVMT5Q/graph.json","fetch_events":"https://pith.science/api/pith-number/S5ZPW33MKJPEPRDJALIFMVMT5Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S5ZPW33MKJPEPRDJALIFMVMT5Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S5ZPW33MKJPEPRDJALIFMVMT5Q/action/storage_attestation","attest_author":"https://pith.science/pith/S5ZPW33MKJPEPRDJALIFMVMT5Q/action/author_attestation","sign_citation":"https://pith.science/pith/S5ZPW33MKJPEPRDJALIFMVMT5Q/action/citation_signature","submit_replication":"https://pith.science/pith/S5ZPW33MKJPEPRDJALIFMVMT5Q/action/replication_record"}},"created_at":"2026-05-28T01:05:00.787675+00:00","updated_at":"2026-05-28T01:05:00.787675+00:00"}