{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6ZGLAVOK2XX53IXSY2DZKCYB3S","short_pith_number":"pith:6ZGLAVOK","schema_version":"1.0","canonical_sha256":"f64cb055cad5efdda2f2c687950b01dc8916a542911167ca85a532e3a5d4458f","source":{"kind":"arxiv","id":"2505.19611","version":1},"attestation_state":"computed","paper":{"title":"Align and Surpass Human Camouflaged Perception: Visual Refocus Reinforcement Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haihua Yang, Jiangning Zhang, Kai Wu, Ruolin Shen, Xiaobin Hu, Xiaoyu Sun, Xiaozhong Ji, Yijun He","submitted_at":"2025-05-26T07:27:18Z","abstract_excerpt":"Current multi-modal models exhibit a notable misalignment with the human visual system when identifying objects that are visually assimilated into the background. Our observations reveal that these multi-modal models cannot distinguish concealed objects, demonstrating an inability to emulate human cognitive processes which effectively utilize foreground-background similarity principles for visual analysis. To analyze this hidden human-model visual thinking discrepancy, we build a visual system that mimicks human visual camouflaged perception to progressively and iteratively `refocus' visual co"},"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":"2505.19611","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T07:27:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f429bc283d10bebd4ddc48a0d9ee9a1e1936157990cd680c248273c8fb405709","abstract_canon_sha256":"c77d6529dc7ebacbb8631741aca7f950f79ba19d281f47baeba6b782ffef5d06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:33.455195Z","signature_b64":"4rO/BC6GU96O5xxwDnCz2aqF7TGfrQEDjr7s3NtyQ/LunEZi7dgyDoUBK265yatVTiYl35FDxVn+gkOLY6NeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f64cb055cad5efdda2f2c687950b01dc8916a542911167ca85a532e3a5d4458f","last_reissued_at":"2026-07-05T11:09:33.454728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:33.454728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Align and Surpass Human Camouflaged Perception: Visual Refocus Reinforcement Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haihua Yang, Jiangning Zhang, Kai Wu, Ruolin Shen, Xiaobin Hu, Xiaoyu Sun, Xiaozhong Ji, Yijun He","submitted_at":"2025-05-26T07:27:18Z","abstract_excerpt":"Current multi-modal models exhibit a notable misalignment with the human visual system when identifying objects that are visually assimilated into the background. Our observations reveal that these multi-modal models cannot distinguish concealed objects, demonstrating an inability to emulate human cognitive processes which effectively utilize foreground-background similarity principles for visual analysis. To analyze this hidden human-model visual thinking discrepancy, we build a visual system that mimicks human visual camouflaged perception to progressively and iteratively `refocus' visual co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19611","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/2505.19611/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":"2505.19611","created_at":"2026-07-05T11:09:33.454785+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19611v1","created_at":"2026-07-05T11:09:33.454785+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19611","created_at":"2026-07-05T11:09:33.454785+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZGLAVOK2XX5","created_at":"2026-07-05T11:09:33.454785+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZGLAVOK2XX53IXS","created_at":"2026-07-05T11:09:33.454785+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZGLAVOK","created_at":"2026-07-05T11:09:33.454785+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21101","citing_title":"OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic Typography","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ZGLAVOK2XX53IXSY2DZKCYB3S","json":"https://pith.science/pith/6ZGLAVOK2XX53IXSY2DZKCYB3S.json","graph_json":"https://pith.science/api/pith-number/6ZGLAVOK2XX53IXSY2DZKCYB3S/graph.json","events_json":"https://pith.science/api/pith-number/6ZGLAVOK2XX53IXSY2DZKCYB3S/events.json","paper":"https://pith.science/paper/6ZGLAVOK"},"agent_actions":{"view_html":"https://pith.science/pith/6ZGLAVOK2XX53IXSY2DZKCYB3S","download_json":"https://pith.science/pith/6ZGLAVOK2XX53IXSY2DZKCYB3S.json","view_paper":"https://pith.science/paper/6ZGLAVOK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19611&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZGLAVOK2XX53IXSY2DZKCYB3S/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZGLAVOK2XX53IXSY2DZKCYB3S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZGLAVOK2XX53IXSY2DZKCYB3S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZGLAVOK2XX53IXSY2DZKCYB3S/action/storage_attestation","attest_author":"https://pith.science/pith/6ZGLAVOK2XX53IXSY2DZKCYB3S/action/author_attestation","sign_citation":"https://pith.science/pith/6ZGLAVOK2XX53IXSY2DZKCYB3S/action/citation_signature","submit_replication":"https://pith.science/pith/6ZGLAVOK2XX53IXSY2DZKCYB3S/action/replication_record"}},"created_at":"2026-07-05T11:09:33.454785+00:00","updated_at":"2026-07-05T11:09:33.454785+00:00"}