{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OTMHSWI532VQ5PCPVOEHDUP6XL","short_pith_number":"pith:OTMHSWI5","schema_version":"1.0","canonical_sha256":"74d879591ddeab0ebc4fab8871d1febace639ce8c7d44698378c6bf7116b05cc","source":{"kind":"arxiv","id":"2607.29222","version":1},"attestation_state":"computed","paper":{"title":"Is It Time for the Renaissance of Salient Object Detection in the Era of MLLMs?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Cheng, Keren Fu, Qijun Zhao, Ronghao Xian, Wenzhuo Zhao, Xiuzhi Li, Yao Jiang, Zhao Gao, Zhongkuan Mao","submitted_at":"2026-07-31T09:54:23Z","abstract_excerpt":"The zero-shot capabilities of multimodal large language models (MLLMs) are pushing salient object detection (SOD) beyond task-specific supervision. To disentangle MLLMs beyond conventional mask-based evaluation, we decompose SOD into localization and segmentation, and re-engineer datasets with phrases, boxes, and attributes, establishing a diagnostic benchmark for MLLM saliency perception (SaliLLM). SaliLLM uncovers a striking capability mismatch: MLLMs outperform state-of-the-art (SOTA) methods in localization, yet remain substantially weaker in segmentation. Further analyses attribute this g"},"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":"2607.29222","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-31T09:54:23Z","cross_cats_sorted":[],"title_canon_sha256":"66848b24e8f83c54c3a618f60a4a287d81f1305f47081e0053637a0a0ca0b830","abstract_canon_sha256":"388cd1a318a33c1a82fd523acb794139e8aa6ed33e57ec36b6960eafe21f80d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:22:02.338589Z","signature_b64":"wAbQajMgE3LNScmJa+Lexb6glNdQSfdJeMN4Jb8kE8ozNFZ18w7dsyZK61rYgiVVorwjJzUhs9kp9GG84p18CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74d879591ddeab0ebc4fab8871d1febace639ce8c7d44698378c6bf7116b05cc","last_reissued_at":"2026-08-03T01:22:02.336820Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:22:02.336820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is It Time for the Renaissance of Salient Object Detection in the Era of MLLMs?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Cheng, Keren Fu, Qijun Zhao, Ronghao Xian, Wenzhuo Zhao, Xiuzhi Li, Yao Jiang, Zhao Gao, Zhongkuan Mao","submitted_at":"2026-07-31T09:54:23Z","abstract_excerpt":"The zero-shot capabilities of multimodal large language models (MLLMs) are pushing salient object detection (SOD) beyond task-specific supervision. To disentangle MLLMs beyond conventional mask-based evaluation, we decompose SOD into localization and segmentation, and re-engineer datasets with phrases, boxes, and attributes, establishing a diagnostic benchmark for MLLM saliency perception (SaliLLM). SaliLLM uncovers a striking capability mismatch: MLLMs outperform state-of-the-art (SOTA) methods in localization, yet remain substantially weaker in segmentation. Further analyses attribute this g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29222","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/2607.29222/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":"2607.29222","created_at":"2026-08-03T01:22:02.337858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.29222v1","created_at":"2026-08-03T01:22:02.337858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29222","created_at":"2026-08-03T01:22:02.337858+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTMHSWI532VQ","created_at":"2026-08-03T01:22:02.337858+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTMHSWI532VQ5PCP","created_at":"2026-08-03T01:22:02.337858+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTMHSWI5","created_at":"2026-08-03T01:22:02.337858+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/OTMHSWI532VQ5PCPVOEHDUP6XL","json":"https://pith.science/pith/OTMHSWI532VQ5PCPVOEHDUP6XL.json","graph_json":"https://pith.science/api/pith-number/OTMHSWI532VQ5PCPVOEHDUP6XL/graph.json","events_json":"https://pith.science/api/pith-number/OTMHSWI532VQ5PCPVOEHDUP6XL/events.json","paper":"https://pith.science/paper/OTMHSWI5"},"agent_actions":{"view_html":"https://pith.science/pith/OTMHSWI532VQ5PCPVOEHDUP6XL","download_json":"https://pith.science/pith/OTMHSWI532VQ5PCPVOEHDUP6XL.json","view_paper":"https://pith.science/paper/OTMHSWI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.29222&json=true","fetch_graph":"https://pith.science/api/pith-number/OTMHSWI532VQ5PCPVOEHDUP6XL/graph.json","fetch_events":"https://pith.science/api/pith-number/OTMHSWI532VQ5PCPVOEHDUP6XL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTMHSWI532VQ5PCPVOEHDUP6XL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTMHSWI532VQ5PCPVOEHDUP6XL/action/storage_attestation","attest_author":"https://pith.science/pith/OTMHSWI532VQ5PCPVOEHDUP6XL/action/author_attestation","sign_citation":"https://pith.science/pith/OTMHSWI532VQ5PCPVOEHDUP6XL/action/citation_signature","submit_replication":"https://pith.science/pith/OTMHSWI532VQ5PCPVOEHDUP6XL/action/replication_record"}},"created_at":"2026-08-03T01:22:02.337858+00:00","updated_at":"2026-08-03T01:22:02.337858+00:00"}