{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7EXIAXALZMYVDFGXQIHR4PEKN6","short_pith_number":"pith:7EXIAXAL","schema_version":"1.0","canonical_sha256":"f92e805c0bcb315194d7820f1e3c8a6fbca3e418ea743cbcf9b787690cf38657","source":{"kind":"arxiv","id":"2605.27764","version":1},"attestation_state":"computed","paper":{"title":"Can Segmentation Models Understand the World? Towards Proactive Affordance Reasoning via Visual Chain-of-Thought","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hongmin Cai, Junli Gong, Weifeng Su, Yiu-ming Cheung, Yuchen Guo","submitted_at":"2026-05-26T23:26:52Z","abstract_excerpt":"Recent segmentation models couple large language models (LLMs) with mask decoders to ground complex language expressions into masks, yet their instructions remain target-referential: they describe, constrain, or imply the region to be segmented. However, in real-world embodied interaction, human instructions are often at the intent-level, which includes the desired outcome without naming the region that enables it. To bridge this gap, we introduce SegWorld, where the model reasons about the scene through a multi-level visual chain-of-thought (CoT) before committing to a mask. Before receiving "},"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":"2605.27764","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T23:26:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4ed3204d7abdd357f214946165a850fa78096c9d7301266389b1698cc6968982","abstract_canon_sha256":"6af87b485d0f70a742e20efbac7616b46d026fa9b860a4f02fe25186a2c0fccb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:48.306651Z","signature_b64":"1NfVfhpE6GK1Dse/Mt8yXfHswHcOa6v5U13BwXb6M9xV2Ge+BBp+78riULRh2PwCBNrQ5DXN1paa8eg2/xleAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f92e805c0bcb315194d7820f1e3c8a6fbca3e418ea743cbcf9b787690cf38657","last_reissued_at":"2026-05-28T01:04:48.306261Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:48.306261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Segmentation Models Understand the World? Towards Proactive Affordance Reasoning via Visual Chain-of-Thought","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hongmin Cai, Junli Gong, Weifeng Su, Yiu-ming Cheung, Yuchen Guo","submitted_at":"2026-05-26T23:26:52Z","abstract_excerpt":"Recent segmentation models couple large language models (LLMs) with mask decoders to ground complex language expressions into masks, yet their instructions remain target-referential: they describe, constrain, or imply the region to be segmented. However, in real-world embodied interaction, human instructions are often at the intent-level, which includes the desired outcome without naming the region that enables it. To bridge this gap, we introduce SegWorld, where the model reasons about the scene through a multi-level visual chain-of-thought (CoT) before committing to a mask. Before receiving "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27764","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/2605.27764/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":"2605.27764","created_at":"2026-05-28T01:04:48.306322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27764v1","created_at":"2026-05-28T01:04:48.306322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27764","created_at":"2026-05-28T01:04:48.306322+00:00"},{"alias_kind":"pith_short_12","alias_value":"7EXIAXALZMYV","created_at":"2026-05-28T01:04:48.306322+00:00"},{"alias_kind":"pith_short_16","alias_value":"7EXIAXALZMYVDFGX","created_at":"2026-05-28T01:04:48.306322+00:00"},{"alias_kind":"pith_short_8","alias_value":"7EXIAXAL","created_at":"2026-05-28T01:04:48.306322+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/7EXIAXALZMYVDFGXQIHR4PEKN6","json":"https://pith.science/pith/7EXIAXALZMYVDFGXQIHR4PEKN6.json","graph_json":"https://pith.science/api/pith-number/7EXIAXALZMYVDFGXQIHR4PEKN6/graph.json","events_json":"https://pith.science/api/pith-number/7EXIAXALZMYVDFGXQIHR4PEKN6/events.json","paper":"https://pith.science/paper/7EXIAXAL"},"agent_actions":{"view_html":"https://pith.science/pith/7EXIAXALZMYVDFGXQIHR4PEKN6","download_json":"https://pith.science/pith/7EXIAXALZMYVDFGXQIHR4PEKN6.json","view_paper":"https://pith.science/paper/7EXIAXAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27764&json=true","fetch_graph":"https://pith.science/api/pith-number/7EXIAXALZMYVDFGXQIHR4PEKN6/graph.json","fetch_events":"https://pith.science/api/pith-number/7EXIAXALZMYVDFGXQIHR4PEKN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7EXIAXALZMYVDFGXQIHR4PEKN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7EXIAXALZMYVDFGXQIHR4PEKN6/action/storage_attestation","attest_author":"https://pith.science/pith/7EXIAXALZMYVDFGXQIHR4PEKN6/action/author_attestation","sign_citation":"https://pith.science/pith/7EXIAXALZMYVDFGXQIHR4PEKN6/action/citation_signature","submit_replication":"https://pith.science/pith/7EXIAXALZMYVDFGXQIHR4PEKN6/action/replication_record"}},"created_at":"2026-05-28T01:04:48.306322+00:00","updated_at":"2026-05-28T01:04:48.306322+00:00"}