{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7EXIAXALZMYVDFGXQIHR4PEKN6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6af87b485d0f70a742e20efbac7616b46d026fa9b860a4f02fe25186a2c0fccb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T23:26:52Z","title_canon_sha256":"4ed3204d7abdd357f214946165a850fa78096c9d7301266389b1698cc6968982"},"schema_version":"1.0","source":{"id":"2605.27764","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27764","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27764v1","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27764","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"7EXIAXALZMYV","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"7EXIAXALZMYVDFGX","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"7EXIAXAL","created_at":"2026-05-28T01:04:48Z"}],"graph_snapshots":[{"event_id":"sha256:f2e0c341c05ea09884746cd1341117c26d8c6d525ff7c2324559c7e4b7f395f6","target":"graph","created_at":"2026-05-28T01:04:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.27764/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Hongmin Cai, Junli Gong, Weifeng Su, Yiu-ming Cheung, Yuchen Guo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T23:26:52Z","title":"Can Segmentation Models Understand the World? Towards Proactive Affordance Reasoning via Visual Chain-of-Thought"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27764","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8d551df5fd97d7957c3b0432c2c1d1a17716b3d4dff7f48ca8ddc84dc1e3ec2b","target":"record","created_at":"2026-05-28T01:04:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6af87b485d0f70a742e20efbac7616b46d026fa9b860a4f02fe25186a2c0fccb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T23:26:52Z","title_canon_sha256":"4ed3204d7abdd357f214946165a850fa78096c9d7301266389b1698cc6968982"},"schema_version":"1.0","source":{"id":"2605.27764","kind":"arxiv","version":1}},"canonical_sha256":"f92e805c0bcb315194d7820f1e3c8a6fbca3e418ea743cbcf9b787690cf38657","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f92e805c0bcb315194d7820f1e3c8a6fbca3e418ea743cbcf9b787690cf38657","first_computed_at":"2026-05-28T01:04:48.306261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:48.306261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1NfVfhpE6GK1Dse/Mt8yXfHswHcOa6v5U13BwXb6M9xV2Ge+BBp+78riULRh2PwCBNrQ5DXN1paa8eg2/xleAQ==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:48.306651Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27764","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d551df5fd97d7957c3b0432c2c1d1a17716b3d4dff7f48ca8ddc84dc1e3ec2b","sha256:f2e0c341c05ea09884746cd1341117c26d8c6d525ff7c2324559c7e4b7f395f6"],"state_sha256":"cc7450c3d079af9f40054e06f93284920c589ad191ce139fa162bf9ec67af222"}