{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:L52JKERBMJVGPQYYM3QC67OWO6","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":"8999d348d52ae2119f98f653f3801babe590260a5d87515139199988c9ef6de8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-12T02:51:59Z","title_canon_sha256":"c71323618891323c184d05e3ea2b82c553d0aa16e94de4d3b4baab35a7853707"},"schema_version":"1.0","source":{"id":"2602.11499","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.11499","created_at":"2026-05-21T01:04:23Z"},{"alias_kind":"arxiv_version","alias_value":"2602.11499v2","created_at":"2026-05-21T01:04:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.11499","created_at":"2026-05-21T01:04:23Z"},{"alias_kind":"pith_short_12","alias_value":"L52JKERBMJVG","created_at":"2026-05-21T01:04:23Z"},{"alias_kind":"pith_short_16","alias_value":"L52JKERBMJVGPQYY","created_at":"2026-05-21T01:04:23Z"},{"alias_kind":"pith_short_8","alias_value":"L52JKERB","created_at":"2026-05-21T01:04:23Z"}],"graph_snapshots":[{"event_id":"sha256:1a8838f5df0471ecc0afc09a5941528a087485d4884b105f0b739c46c4dff0f0","target":"graph","created_at":"2026-05-21T01:04:23Z","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/2602.11499/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models have shown promising capabilities in bridging visual and textual reasoning, yet their reasoning capabilities in Open-Vocabulary Human-Object Interaction (OV-HOI) are limited by cross-modal hallucinations and limited viewpoints of images. To address this, we propose ImagineAgent, an agentic framework that integrates cognitive mapping, tool-augmented reinforcement learning (RL), and generative world modeling for robust OV-HOI understanding. Specifically, we first propose an innovative CoT dataset named hicodet-6K for supervised fine-tuning (SFT), which effectivel","authors_text":"Chengxuan Qian, Dapeng Zhang, Hongwei Yu, Jing Tang, Kejin Cui, Lei Sun, Rui Chen, Shuo Li, Xiangxiang Chu, Yue Wang, Yuyin Zhou, Zhenlong Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-12T02:51:59Z","title":"What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.11499","kind":"arxiv","version":2},"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":"sha256:9ee628d3f9fc54b8be4e30dd6b491ab6eac058206bc3df97ed34b47a204a3825","target":"record","created_at":"2026-05-21T01:04:23Z","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":"8999d348d52ae2119f98f653f3801babe590260a5d87515139199988c9ef6de8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-12T02:51:59Z","title_canon_sha256":"c71323618891323c184d05e3ea2b82c553d0aa16e94de4d3b4baab35a7853707"},"schema_version":"1.0","source":{"id":"2602.11499","kind":"arxiv","version":2}},"canonical_sha256":"5f74951221626a67c31866e02f7dd6778cf45ec4e8443000c9257d8d41e2f894","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f74951221626a67c31866e02f7dd6778cf45ec4e8443000c9257d8d41e2f894","first_computed_at":"2026-05-21T01:04:23.036136Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:23.036136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i80soA71FriqFlyiQm6icCJRqwK2Akzizk9glTbcQUv8t6Wge5NWN+pIAPjy/TFZIFg4sevduWi4o4l4BcHBBQ==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:23.036894Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.11499","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ee628d3f9fc54b8be4e30dd6b491ab6eac058206bc3df97ed34b47a204a3825","sha256:1a8838f5df0471ecc0afc09a5941528a087485d4884b105f0b739c46c4dff0f0"],"state_sha256":"752d2be6c0b5576379fd32d3e844251a138c5c410ecea2764c0645cd3247092a"}