{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L52JKERBMJVGPQYYM3QC67OWO6","short_pith_number":"pith:L52JKERB","schema_version":"1.0","canonical_sha256":"5f74951221626a67c31866e02f7dd6778cf45ec4e8443000c9257d8d41e2f894","source":{"kind":"arxiv","id":"2602.11499","version":2},"attestation_state":"computed","paper":{"title":"What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","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","submitted_at":"2026-02-12T02:51:59Z","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"},"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":"2602.11499","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-12T02:51:59Z","cross_cats_sorted":[],"title_canon_sha256":"c71323618891323c184d05e3ea2b82c553d0aa16e94de4d3b4baab35a7853707","abstract_canon_sha256":"8999d348d52ae2119f98f653f3801babe590260a5d87515139199988c9ef6de8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:23.036894Z","signature_b64":"i80soA71FriqFlyiQm6icCJRqwK2Akzizk9glTbcQUv8t6Wge5NWN+pIAPjy/TFZIFg4sevduWi4o4l4BcHBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f74951221626a67c31866e02f7dd6778cf45ec4e8443000c9257d8d41e2f894","last_reissued_at":"2026-05-21T01:04:23.036136Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:23.036136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","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","submitted_at":"2026-02-12T02:51:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.11499","kind":"arxiv","version":2},"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/2602.11499/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":"2602.11499","created_at":"2026-05-21T01:04:23.036218+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.11499v2","created_at":"2026-05-21T01:04:23.036218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.11499","created_at":"2026-05-21T01:04:23.036218+00:00"},{"alias_kind":"pith_short_12","alias_value":"L52JKERBMJVG","created_at":"2026-05-21T01:04:23.036218+00:00"},{"alias_kind":"pith_short_16","alias_value":"L52JKERBMJVGPQYY","created_at":"2026-05-21T01:04:23.036218+00:00"},{"alias_kind":"pith_short_8","alias_value":"L52JKERB","created_at":"2026-05-21T01:04:23.036218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.15024","citing_title":"HiSem: Hierarchical Semantic Disentangling for Remote Sensing Image Change Captioning","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19386","citing_title":"Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval","ref_index":115,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20358","citing_title":"ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval","ref_index":111,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L52JKERBMJVGPQYYM3QC67OWO6","json":"https://pith.science/pith/L52JKERBMJVGPQYYM3QC67OWO6.json","graph_json":"https://pith.science/api/pith-number/L52JKERBMJVGPQYYM3QC67OWO6/graph.json","events_json":"https://pith.science/api/pith-number/L52JKERBMJVGPQYYM3QC67OWO6/events.json","paper":"https://pith.science/paper/L52JKERB"},"agent_actions":{"view_html":"https://pith.science/pith/L52JKERBMJVGPQYYM3QC67OWO6","download_json":"https://pith.science/pith/L52JKERBMJVGPQYYM3QC67OWO6.json","view_paper":"https://pith.science/paper/L52JKERB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.11499&json=true","fetch_graph":"https://pith.science/api/pith-number/L52JKERBMJVGPQYYM3QC67OWO6/graph.json","fetch_events":"https://pith.science/api/pith-number/L52JKERBMJVGPQYYM3QC67OWO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L52JKERBMJVGPQYYM3QC67OWO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L52JKERBMJVGPQYYM3QC67OWO6/action/storage_attestation","attest_author":"https://pith.science/pith/L52JKERBMJVGPQYYM3QC67OWO6/action/author_attestation","sign_citation":"https://pith.science/pith/L52JKERBMJVGPQYYM3QC67OWO6/action/citation_signature","submit_replication":"https://pith.science/pith/L52JKERBMJVGPQYYM3QC67OWO6/action/replication_record"}},"created_at":"2026-05-21T01:04:23.036218+00:00","updated_at":"2026-05-21T01:04:23.036218+00:00"}