{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IT52B4DRXDW7SDMGURPBCMR73T","short_pith_number":"pith:IT52B4DR","schema_version":"1.0","canonical_sha256":"44fba0f071b8edf90d86a45e11323fdce6b08e0483430fd1c587deb08dcd33ca","source":{"kind":"arxiv","id":"2405.13751","version":1},"attestation_state":"computed","paper":{"title":"GameVLM: A Decision-making Framework for Robotic Task Planning Based on Visual Language Models and Zero-sum Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Aoran Mei, Guo-Niu Zhu, Jianhua Wang, Zhongxue Gan","submitted_at":"2024-05-22T15:37:28Z","abstract_excerpt":"With their prominent scene understanding and reasoning capabilities, pre-trained visual-language models (VLMs) such as GPT-4V have attracted increasing attention in robotic task planning. Compared with traditional task planning strategies, VLMs are strong in multimodal information parsing and code generation and show remarkable efficiency. Although VLMs demonstrate great potential in robotic task planning, they suffer from challenges like hallucination, semantic complexity, and limited context. To handle such issues, this paper proposes a multi-agent framework, i.e., GameVLM, to enhance the de"},"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":"2405.13751","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-05-22T15:37:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"413273c01a6726c9b313ff6425d72da4b33ce9e777580822504b33a8aada1c08","abstract_canon_sha256":"6bb852c57f5ba0b56465beda1de05b6ffa2f7c05f13f2e1099bdb140f7a4e552"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:06.563912Z","signature_b64":"IGDWHGA4ZsEyLQ5S0h4rdZ/vYGJiU7u6Igez1B9KGEqXfS1qioGt3wnsq/gsCaFudZmrtpl/OqLEx+0icc3eBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44fba0f071b8edf90d86a45e11323fdce6b08e0483430fd1c587deb08dcd33ca","last_reissued_at":"2026-07-05T08:22:06.563560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:06.563560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GameVLM: A Decision-making Framework for Robotic Task Planning Based on Visual Language Models and Zero-sum Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Aoran Mei, Guo-Niu Zhu, Jianhua Wang, Zhongxue Gan","submitted_at":"2024-05-22T15:37:28Z","abstract_excerpt":"With their prominent scene understanding and reasoning capabilities, pre-trained visual-language models (VLMs) such as GPT-4V have attracted increasing attention in robotic task planning. Compared with traditional task planning strategies, VLMs are strong in multimodal information parsing and code generation and show remarkable efficiency. Although VLMs demonstrate great potential in robotic task planning, they suffer from challenges like hallucination, semantic complexity, and limited context. To handle such issues, this paper proposes a multi-agent framework, i.e., GameVLM, to enhance the de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13751","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/2405.13751/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":"2405.13751","created_at":"2026-07-05T08:22:06.563620+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13751v1","created_at":"2026-07-05T08:22:06.563620+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13751","created_at":"2026-07-05T08:22:06.563620+00:00"},{"alias_kind":"pith_short_12","alias_value":"IT52B4DRXDW7","created_at":"2026-07-05T08:22:06.563620+00:00"},{"alias_kind":"pith_short_16","alias_value":"IT52B4DRXDW7SDMG","created_at":"2026-07-05T08:22:06.563620+00:00"},{"alias_kind":"pith_short_8","alias_value":"IT52B4DR","created_at":"2026-07-05T08:22:06.563620+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21652","citing_title":"PartInstruct: Part-level Instruction Following for Fine-grained Robot Manipulation","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IT52B4DRXDW7SDMGURPBCMR73T","json":"https://pith.science/pith/IT52B4DRXDW7SDMGURPBCMR73T.json","graph_json":"https://pith.science/api/pith-number/IT52B4DRXDW7SDMGURPBCMR73T/graph.json","events_json":"https://pith.science/api/pith-number/IT52B4DRXDW7SDMGURPBCMR73T/events.json","paper":"https://pith.science/paper/IT52B4DR"},"agent_actions":{"view_html":"https://pith.science/pith/IT52B4DRXDW7SDMGURPBCMR73T","download_json":"https://pith.science/pith/IT52B4DRXDW7SDMGURPBCMR73T.json","view_paper":"https://pith.science/paper/IT52B4DR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13751&json=true","fetch_graph":"https://pith.science/api/pith-number/IT52B4DRXDW7SDMGURPBCMR73T/graph.json","fetch_events":"https://pith.science/api/pith-number/IT52B4DRXDW7SDMGURPBCMR73T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IT52B4DRXDW7SDMGURPBCMR73T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IT52B4DRXDW7SDMGURPBCMR73T/action/storage_attestation","attest_author":"https://pith.science/pith/IT52B4DRXDW7SDMGURPBCMR73T/action/author_attestation","sign_citation":"https://pith.science/pith/IT52B4DRXDW7SDMGURPBCMR73T/action/citation_signature","submit_replication":"https://pith.science/pith/IT52B4DRXDW7SDMGURPBCMR73T/action/replication_record"}},"created_at":"2026-07-05T08:22:06.563620+00:00","updated_at":"2026-07-05T08:22:06.563620+00:00"}