{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WM2XUGJ5Y4EMXKO2YFDTMG7RGX","short_pith_number":"pith:WM2XUGJ5","schema_version":"1.0","canonical_sha256":"b3357a193dc708cba9dac147361bf135dca9b6a0ac8bde6613ef95de03c9dfaa","source":{"kind":"arxiv","id":"2507.07445","version":3},"attestation_state":"computed","paper":{"title":"StarDojo: Benchmarking Open-Ended Behaviors of Agentic Multimodal LLMs in Production-Living Simulations with Stardew Valley","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo An, Changjiu Jiang, Jiageng Li, Mingcong Lei, Weihao Tan, Xinrun Wang, Yitian Hong, Yu Duan","submitted_at":"2025-07-10T05:48:28Z","abstract_excerpt":"Autonomous agents navigating human society must master both production activities and social interactions, yet existing benchmarks rarely evaluate these skills simultaneously. To bridge this gap, we introduce StarDojo, a novel benchmark based on Stardew Valley, designed to assess AI agents in open-ended production-living simulations. In StarDojo, agents are tasked to perform essential livelihood activities such as farming and crafting, while simultaneously engaging in social interactions to establish relationships within a vibrant community. StarDojo features 1,000 meticulously curated tasks a"},"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":"2507.07445","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-10T05:48:28Z","cross_cats_sorted":[],"title_canon_sha256":"7dd9ae9163fd5269b7a8bbdcc77e7a3afa4a64fdffb7c69374e7ad4a47767008","abstract_canon_sha256":"c5ca8d9e50590533631bf376efe4124b4111a559a0dba92a9543e7fcf061234d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:24.639097Z","signature_b64":"3u6jKTNaY3+hdlT2nU9lQpUeVQmjej1U0+jsQa6U5wWSgkzEegLa8oUKH7YNnOSAnrodJ4mL9Hpn6XnpqTV1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3357a193dc708cba9dac147361bf135dca9b6a0ac8bde6613ef95de03c9dfaa","last_reissued_at":"2026-06-30T01:17:24.638486Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:24.638486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StarDojo: Benchmarking Open-Ended Behaviors of Agentic Multimodal LLMs in Production-Living Simulations with Stardew Valley","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo An, Changjiu Jiang, Jiageng Li, Mingcong Lei, Weihao Tan, Xinrun Wang, Yitian Hong, Yu Duan","submitted_at":"2025-07-10T05:48:28Z","abstract_excerpt":"Autonomous agents navigating human society must master both production activities and social interactions, yet existing benchmarks rarely evaluate these skills simultaneously. To bridge this gap, we introduce StarDojo, a novel benchmark based on Stardew Valley, designed to assess AI agents in open-ended production-living simulations. In StarDojo, agents are tasked to perform essential livelihood activities such as farming and crafting, while simultaneously engaging in social interactions to establish relationships within a vibrant community. StarDojo features 1,000 meticulously curated tasks a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07445","kind":"arxiv","version":3},"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/2507.07445/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":"2507.07445","created_at":"2026-06-30T01:17:24.638552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07445v3","created_at":"2026-06-30T01:17:24.638552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07445","created_at":"2026-06-30T01:17:24.638552+00:00"},{"alias_kind":"pith_short_12","alias_value":"WM2XUGJ5Y4EM","created_at":"2026-06-30T01:17:24.638552+00:00"},{"alias_kind":"pith_short_16","alias_value":"WM2XUGJ5Y4EMXKO2","created_at":"2026-06-30T01:17:24.638552+00:00"},{"alias_kind":"pith_short_8","alias_value":"WM2XUGJ5","created_at":"2026-06-30T01:17:24.638552+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2602.18600","citing_title":"MapTab: Are MLLMs Ready for Multi-Criteria Route Planning in Heterogeneous Graphs?","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18636","citing_title":"SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2602.18600","citing_title":"MapTab: Are MLLMs Ready for Multi-Criteria Route Planning in Heterogeneous Graphs?","ref_index":68,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WM2XUGJ5Y4EMXKO2YFDTMG7RGX","json":"https://pith.science/pith/WM2XUGJ5Y4EMXKO2YFDTMG7RGX.json","graph_json":"https://pith.science/api/pith-number/WM2XUGJ5Y4EMXKO2YFDTMG7RGX/graph.json","events_json":"https://pith.science/api/pith-number/WM2XUGJ5Y4EMXKO2YFDTMG7RGX/events.json","paper":"https://pith.science/paper/WM2XUGJ5"},"agent_actions":{"view_html":"https://pith.science/pith/WM2XUGJ5Y4EMXKO2YFDTMG7RGX","download_json":"https://pith.science/pith/WM2XUGJ5Y4EMXKO2YFDTMG7RGX.json","view_paper":"https://pith.science/paper/WM2XUGJ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07445&json=true","fetch_graph":"https://pith.science/api/pith-number/WM2XUGJ5Y4EMXKO2YFDTMG7RGX/graph.json","fetch_events":"https://pith.science/api/pith-number/WM2XUGJ5Y4EMXKO2YFDTMG7RGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WM2XUGJ5Y4EMXKO2YFDTMG7RGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WM2XUGJ5Y4EMXKO2YFDTMG7RGX/action/storage_attestation","attest_author":"https://pith.science/pith/WM2XUGJ5Y4EMXKO2YFDTMG7RGX/action/author_attestation","sign_citation":"https://pith.science/pith/WM2XUGJ5Y4EMXKO2YFDTMG7RGX/action/citation_signature","submit_replication":"https://pith.science/pith/WM2XUGJ5Y4EMXKO2YFDTMG7RGX/action/replication_record"}},"created_at":"2026-06-30T01:17:24.638552+00:00","updated_at":"2026-06-30T01:17:24.638552+00:00"}