{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WATVSV6POF75O6EHVEJ4Y3U62L","short_pith_number":"pith:WATVSV6P","schema_version":"1.0","canonical_sha256":"b0275957cf717fd77887a913cc6e9ed2fb075d4f8b29a9d327abfb413848b9f2","source":{"kind":"arxiv","id":"2501.17015","version":2},"attestation_state":"computed","paper":{"title":"UniMM: A Unified Mixture Model Framework for Multi-Agent Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","cs.RO"],"primary_cat":"cs.AI","authors_text":"Haojian Lu, Kechun Xu, Lichao Huang, Longzhong Lin, Rong Xiong, Xuewu Lin, Yue Wang","submitted_at":"2025-01-28T15:26:25Z","abstract_excerpt":"Simulation plays a crucial role in assessing autonomous driving systems, where the generation of realistic multi-agent behaviors is a key aspect. In multi-agent simulation, the primary challenges include behavioral multimodality and closed-loop distributional shifts. In this study, we formulate a unified mixture model (UniMM) framework for generating multimodal agent behaviors, which can cover the mainstream methods including regression-based mixture models and discrete NTP models. Furthermore, we introduce a closed-loop sample generation approach tailored for mixture models to mitigate distri"},"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":"2501.17015","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-01-28T15:26:25Z","cross_cats_sorted":["cs.MA","cs.RO"],"title_canon_sha256":"8d68f7b68f080d5e7f8da45af59fc5bd505bb4132f87e0ed3a6e6668d8f7d450","abstract_canon_sha256":"2cc2deadba131fd81cfb6205b27c680410a1acb43d5a90c2c3d179c5ccaa1d3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:44.965193Z","signature_b64":"7I8BJuKWAVQK5YeNVcCwxnMEVEK+p1dvnmhLni1h+s1QKkU2pSj/SgYZ/+05L4r8NCoPIQNG2RcfEQLlGnhPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0275957cf717fd77887a913cc6e9ed2fb075d4f8b29a9d327abfb413848b9f2","last_reissued_at":"2026-06-19T16:12:44.964709Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:44.964709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniMM: A Unified Mixture Model Framework for Multi-Agent Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","cs.RO"],"primary_cat":"cs.AI","authors_text":"Haojian Lu, Kechun Xu, Lichao Huang, Longzhong Lin, Rong Xiong, Xuewu Lin, Yue Wang","submitted_at":"2025-01-28T15:26:25Z","abstract_excerpt":"Simulation plays a crucial role in assessing autonomous driving systems, where the generation of realistic multi-agent behaviors is a key aspect. In multi-agent simulation, the primary challenges include behavioral multimodality and closed-loop distributional shifts. In this study, we formulate a unified mixture model (UniMM) framework for generating multimodal agent behaviors, which can cover the mainstream methods including regression-based mixture models and discrete NTP models. Furthermore, we introduce a closed-loop sample generation approach tailored for mixture models to mitigate distri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17015","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/2501.17015/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":"2501.17015","created_at":"2026-06-19T16:12:44.964768+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.17015v2","created_at":"2026-06-19T16:12:44.964768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17015","created_at":"2026-06-19T16:12:44.964768+00:00"},{"alias_kind":"pith_short_12","alias_value":"WATVSV6POF75","created_at":"2026-06-19T16:12:44.964768+00:00"},{"alias_kind":"pith_short_16","alias_value":"WATVSV6POF75O6EH","created_at":"2026-06-19T16:12:44.964768+00:00"},{"alias_kind":"pith_short_8","alias_value":"WATVSV6P","created_at":"2026-06-19T16:12:44.964768+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.19033","citing_title":"RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2512.14735","citing_title":"PyFi: Toward Pyramid-like Financial Image Understanding for VLMs via Adversarial Agents","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2603.24155","citing_title":"Goal-Oriented Reactive Simulation for Closed-Loop Trajectory Prediction","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WATVSV6POF75O6EHVEJ4Y3U62L","json":"https://pith.science/pith/WATVSV6POF75O6EHVEJ4Y3U62L.json","graph_json":"https://pith.science/api/pith-number/WATVSV6POF75O6EHVEJ4Y3U62L/graph.json","events_json":"https://pith.science/api/pith-number/WATVSV6POF75O6EHVEJ4Y3U62L/events.json","paper":"https://pith.science/paper/WATVSV6P"},"agent_actions":{"view_html":"https://pith.science/pith/WATVSV6POF75O6EHVEJ4Y3U62L","download_json":"https://pith.science/pith/WATVSV6POF75O6EHVEJ4Y3U62L.json","view_paper":"https://pith.science/paper/WATVSV6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.17015&json=true","fetch_graph":"https://pith.science/api/pith-number/WATVSV6POF75O6EHVEJ4Y3U62L/graph.json","fetch_events":"https://pith.science/api/pith-number/WATVSV6POF75O6EHVEJ4Y3U62L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WATVSV6POF75O6EHVEJ4Y3U62L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WATVSV6POF75O6EHVEJ4Y3U62L/action/storage_attestation","attest_author":"https://pith.science/pith/WATVSV6POF75O6EHVEJ4Y3U62L/action/author_attestation","sign_citation":"https://pith.science/pith/WATVSV6POF75O6EHVEJ4Y3U62L/action/citation_signature","submit_replication":"https://pith.science/pith/WATVSV6POF75O6EHVEJ4Y3U62L/action/replication_record"}},"created_at":"2026-06-19T16:12:44.964768+00:00","updated_at":"2026-06-19T16:12:44.964768+00:00"}