{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V7XZNP5M4HG4K3ETSKBYRNDSL2","short_pith_number":"pith:V7XZNP5M","schema_version":"1.0","canonical_sha256":"afef96bface1cdc56c93928388b4725e82b63abb6e3f472f7e0329fcb379c38e","source":{"kind":"arxiv","id":"2411.19921","version":2},"attestation_state":"computed","paper":{"title":"SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.GR"],"primary_cat":"cs.CV","authors_text":"Jidong Mei, Jingbo Wang, Lei Yang, Liang Pan, Taku Komura, Wenjia Wang, Yifan Wu, Yuke Lou, Zhiyang Dou, Zhouyingcheng Liao","submitted_at":"2024-11-29T18:36:15Z","abstract_excerpt":"Simulating stylized human-scene interactions (HSI) in physical environments is a challenging yet fascinating task. Prior works emphasize long-term execution but fall short in achieving both diverse style and physical plausibility. To tackle this challenge, we introduce a novel hierarchical framework named SIMS that seamlessly bridges highlevel script-driven intent with a low-level control policy, enabling more expressive and diverse human-scene interactions. Specifically, we employ Large Language Models with Retrieval-Augmented Generation (RAG) to generate coherent and diverse long-form script"},"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":"2411.19921","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T18:36:15Z","cross_cats_sorted":["cs.AI","cs.CL","cs.GR"],"title_canon_sha256":"34131b07555c2c26a8092fe59794bb677e8ec6a706d0d74c8be1e2aa581d902a","abstract_canon_sha256":"7076f51ca950fd0b6a38dd2851302311f86ccab90aa935db6da0e1cc29842291"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:51.088396Z","signature_b64":"bPM4PPs7+Cvkxf48LCpxNUw8xBdOiFqxh8nnt27kpmGECWT9/Kjt1htUtycNUw7jPTzCgagEuxRdAFYYY72WDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afef96bface1cdc56c93928388b4725e82b63abb6e3f472f7e0329fcb379c38e","last_reissued_at":"2026-07-05T10:31:51.087875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:51.087875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.GR"],"primary_cat":"cs.CV","authors_text":"Jidong Mei, Jingbo Wang, Lei Yang, Liang Pan, Taku Komura, Wenjia Wang, Yifan Wu, Yuke Lou, Zhiyang Dou, Zhouyingcheng Liao","submitted_at":"2024-11-29T18:36:15Z","abstract_excerpt":"Simulating stylized human-scene interactions (HSI) in physical environments is a challenging yet fascinating task. Prior works emphasize long-term execution but fall short in achieving both diverse style and physical plausibility. To tackle this challenge, we introduce a novel hierarchical framework named SIMS that seamlessly bridges highlevel script-driven intent with a low-level control policy, enabling more expressive and diverse human-scene interactions. Specifically, we employ Large Language Models with Retrieval-Augmented Generation (RAG) to generate coherent and diverse long-form script"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19921","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/2411.19921/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":"2411.19921","created_at":"2026-07-05T10:31:51.087934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19921v2","created_at":"2026-07-05T10:31:51.087934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19921","created_at":"2026-07-05T10:31:51.087934+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7XZNP5M4HG4","created_at":"2026-07-05T10:31:51.087934+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7XZNP5M4HG4K3ET","created_at":"2026-07-05T10:31:51.087934+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7XZNP5M","created_at":"2026-07-05T10:31:51.087934+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04843","citing_title":"InfBaGel: Human-Object-Scene Interaction Generation with Dynamic Perception and Iterative Refinement","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V7XZNP5M4HG4K3ETSKBYRNDSL2","json":"https://pith.science/pith/V7XZNP5M4HG4K3ETSKBYRNDSL2.json","graph_json":"https://pith.science/api/pith-number/V7XZNP5M4HG4K3ETSKBYRNDSL2/graph.json","events_json":"https://pith.science/api/pith-number/V7XZNP5M4HG4K3ETSKBYRNDSL2/events.json","paper":"https://pith.science/paper/V7XZNP5M"},"agent_actions":{"view_html":"https://pith.science/pith/V7XZNP5M4HG4K3ETSKBYRNDSL2","download_json":"https://pith.science/pith/V7XZNP5M4HG4K3ETSKBYRNDSL2.json","view_paper":"https://pith.science/paper/V7XZNP5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19921&json=true","fetch_graph":"https://pith.science/api/pith-number/V7XZNP5M4HG4K3ETSKBYRNDSL2/graph.json","fetch_events":"https://pith.science/api/pith-number/V7XZNP5M4HG4K3ETSKBYRNDSL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7XZNP5M4HG4K3ETSKBYRNDSL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7XZNP5M4HG4K3ETSKBYRNDSL2/action/storage_attestation","attest_author":"https://pith.science/pith/V7XZNP5M4HG4K3ETSKBYRNDSL2/action/author_attestation","sign_citation":"https://pith.science/pith/V7XZNP5M4HG4K3ETSKBYRNDSL2/action/citation_signature","submit_replication":"https://pith.science/pith/V7XZNP5M4HG4K3ETSKBYRNDSL2/action/replication_record"}},"created_at":"2026-07-05T10:31:51.087934+00:00","updated_at":"2026-07-05T10:31:51.087934+00:00"}