{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N3FOYMIVJLOXW2XMSYQQZ2YO46","short_pith_number":"pith:N3FOYMIV","schema_version":"1.0","canonical_sha256":"6ecaec31154add7b6aec96210ceb0ee78310ffa6912758cd0260b32c3e33b3d1","source":{"kind":"arxiv","id":"2601.08454","version":2},"attestation_state":"computed","paper":{"title":"Real2Sim via Active Perception with Behavior Trees Automatically Generated by VLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alessandro Adami, Pietro Falco, Ruggero Carli, Sebastian Zudaire","submitted_at":"2026-01-13T11:28:46Z","abstract_excerpt":"Constructing physically accurate simulation environments (Real2Sim) traditionally relies on manual system identification or rigid, exhaustive exploration routines. These task-agnostic pipelines often fail to leverage semantic scene context, leading to redundant physical interactions and inefficient data acquisition. In this paper, we present an autonomous, intent-driven Real2Sim framework that leverages Vision-Language Models (VLMs) for Semantic Task Decomposition. Given a high-level natural language request, an incomplete simulation description, and a visual observation, the framework autonom"},"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":"2601.08454","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-01-13T11:28:46Z","cross_cats_sorted":[],"title_canon_sha256":"8e70a129adb1f7ba100e80a15736524a4366b0f01547a7932d3553ab6f9678da","abstract_canon_sha256":"3d61c820c568de3915e49717309e864cb737fded091917b1d933f8cccc5d9a8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:02.156392Z","signature_b64":"ZtqByvNhaafSbwOtTxPbrM0ySaEIYCUO8/BuZtcwYC74NrH4tWtdiGvD5cqOEek1CQ4cqd3k3wS/iJdbp7NjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ecaec31154add7b6aec96210ceb0ee78310ffa6912758cd0260b32c3e33b3d1","last_reissued_at":"2026-05-20T00:03:02.155588Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:02.155588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real2Sim via Active Perception with Behavior Trees Automatically Generated by VLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alessandro Adami, Pietro Falco, Ruggero Carli, Sebastian Zudaire","submitted_at":"2026-01-13T11:28:46Z","abstract_excerpt":"Constructing physically accurate simulation environments (Real2Sim) traditionally relies on manual system identification or rigid, exhaustive exploration routines. These task-agnostic pipelines often fail to leverage semantic scene context, leading to redundant physical interactions and inefficient data acquisition. In this paper, we present an autonomous, intent-driven Real2Sim framework that leverages Vision-Language Models (VLMs) for Semantic Task Decomposition. Given a high-level natural language request, an incomplete simulation description, and a visual observation, the framework autonom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.08454","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/2601.08454/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":"2601.08454","created_at":"2026-05-20T00:03:02.155725+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.08454v2","created_at":"2026-05-20T00:03:02.155725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.08454","created_at":"2026-05-20T00:03:02.155725+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3FOYMIVJLOX","created_at":"2026-05-20T00:03:02.155725+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3FOYMIVJLOXW2XM","created_at":"2026-05-20T00:03:02.155725+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3FOYMIV","created_at":"2026-05-20T00:03:02.155725+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2604.02812","citing_title":"Learning Structured Robot Policies from Vision-Language Models via Synthetic Neuro-Symbolic Supervision","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02812","citing_title":"Learning Structured Robot Policies from Vision-Language Models via Synthetic Neuro-Symbolic Supervision","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N3FOYMIVJLOXW2XMSYQQZ2YO46","json":"https://pith.science/pith/N3FOYMIVJLOXW2XMSYQQZ2YO46.json","graph_json":"https://pith.science/api/pith-number/N3FOYMIVJLOXW2XMSYQQZ2YO46/graph.json","events_json":"https://pith.science/api/pith-number/N3FOYMIVJLOXW2XMSYQQZ2YO46/events.json","paper":"https://pith.science/paper/N3FOYMIV"},"agent_actions":{"view_html":"https://pith.science/pith/N3FOYMIVJLOXW2XMSYQQZ2YO46","download_json":"https://pith.science/pith/N3FOYMIVJLOXW2XMSYQQZ2YO46.json","view_paper":"https://pith.science/paper/N3FOYMIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.08454&json=true","fetch_graph":"https://pith.science/api/pith-number/N3FOYMIVJLOXW2XMSYQQZ2YO46/graph.json","fetch_events":"https://pith.science/api/pith-number/N3FOYMIVJLOXW2XMSYQQZ2YO46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3FOYMIVJLOXW2XMSYQQZ2YO46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3FOYMIVJLOXW2XMSYQQZ2YO46/action/storage_attestation","attest_author":"https://pith.science/pith/N3FOYMIVJLOXW2XMSYQQZ2YO46/action/author_attestation","sign_citation":"https://pith.science/pith/N3FOYMIVJLOXW2XMSYQQZ2YO46/action/citation_signature","submit_replication":"https://pith.science/pith/N3FOYMIVJLOXW2XMSYQQZ2YO46/action/replication_record"}},"created_at":"2026-05-20T00:03:02.155725+00:00","updated_at":"2026-05-20T00:03:02.155725+00:00"}