{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2VE6CKAAYSF57PTWWSWDLHTXSU","short_pith_number":"pith:2VE6CKAA","schema_version":"1.0","canonical_sha256":"d549e12800c48bdfbe76b4ac359e779516226460fbbf752170a9143846dc7074","source":{"kind":"arxiv","id":"2505.04831","version":2},"attestation_state":"computed","paper":{"title":"Steerable Scene Generation with Post Training and Inference-Time Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.RO","authors_text":"Hongkai Dai, Nicholas Pfaff, Russ Tedrake, Sergey Zakharov, Shun Iwase","submitted_at":"2025-05-07T22:07:42Z","abstract_excerpt":"Training robots in simulation requires diverse 3D scenes that reflect the specific challenges of downstream tasks. However, scenes that satisfy strict task requirements, such as high-clutter environments with plausible spatial arrangement, are rare and costly to curate manually. Instead, we generate large-scale scene data using procedural models that approximate realistic environments for robotic manipulation, and adapt it to task-specific goals. We do this by training a unified diffusion-based generative model that predicts which objects to place from a fixed asset library, along with their S"},"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":"2505.04831","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-07T22:07:42Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"f4c81783825707af97b415dcda9c7d3c1fea1bc96f907b7604502c5d6c61adc8","abstract_canon_sha256":"658feab9e21da77ccf415395b96524d8970e1d012c226b0797788cbbd6447171"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:13.956981Z","signature_b64":"y1zVp51COGKx0TqxrYc3onO0S+XWGF31uxeSGTHzcluHyxt/YyvJjwKSLB5hR5KmwL7/Qp8p3kHqB4fRCRyiBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d549e12800c48bdfbe76b4ac359e779516226460fbbf752170a9143846dc7074","last_reissued_at":"2026-07-05T11:59:13.956542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:13.956542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Steerable Scene Generation with Post Training and Inference-Time Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.RO","authors_text":"Hongkai Dai, Nicholas Pfaff, Russ Tedrake, Sergey Zakharov, Shun Iwase","submitted_at":"2025-05-07T22:07:42Z","abstract_excerpt":"Training robots in simulation requires diverse 3D scenes that reflect the specific challenges of downstream tasks. However, scenes that satisfy strict task requirements, such as high-clutter environments with plausible spatial arrangement, are rare and costly to curate manually. Instead, we generate large-scale scene data using procedural models that approximate realistic environments for robotic manipulation, and adapt it to task-specific goals. We do this by training a unified diffusion-based generative model that predicts which objects to place from a fixed asset library, along with their S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04831","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/2505.04831/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":"2505.04831","created_at":"2026-07-05T11:59:13.956600+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04831v2","created_at":"2026-07-05T11:59:13.956600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04831","created_at":"2026-07-05T11:59:13.956600+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VE6CKAAYSF5","created_at":"2026-07-05T11:59:13.956600+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VE6CKAAYSF57PTW","created_at":"2026-07-05T11:59:13.956600+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VE6CKAA","created_at":"2026-07-05T11:59:13.956600+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12365","citing_title":"Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16137","citing_title":"STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2VE6CKAAYSF57PTWWSWDLHTXSU","json":"https://pith.science/pith/2VE6CKAAYSF57PTWWSWDLHTXSU.json","graph_json":"https://pith.science/api/pith-number/2VE6CKAAYSF57PTWWSWDLHTXSU/graph.json","events_json":"https://pith.science/api/pith-number/2VE6CKAAYSF57PTWWSWDLHTXSU/events.json","paper":"https://pith.science/paper/2VE6CKAA"},"agent_actions":{"view_html":"https://pith.science/pith/2VE6CKAAYSF57PTWWSWDLHTXSU","download_json":"https://pith.science/pith/2VE6CKAAYSF57PTWWSWDLHTXSU.json","view_paper":"https://pith.science/paper/2VE6CKAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04831&json=true","fetch_graph":"https://pith.science/api/pith-number/2VE6CKAAYSF57PTWWSWDLHTXSU/graph.json","fetch_events":"https://pith.science/api/pith-number/2VE6CKAAYSF57PTWWSWDLHTXSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VE6CKAAYSF57PTWWSWDLHTXSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VE6CKAAYSF57PTWWSWDLHTXSU/action/storage_attestation","attest_author":"https://pith.science/pith/2VE6CKAAYSF57PTWWSWDLHTXSU/action/author_attestation","sign_citation":"https://pith.science/pith/2VE6CKAAYSF57PTWWSWDLHTXSU/action/citation_signature","submit_replication":"https://pith.science/pith/2VE6CKAAYSF57PTWWSWDLHTXSU/action/replication_record"}},"created_at":"2026-07-05T11:59:13.956600+00:00","updated_at":"2026-07-05T11:59:13.956600+00:00"}