{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5AZ5AZGN5KBZKWTXPGU6YT4BDW","short_pith_number":"pith:5AZ5AZGN","schema_version":"1.0","canonical_sha256":"e833d064cdea83955a7779a9ec4f811d9a4d612e15b5485b83389aab9e157635","source":{"kind":"arxiv","id":"2505.19306","version":1},"attestation_state":"computed","paper":{"title":"From Single Images to Motion Policies via Video-Generation Environment Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.GR","cs.LG"],"primary_cat":"cs.RO","authors_text":"Matthew Johnson-Roberson, Tianyi Zhang, Weiming Zhi, Ziyong Ma","submitted_at":"2025-05-25T20:30:25Z","abstract_excerpt":"Autonomous robots typically need to construct representations of their surroundings and adapt their motions to the geometry of their environment. Here, we tackle the problem of constructing a policy model for collision-free motion generation, consistent with the environment, from a single input RGB image. Extracting 3D structures from a single image often involves monocular depth estimation. Developments in depth estimation have given rise to large pre-trained models such as DepthAnything. However, using outputs of these models for downstream motion generation is challenging due to frustum-sha"},"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":"2505.19306","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-25T20:30:25Z","cross_cats_sorted":["cs.CV","cs.GR","cs.LG"],"title_canon_sha256":"1f5ef42f151538ea610de33ab63b0caf9a7c0b77b14dab8226e1ef695bfdb6ca","abstract_canon_sha256":"e93836e1254e000de46f61f0a30280e7dfee444656f887fc34b74180696bd1ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:27.941670Z","signature_b64":"heKPCS2mlJAM05/UOH7UCACZj0WMx9pTqO1JoVNrsHZMMOSz/aWnajq9YzkMhqQMvJlEPWEbbUaeN56wUDDhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e833d064cdea83955a7779a9ec4f811d9a4d612e15b5485b83389aab9e157635","last_reissued_at":"2026-07-05T11:09:27.941129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:27.941129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Single Images to Motion Policies via Video-Generation Environment Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.GR","cs.LG"],"primary_cat":"cs.RO","authors_text":"Matthew Johnson-Roberson, Tianyi Zhang, Weiming Zhi, Ziyong Ma","submitted_at":"2025-05-25T20:30:25Z","abstract_excerpt":"Autonomous robots typically need to construct representations of their surroundings and adapt their motions to the geometry of their environment. Here, we tackle the problem of constructing a policy model for collision-free motion generation, consistent with the environment, from a single input RGB image. Extracting 3D structures from a single image often involves monocular depth estimation. Developments in depth estimation have given rise to large pre-trained models such as DepthAnything. However, using outputs of these models for downstream motion generation is challenging due to frustum-sha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19306","kind":"arxiv","version":1},"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/2505.19306/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":"2505.19306","created_at":"2026-07-05T11:09:27.941191+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19306v1","created_at":"2026-07-05T11:09:27.941191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19306","created_at":"2026-07-05T11:09:27.941191+00:00"},{"alias_kind":"pith_short_12","alias_value":"5AZ5AZGN5KBZ","created_at":"2026-07-05T11:09:27.941191+00:00"},{"alias_kind":"pith_short_16","alias_value":"5AZ5AZGN5KBZKWTX","created_at":"2026-07-05T11:09:27.941191+00:00"},{"alias_kind":"pith_short_8","alias_value":"5AZ5AZGN","created_at":"2026-07-05T11:09:27.941191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5AZ5AZGN5KBZKWTXPGU6YT4BDW","json":"https://pith.science/pith/5AZ5AZGN5KBZKWTXPGU6YT4BDW.json","graph_json":"https://pith.science/api/pith-number/5AZ5AZGN5KBZKWTXPGU6YT4BDW/graph.json","events_json":"https://pith.science/api/pith-number/5AZ5AZGN5KBZKWTXPGU6YT4BDW/events.json","paper":"https://pith.science/paper/5AZ5AZGN"},"agent_actions":{"view_html":"https://pith.science/pith/5AZ5AZGN5KBZKWTXPGU6YT4BDW","download_json":"https://pith.science/pith/5AZ5AZGN5KBZKWTXPGU6YT4BDW.json","view_paper":"https://pith.science/paper/5AZ5AZGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19306&json=true","fetch_graph":"https://pith.science/api/pith-number/5AZ5AZGN5KBZKWTXPGU6YT4BDW/graph.json","fetch_events":"https://pith.science/api/pith-number/5AZ5AZGN5KBZKWTXPGU6YT4BDW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5AZ5AZGN5KBZKWTXPGU6YT4BDW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5AZ5AZGN5KBZKWTXPGU6YT4BDW/action/storage_attestation","attest_author":"https://pith.science/pith/5AZ5AZGN5KBZKWTXPGU6YT4BDW/action/author_attestation","sign_citation":"https://pith.science/pith/5AZ5AZGN5KBZKWTXPGU6YT4BDW/action/citation_signature","submit_replication":"https://pith.science/pith/5AZ5AZGN5KBZKWTXPGU6YT4BDW/action/replication_record"}},"created_at":"2026-07-05T11:09:27.941191+00:00","updated_at":"2026-07-05T11:09:27.941191+00:00"}