{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZHWSGPLPTFMCIQ4OONFHD2O2F3","short_pith_number":"pith:ZHWSGPLP","schema_version":"1.0","canonical_sha256":"c9ed233d6f995824438e734a71e9da2ecaeeb016cd47a92107b7022ecfefdbff","source":{"kind":"arxiv","id":"2505.12428","version":1},"attestation_state":"computed","paper":{"title":"Depth Transfer: Learning to See Like a Simulator for Real-World Drone Navigation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Christophe de Wagter, Guido C. H. E de Croon, Hang Yu","submitted_at":"2025-05-18T13:53:53Z","abstract_excerpt":"Sim-to-real transfer is a fundamental challenge in robot reinforcement learning. Discrepancies between simulation and reality can significantly impair policy performance, especially if it receives high-dimensional inputs such as dense depth estimates from vision. We propose a novel depth transfer method based on domain adaptation to bridge the visual gap between simulated and real-world depth data. A Variational Autoencoder (VAE) is first trained to encode ground-truth depth images from simulation into a latent space, which serves as input to a reinforcement learning (RL) policy. During deploy"},"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":"2505.12428","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-18T13:53:53Z","cross_cats_sorted":[],"title_canon_sha256":"3048743f64a3aeec14c455e934d6a95c9e690b68e50e8aa5c3d7746069fcb0c1","abstract_canon_sha256":"95fc108c5b21227b20cbbb00bab398b1cd73e003f0e77a0e601aeef10835830c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:04.007652Z","signature_b64":"4jzWWMxTURCm92BOYU6U/9DpT0Tmm46MsQGuIFHlgL2qJLE/2B3dgGGHOISbl8qBAQYWKrFGm5yQzee5mHcgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9ed233d6f995824438e734a71e9da2ecaeeb016cd47a92107b7022ecfefdbff","last_reissued_at":"2026-07-05T11:05:04.007160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:04.007160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Depth Transfer: Learning to See Like a Simulator for Real-World Drone Navigation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Christophe de Wagter, Guido C. H. E de Croon, Hang Yu","submitted_at":"2025-05-18T13:53:53Z","abstract_excerpt":"Sim-to-real transfer is a fundamental challenge in robot reinforcement learning. Discrepancies between simulation and reality can significantly impair policy performance, especially if it receives high-dimensional inputs such as dense depth estimates from vision. We propose a novel depth transfer method based on domain adaptation to bridge the visual gap between simulated and real-world depth data. A Variational Autoencoder (VAE) is first trained to encode ground-truth depth images from simulation into a latent space, which serves as input to a reinforcement learning (RL) policy. During deploy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12428","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/2505.12428/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":"2505.12428","created_at":"2026-07-05T11:05:04.007217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12428v1","created_at":"2026-07-05T11:05:04.007217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12428","created_at":"2026-07-05T11:05:04.007217+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZHWSGPLPTFMC","created_at":"2026-07-05T11:05:04.007217+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZHWSGPLPTFMCIQ4O","created_at":"2026-07-05T11:05:04.007217+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZHWSGPLP","created_at":"2026-07-05T11:05:04.007217+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04534","citing_title":"MAD: Mapping-Aware World Models for Agile Quadrotor Flight","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZHWSGPLPTFMCIQ4OONFHD2O2F3","json":"https://pith.science/pith/ZHWSGPLPTFMCIQ4OONFHD2O2F3.json","graph_json":"https://pith.science/api/pith-number/ZHWSGPLPTFMCIQ4OONFHD2O2F3/graph.json","events_json":"https://pith.science/api/pith-number/ZHWSGPLPTFMCIQ4OONFHD2O2F3/events.json","paper":"https://pith.science/paper/ZHWSGPLP"},"agent_actions":{"view_html":"https://pith.science/pith/ZHWSGPLPTFMCIQ4OONFHD2O2F3","download_json":"https://pith.science/pith/ZHWSGPLPTFMCIQ4OONFHD2O2F3.json","view_paper":"https://pith.science/paper/ZHWSGPLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12428&json=true","fetch_graph":"https://pith.science/api/pith-number/ZHWSGPLPTFMCIQ4OONFHD2O2F3/graph.json","fetch_events":"https://pith.science/api/pith-number/ZHWSGPLPTFMCIQ4OONFHD2O2F3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZHWSGPLPTFMCIQ4OONFHD2O2F3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZHWSGPLPTFMCIQ4OONFHD2O2F3/action/storage_attestation","attest_author":"https://pith.science/pith/ZHWSGPLPTFMCIQ4OONFHD2O2F3/action/author_attestation","sign_citation":"https://pith.science/pith/ZHWSGPLPTFMCIQ4OONFHD2O2F3/action/citation_signature","submit_replication":"https://pith.science/pith/ZHWSGPLPTFMCIQ4OONFHD2O2F3/action/replication_record"}},"created_at":"2026-07-05T11:05:04.007217+00:00","updated_at":"2026-07-05T11:05:04.007217+00:00"}