{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YHFXQ2AMC3ZZNMBVEAUNF66HME","short_pith_number":"pith:YHFXQ2AM","schema_version":"1.0","canonical_sha256":"c1cb78680c16f396b0352028d2fbc761031f4283f7e0f328dfef34388ba02f45","source":{"kind":"arxiv","id":"2508.09976","version":1},"attestation_state":"computed","paper":{"title":"Masquerade: Learning from In-the-wild Human Videos using Data-Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jeannette Bohg, Jiaying Fang, Marion Lepert","submitted_at":"2025-08-13T17:43:34Z","abstract_excerpt":"Robot manipulation research still suffers from significant data scarcity: even the largest robot datasets are orders of magnitude smaller and less diverse than those that fueled recent breakthroughs in language and vision. We introduce Masquerade, a method that edits in-the-wild egocentric human videos to bridge the visual embodiment gap between humans and robots and then learns a robot policy with these edited videos. Our pipeline turns each human video into robotized demonstrations by (i) estimating 3-D hand poses, (ii) inpainting the human arms, and (iii) overlaying a rendered bimanual robo"},"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":"2508.09976","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-13T17:43:34Z","cross_cats_sorted":[],"title_canon_sha256":"1f327abf5c6337e4232ec2d6a73e98fa4db7f60aa2a6aa7cf3b83a37998ddd58","abstract_canon_sha256":"a593e97f8116cec943a24148dd742f3318bc26c22e8db7fd11315bc0af4dbed8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:55.041777Z","signature_b64":"YxGs/3lNnkgkpxYkV8AcK873rjIQCm1pbf8kO8Snx4ujfJpsC7chfZOS277qOHuEPYV0I+3ML0VZ9+olt0HvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1cb78680c16f396b0352028d2fbc761031f4283f7e0f328dfef34388ba02f45","last_reissued_at":"2026-05-29T01:04:55.041331Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:55.041331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Masquerade: Learning from In-the-wild Human Videos using Data-Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Jeannette Bohg, Jiaying Fang, Marion Lepert","submitted_at":"2025-08-13T17:43:34Z","abstract_excerpt":"Robot manipulation research still suffers from significant data scarcity: even the largest robot datasets are orders of magnitude smaller and less diverse than those that fueled recent breakthroughs in language and vision. We introduce Masquerade, a method that edits in-the-wild egocentric human videos to bridge the visual embodiment gap between humans and robots and then learns a robot policy with these edited videos. Our pipeline turns each human video into robotized demonstrations by (i) estimating 3-D hand poses, (ii) inpainting the human arms, and (iii) overlaying a rendered bimanual robo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09976","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/2508.09976/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":"2508.09976","created_at":"2026-05-29T01:04:55.041391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09976v1","created_at":"2026-05-29T01:04:55.041391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09976","created_at":"2026-05-29T01:04:55.041391+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHFXQ2AMC3ZZ","created_at":"2026-05-29T01:04:55.041391+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHFXQ2AMC3ZZNMBV","created_at":"2026-05-29T01:04:55.041391+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHFXQ2AM","created_at":"2026-05-29T01:04:55.041391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":13,"sample":[{"citing_arxiv_id":"2605.16743","citing_title":"LACE: Latent Visual Representation for Cross-Embodiment Learning","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2511.04671","citing_title":"X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19092","citing_title":"RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12038","citing_title":"OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03637","citing_title":"Bridging the Embodiment Gap: Disentangled Cross-Embodiment Video Editing","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2604.28185","citing_title":"Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23121","citing_title":"Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22615","citing_title":"GazeVLA: Learning Human Intention for Robotic Manipulation","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10809","citing_title":"WARPED: Wrist-Aligned Rendering for Robot Policy Learning from Egocentric Human Demonstrations","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10677","citing_title":"LIDEA: Human-to-Robot Imitation Learning via Implicit Feature Distillation and Explicit Geometry Alignment","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08534","citing_title":"ActiveGlasses: Learning Manipulation with Active Vision from Ego-centric Human Demonstration","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13645","citing_title":"A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19092","citing_title":"RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YHFXQ2AMC3ZZNMBVEAUNF66HME","json":"https://pith.science/pith/YHFXQ2AMC3ZZNMBVEAUNF66HME.json","graph_json":"https://pith.science/api/pith-number/YHFXQ2AMC3ZZNMBVEAUNF66HME/graph.json","events_json":"https://pith.science/api/pith-number/YHFXQ2AMC3ZZNMBVEAUNF66HME/events.json","paper":"https://pith.science/paper/YHFXQ2AM"},"agent_actions":{"view_html":"https://pith.science/pith/YHFXQ2AMC3ZZNMBVEAUNF66HME","download_json":"https://pith.science/pith/YHFXQ2AMC3ZZNMBVEAUNF66HME.json","view_paper":"https://pith.science/paper/YHFXQ2AM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09976&json=true","fetch_graph":"https://pith.science/api/pith-number/YHFXQ2AMC3ZZNMBVEAUNF66HME/graph.json","fetch_events":"https://pith.science/api/pith-number/YHFXQ2AMC3ZZNMBVEAUNF66HME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHFXQ2AMC3ZZNMBVEAUNF66HME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHFXQ2AMC3ZZNMBVEAUNF66HME/action/storage_attestation","attest_author":"https://pith.science/pith/YHFXQ2AMC3ZZNMBVEAUNF66HME/action/author_attestation","sign_citation":"https://pith.science/pith/YHFXQ2AMC3ZZNMBVEAUNF66HME/action/citation_signature","submit_replication":"https://pith.science/pith/YHFXQ2AMC3ZZNMBVEAUNF66HME/action/replication_record"}},"created_at":"2026-05-29T01:04:55.041391+00:00","updated_at":"2026-05-29T01:04:55.041391+00:00"}