{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OGU3WDNIU2IH6VUDMYO4GU7MVQ","short_pith_number":"pith:OGU3WDNI","schema_version":"1.0","canonical_sha256":"71a9bb0da8a6907f5683661dc353ecac0bf8339b015d9c1f3e345c592b798036","source":{"kind":"arxiv","id":"2406.14235","version":3},"attestation_state":"computed","paper":{"title":"Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Jiaming Zhou, Junwei Liang, Kun-Yu Lin, Ronghe Qiu, Teli Ma, Zifan Wang","submitted_at":"2024-06-20T11:57:46Z","abstract_excerpt":"Learning generalizable visual representations across different embodied environments is essential for effective robotic manipulation in real-world scenarios. However, the limited scale and diversity of robot demonstration data pose a significant challenge. Recent research has explored leveraging large-scale human activity data for pre-training, but the substantial morphological differences between humans and robots introduce a significant human-robot domain discrepancy, hindering the generalization of these models to downstream manipulation tasks. To overcome this, we propose a novel adaptatio"},"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":"2406.14235","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-20T11:57:46Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"8e7f36e0483cae9bf4b78cd4c34a4e81b2637ecb62de9c9e4513662c8768aa75","abstract_canon_sha256":"321c6b2031674439cc3af6fc2afa6862a47ee4f11ac1f3f8ab4ad8a2a70f6e53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:09.400541Z","signature_b64":"guW0F6jUP9B7+gHONiDAsSN5p97eSk2/QTC7eCYr5qUYddgM/F30YAngktRyyyYEC2i8kpcZEu7uJO97wRkMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71a9bb0da8a6907f5683661dc353ecac0bf8339b015d9c1f3e345c592b798036","last_reissued_at":"2026-07-05T10:45:09.400020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:09.400020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Jiaming Zhou, Junwei Liang, Kun-Yu Lin, Ronghe Qiu, Teli Ma, Zifan Wang","submitted_at":"2024-06-20T11:57:46Z","abstract_excerpt":"Learning generalizable visual representations across different embodied environments is essential for effective robotic manipulation in real-world scenarios. However, the limited scale and diversity of robot demonstration data pose a significant challenge. Recent research has explored leveraging large-scale human activity data for pre-training, but the substantial morphological differences between humans and robots introduce a significant human-robot domain discrepancy, hindering the generalization of these models to downstream manipulation tasks. To overcome this, we propose a novel adaptatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14235","kind":"arxiv","version":3},"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/2406.14235/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":"2406.14235","created_at":"2026-07-05T10:45:09.400080+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14235v3","created_at":"2026-07-05T10:45:09.400080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14235","created_at":"2026-07-05T10:45:09.400080+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGU3WDNIU2IH","created_at":"2026-07-05T10:45:09.400080+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGU3WDNIU2IH6VUD","created_at":"2026-07-05T10:45:09.400080+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGU3WDNI","created_at":"2026-07-05T10:45:09.400080+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08639","citing_title":"Native Video-Action Pretraining for Generalizable Robot Control","ref_index":128,"is_internal_anchor":true},{"citing_arxiv_id":"2507.00990","citing_title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","ref_index":137,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01448","citing_title":"Decompose and Recompose: Reasoning New Skills from Existing Abilities for Cross-Task Robotic Manipulation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OGU3WDNIU2IH6VUDMYO4GU7MVQ","json":"https://pith.science/pith/OGU3WDNIU2IH6VUDMYO4GU7MVQ.json","graph_json":"https://pith.science/api/pith-number/OGU3WDNIU2IH6VUDMYO4GU7MVQ/graph.json","events_json":"https://pith.science/api/pith-number/OGU3WDNIU2IH6VUDMYO4GU7MVQ/events.json","paper":"https://pith.science/paper/OGU3WDNI"},"agent_actions":{"view_html":"https://pith.science/pith/OGU3WDNIU2IH6VUDMYO4GU7MVQ","download_json":"https://pith.science/pith/OGU3WDNIU2IH6VUDMYO4GU7MVQ.json","view_paper":"https://pith.science/paper/OGU3WDNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14235&json=true","fetch_graph":"https://pith.science/api/pith-number/OGU3WDNIU2IH6VUDMYO4GU7MVQ/graph.json","fetch_events":"https://pith.science/api/pith-number/OGU3WDNIU2IH6VUDMYO4GU7MVQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGU3WDNIU2IH6VUDMYO4GU7MVQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGU3WDNIU2IH6VUDMYO4GU7MVQ/action/storage_attestation","attest_author":"https://pith.science/pith/OGU3WDNIU2IH6VUDMYO4GU7MVQ/action/author_attestation","sign_citation":"https://pith.science/pith/OGU3WDNIU2IH6VUDMYO4GU7MVQ/action/citation_signature","submit_replication":"https://pith.science/pith/OGU3WDNIU2IH6VUDMYO4GU7MVQ/action/replication_record"}},"created_at":"2026-07-05T10:45:09.400080+00:00","updated_at":"2026-07-05T10:45:09.400080+00:00"}