{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UDQFSDY3HGCEKBDZJ6VBQLORIO","short_pith_number":"pith:UDQFSDY3","schema_version":"1.0","canonical_sha256":"a0e0590f1b39844504794faa182dd143b01015e14d002078c8b301551d4843ef","source":{"kind":"arxiv","id":"2505.11865","version":1},"attestation_state":"computed","paper":{"title":"GLOVER++: Unleashing the Potential of Affordance Learning from Human Behaviors for Robotic Manipulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Jiaming Zhou, Jia Zheng, Junwei Liang, Teli Ma, Zifan Wang, Ziyao Gao","submitted_at":"2025-05-17T06:14:31Z","abstract_excerpt":"Learning manipulation skills from human demonstration videos offers a promising path toward generalizable and interpretable robotic intelligence-particularly through the lens of actionable affordances. However, transferring such knowledge remains challenging due to: 1) a lack of large-scale datasets with precise affordance annotations, and 2) insufficient exploration of affordances in diverse manipulation contexts. To address these gaps, we introduce HOVA-500K, a large-scale, affordance-annotated dataset comprising 500,000 images across 1,726 object categories and 675 actions. We also release "},"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":"2505.11865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-17T06:14:31Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6d77f35d2953608a85426225257ef9c18a787e628a3d420e7c6a77bb6f826d7f","abstract_canon_sha256":"9d381c2c8e4ae3f302802f93db3a3e697bed028455fe76a28e00a038135f717f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:53.525034Z","signature_b64":"WdaN5CzZUOPtv/n8Tiak48Eg4Y0MKQDaZHUb3D40+W5/MuffKxyk0P4ObS42aX0zVI/YLyMdRji+yPucec9kCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0e0590f1b39844504794faa182dd143b01015e14d002078c8b301551d4843ef","last_reissued_at":"2026-07-05T11:04:53.524501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:53.524501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GLOVER++: Unleashing the Potential of Affordance Learning from Human Behaviors for Robotic Manipulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Jiaming Zhou, Jia Zheng, Junwei Liang, Teli Ma, Zifan Wang, Ziyao Gao","submitted_at":"2025-05-17T06:14:31Z","abstract_excerpt":"Learning manipulation skills from human demonstration videos offers a promising path toward generalizable and interpretable robotic intelligence-particularly through the lens of actionable affordances. However, transferring such knowledge remains challenging due to: 1) a lack of large-scale datasets with precise affordance annotations, and 2) insufficient exploration of affordances in diverse manipulation contexts. To address these gaps, we introduce HOVA-500K, a large-scale, affordance-annotated dataset comprising 500,000 images across 1,726 object categories and 675 actions. We also release "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11865","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/2505.11865/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":"2505.11865","created_at":"2026-07-05T11:04:53.524562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11865v1","created_at":"2026-07-05T11:04:53.524562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11865","created_at":"2026-07-05T11:04:53.524562+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDQFSDY3HGCE","created_at":"2026-07-05T11:04:53.524562+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDQFSDY3HGCEKBDZ","created_at":"2026-07-05T11:04:53.524562+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDQFSDY3","created_at":"2026-07-05T11:04:53.524562+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14923","citing_title":"SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24203","citing_title":"Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2601.07060","citing_title":"PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00078","citing_title":"Being-H0.7: A Latent World-Action Model from Egocentric Videos","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20834","citing_title":"PokeVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidance","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDQFSDY3HGCEKBDZJ6VBQLORIO","json":"https://pith.science/pith/UDQFSDY3HGCEKBDZJ6VBQLORIO.json","graph_json":"https://pith.science/api/pith-number/UDQFSDY3HGCEKBDZJ6VBQLORIO/graph.json","events_json":"https://pith.science/api/pith-number/UDQFSDY3HGCEKBDZJ6VBQLORIO/events.json","paper":"https://pith.science/paper/UDQFSDY3"},"agent_actions":{"view_html":"https://pith.science/pith/UDQFSDY3HGCEKBDZJ6VBQLORIO","download_json":"https://pith.science/pith/UDQFSDY3HGCEKBDZJ6VBQLORIO.json","view_paper":"https://pith.science/paper/UDQFSDY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11865&json=true","fetch_graph":"https://pith.science/api/pith-number/UDQFSDY3HGCEKBDZJ6VBQLORIO/graph.json","fetch_events":"https://pith.science/api/pith-number/UDQFSDY3HGCEKBDZJ6VBQLORIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDQFSDY3HGCEKBDZJ6VBQLORIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDQFSDY3HGCEKBDZJ6VBQLORIO/action/storage_attestation","attest_author":"https://pith.science/pith/UDQFSDY3HGCEKBDZJ6VBQLORIO/action/author_attestation","sign_citation":"https://pith.science/pith/UDQFSDY3HGCEKBDZJ6VBQLORIO/action/citation_signature","submit_replication":"https://pith.science/pith/UDQFSDY3HGCEKBDZJ6VBQLORIO/action/replication_record"}},"created_at":"2026-07-05T11:04:53.524562+00:00","updated_at":"2026-07-05T11:04:53.524562+00:00"}