{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R2MNR7C5PZD4GFH426J5YTP2TF","short_pith_number":"pith:R2MNR7C5","schema_version":"1.0","canonical_sha256":"8e98d8fc5d7e47c314fcd793dc4dfa997d0a3d928d203e4fb85c1b0e45b14a3a","source":{"kind":"arxiv","id":"2409.20551","version":2},"attestation_state":"computed","paper":{"title":"UniAff: A Unified Representation of Affordances for Tool Usage and Articulation with Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ce Hao, Cewu Lu, Haonan Chang, Hongsheng Li, Junbo Wang, Liu Liu, Peng Gao, Qiaojun Yu, Siyuan Huang, Xibin Yuan, Xin Li, Zhengkai Jiang","submitted_at":"2024-09-30T17:52:05Z","abstract_excerpt":"Previous studies on robotic manipulation are based on a limited understanding of the underlying 3D motion constraints and affordances. To address these challenges, we propose a comprehensive paradigm, termed UniAff, that integrates 3D object-centric manipulation and task understanding in a unified formulation. Specifically, we constructed a dataset labeled with manipulation-related key attributes, comprising 900 articulated objects from 19 categories and 600 tools from 12 categories. Furthermore, we leverage MLLMs to infer object-centric representations for manipulation tasks, including afford"},"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":"2409.20551","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-30T17:52:05Z","cross_cats_sorted":[],"title_canon_sha256":"793f5796710a4d6e11257593b560861f251f3a28dac25caa7a18efbf5332e572","abstract_canon_sha256":"f4341ee161a0afe994612b69f72d8c69521a1bf7de970c026d5a68475f59b6ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:44.431415Z","signature_b64":"mQ3O50CJJKZdLE8Jtsz/qEdNd7/K57fw2yABDBq6OUllUCC2H1pZIIK8kyU7ttXBsfg/n9wU2WVpz+E9I6AxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e98d8fc5d7e47c314fcd793dc4dfa997d0a3d928d203e4fb85c1b0e45b14a3a","last_reissued_at":"2026-07-05T10:10:44.430975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:44.430975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniAff: A Unified Representation of Affordances for Tool Usage and Articulation with Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ce Hao, Cewu Lu, Haonan Chang, Hongsheng Li, Junbo Wang, Liu Liu, Peng Gao, Qiaojun Yu, Siyuan Huang, Xibin Yuan, Xin Li, Zhengkai Jiang","submitted_at":"2024-09-30T17:52:05Z","abstract_excerpt":"Previous studies on robotic manipulation are based on a limited understanding of the underlying 3D motion constraints and affordances. To address these challenges, we propose a comprehensive paradigm, termed UniAff, that integrates 3D object-centric manipulation and task understanding in a unified formulation. Specifically, we constructed a dataset labeled with manipulation-related key attributes, comprising 900 articulated objects from 19 categories and 600 tools from 12 categories. Furthermore, we leverage MLLMs to infer object-centric representations for manipulation tasks, including afford"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20551","kind":"arxiv","version":2},"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/2409.20551/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":"2409.20551","created_at":"2026-07-05T10:10:44.431034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.20551v2","created_at":"2026-07-05T10:10:44.431034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20551","created_at":"2026-07-05T10:10:44.431034+00:00"},{"alias_kind":"pith_short_12","alias_value":"R2MNR7C5PZD4","created_at":"2026-07-05T10:10:44.431034+00:00"},{"alias_kind":"pith_short_16","alias_value":"R2MNR7C5PZD4GFH4","created_at":"2026-07-05T10:10:44.431034+00:00"},{"alias_kind":"pith_short_8","alias_value":"R2MNR7C5","created_at":"2026-07-05T10:10:44.431034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05411","citing_title":"Creative Robot Tool Use by Counterfactual Reasoning","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R2MNR7C5PZD4GFH426J5YTP2TF","json":"https://pith.science/pith/R2MNR7C5PZD4GFH426J5YTP2TF.json","graph_json":"https://pith.science/api/pith-number/R2MNR7C5PZD4GFH426J5YTP2TF/graph.json","events_json":"https://pith.science/api/pith-number/R2MNR7C5PZD4GFH426J5YTP2TF/events.json","paper":"https://pith.science/paper/R2MNR7C5"},"agent_actions":{"view_html":"https://pith.science/pith/R2MNR7C5PZD4GFH426J5YTP2TF","download_json":"https://pith.science/pith/R2MNR7C5PZD4GFH426J5YTP2TF.json","view_paper":"https://pith.science/paper/R2MNR7C5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.20551&json=true","fetch_graph":"https://pith.science/api/pith-number/R2MNR7C5PZD4GFH426J5YTP2TF/graph.json","fetch_events":"https://pith.science/api/pith-number/R2MNR7C5PZD4GFH426J5YTP2TF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R2MNR7C5PZD4GFH426J5YTP2TF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R2MNR7C5PZD4GFH426J5YTP2TF/action/storage_attestation","attest_author":"https://pith.science/pith/R2MNR7C5PZD4GFH426J5YTP2TF/action/author_attestation","sign_citation":"https://pith.science/pith/R2MNR7C5PZD4GFH426J5YTP2TF/action/citation_signature","submit_replication":"https://pith.science/pith/R2MNR7C5PZD4GFH426J5YTP2TF/action/replication_record"}},"created_at":"2026-07-05T10:10:44.431034+00:00","updated_at":"2026-07-05T10:10:44.431034+00:00"}