{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3TV62G4EWR4RE27R2BYODKX5IF","short_pith_number":"pith:3TV62G4E","schema_version":"1.0","canonical_sha256":"dcebed1b84b479126bf1d070e1aafd4156b4a4b0c5bb85c7b133e6a9397614da","source":{"kind":"arxiv","id":"2409.10078","version":5},"attestation_state":"computed","paper":{"title":"3D-TAFS: A Training-free Framework for 3D Affordance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Meng Chu, Tat-Seng Chua, Xuan Zhang, Zhedong Zheng","submitted_at":"2024-09-16T08:30:59Z","abstract_excerpt":"Translating high-level linguistic instructions into precise robotic actions in the physical world remains challenging, particularly when considering the feasibility of interacting with 3D objects. In this paper, we introduce 3D-TAFS, a novel training-free multimodal framework for 3D affordance segmentation. To facilitate a comprehensive evaluation of such frameworks, we present IndoorAfford-Bench, a large-scale benchmark containing 9,248 images spanning 20 diverse indoor scenes across 6 areas, supporting standardized interaction queries. In particular, our framework integrates a large multimod"},"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":"2409.10078","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-09-16T08:30:59Z","cross_cats_sorted":[],"title_canon_sha256":"82a304b521f617becc895c87f4c266850166de67465ab0591d42d2c1dc0fd8df","abstract_canon_sha256":"18092e008a04564ba7cc5c5f2a27c4aa986fb45825b95002a54339350356a194"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:40.213536Z","signature_b64":"hEHKiyiHnFSRzA1FSv5SXefYGRm1UWchgvki3mV+1YwJPXzaR2zlWrWsEChMd7L2bBLQZNAPK/J2BJavP+msAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcebed1b84b479126bf1d070e1aafd4156b4a4b0c5bb85c7b133e6a9397614da","last_reissued_at":"2026-07-05T10:44:40.213061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:40.213061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D-TAFS: A Training-free Framework for 3D Affordance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Meng Chu, Tat-Seng Chua, Xuan Zhang, Zhedong Zheng","submitted_at":"2024-09-16T08:30:59Z","abstract_excerpt":"Translating high-level linguistic instructions into precise robotic actions in the physical world remains challenging, particularly when considering the feasibility of interacting with 3D objects. In this paper, we introduce 3D-TAFS, a novel training-free multimodal framework for 3D affordance segmentation. To facilitate a comprehensive evaluation of such frameworks, we present IndoorAfford-Bench, a large-scale benchmark containing 9,248 images spanning 20 diverse indoor scenes across 6 areas, supporting standardized interaction queries. In particular, our framework integrates a large multimod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10078","kind":"arxiv","version":5},"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/2409.10078/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":"2409.10078","created_at":"2026-07-05T10:44:40.213120+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10078v5","created_at":"2026-07-05T10:44:40.213120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10078","created_at":"2026-07-05T10:44:40.213120+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TV62G4EWR4R","created_at":"2026-07-05T10:44:40.213120+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TV62G4EWR4RE27R","created_at":"2026-07-05T10:44:40.213120+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TV62G4E","created_at":"2026-07-05T10:44:40.213120+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15953","citing_title":"Understanding Long Videos via LLM-Powered Entity Relation Graphs","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3TV62G4EWR4RE27R2BYODKX5IF","json":"https://pith.science/pith/3TV62G4EWR4RE27R2BYODKX5IF.json","graph_json":"https://pith.science/api/pith-number/3TV62G4EWR4RE27R2BYODKX5IF/graph.json","events_json":"https://pith.science/api/pith-number/3TV62G4EWR4RE27R2BYODKX5IF/events.json","paper":"https://pith.science/paper/3TV62G4E"},"agent_actions":{"view_html":"https://pith.science/pith/3TV62G4EWR4RE27R2BYODKX5IF","download_json":"https://pith.science/pith/3TV62G4EWR4RE27R2BYODKX5IF.json","view_paper":"https://pith.science/paper/3TV62G4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10078&json=true","fetch_graph":"https://pith.science/api/pith-number/3TV62G4EWR4RE27R2BYODKX5IF/graph.json","fetch_events":"https://pith.science/api/pith-number/3TV62G4EWR4RE27R2BYODKX5IF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TV62G4EWR4RE27R2BYODKX5IF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TV62G4EWR4RE27R2BYODKX5IF/action/storage_attestation","attest_author":"https://pith.science/pith/3TV62G4EWR4RE27R2BYODKX5IF/action/author_attestation","sign_citation":"https://pith.science/pith/3TV62G4EWR4RE27R2BYODKX5IF/action/citation_signature","submit_replication":"https://pith.science/pith/3TV62G4EWR4RE27R2BYODKX5IF/action/replication_record"}},"created_at":"2026-07-05T10:44:40.213120+00:00","updated_at":"2026-07-05T10:44:40.213120+00:00"}