{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UDAFWMQRRQVPCN5KBR5PFXAEPE","short_pith_number":"pith:UDAFWMQR","schema_version":"1.0","canonical_sha256":"a0c05b32118c2af137aa0c7af2dc0479378193d422a6ddcf313c81aa38e5d2d5","source":{"kind":"arxiv","id":"2508.17922","version":1},"attestation_state":"computed","paper":{"title":"Egocentric Instruction-oriented Affordance Prediction via Large Multimodal Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Bokai Ji, Chu Tang, Guangxia Li, Jie Gu, Jingmin Chen, Xiaokang Ma","submitted_at":"2025-08-25T11:40:31Z","abstract_excerpt":"Affordance is crucial for intelligent robots in the context of object manipulation. In this paper, we argue that affordance should be task-/instruction-dependent, which is overlooked by many previous works. That is, different instructions can lead to different manipulation regions and directions even for the same object. According to this observation, we present a new dataset comprising fifteen thousand object-instruction-affordance triplets. All scenes in the dataset are from an egocentric viewpoint, designed to approximate the perspective of a human-like robot. Furthermore, we investigate ho"},"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":"2508.17922","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-25T11:40:31Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a717e2450c45a49a06edf20c14ba2a897730ed7c86d442fe4f7f1cd7c6f6fd0b","abstract_canon_sha256":"73dc35a6e2dc13e8da61965a4706ea2437cc1b5a13bc3afe14e36c74469d3697"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:50.417005Z","signature_b64":"vAZE6fvB01CZSpW8i7Cdwo7exzRpl1RMSU4/3G71jLMEO8u8WKSNh+vcRXXYP+MiQ5v8fjK2PSv9kfaJwULQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0c05b32118c2af137aa0c7af2dc0479378193d422a6ddcf313c81aa38e5d2d5","last_reissued_at":"2026-07-05T11:58:50.416532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:50.416532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Egocentric Instruction-oriented Affordance Prediction via Large Multimodal Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Bokai Ji, Chu Tang, Guangxia Li, Jie Gu, Jingmin Chen, Xiaokang Ma","submitted_at":"2025-08-25T11:40:31Z","abstract_excerpt":"Affordance is crucial for intelligent robots in the context of object manipulation. In this paper, we argue that affordance should be task-/instruction-dependent, which is overlooked by many previous works. That is, different instructions can lead to different manipulation regions and directions even for the same object. According to this observation, we present a new dataset comprising fifteen thousand object-instruction-affordance triplets. All scenes in the dataset are from an egocentric viewpoint, designed to approximate the perspective of a human-like robot. Furthermore, we investigate ho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17922","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/2508.17922/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":"2508.17922","created_at":"2026-07-05T11:58:50.416598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.17922v1","created_at":"2026-07-05T11:58:50.416598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17922","created_at":"2026-07-05T11:58:50.416598+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDAFWMQRRQVP","created_at":"2026-07-05T11:58:50.416598+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDAFWMQRRQVPCN5K","created_at":"2026-07-05T11:58:50.416598+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDAFWMQR","created_at":"2026-07-05T11:58:50.416598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07642","citing_title":"EggHand: A Multimodal Foundation Model for Egocentric Hand Pose Forecasting","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDAFWMQRRQVPCN5KBR5PFXAEPE","json":"https://pith.science/pith/UDAFWMQRRQVPCN5KBR5PFXAEPE.json","graph_json":"https://pith.science/api/pith-number/UDAFWMQRRQVPCN5KBR5PFXAEPE/graph.json","events_json":"https://pith.science/api/pith-number/UDAFWMQRRQVPCN5KBR5PFXAEPE/events.json","paper":"https://pith.science/paper/UDAFWMQR"},"agent_actions":{"view_html":"https://pith.science/pith/UDAFWMQRRQVPCN5KBR5PFXAEPE","download_json":"https://pith.science/pith/UDAFWMQRRQVPCN5KBR5PFXAEPE.json","view_paper":"https://pith.science/paper/UDAFWMQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.17922&json=true","fetch_graph":"https://pith.science/api/pith-number/UDAFWMQRRQVPCN5KBR5PFXAEPE/graph.json","fetch_events":"https://pith.science/api/pith-number/UDAFWMQRRQVPCN5KBR5PFXAEPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDAFWMQRRQVPCN5KBR5PFXAEPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDAFWMQRRQVPCN5KBR5PFXAEPE/action/storage_attestation","attest_author":"https://pith.science/pith/UDAFWMQRRQVPCN5KBR5PFXAEPE/action/author_attestation","sign_citation":"https://pith.science/pith/UDAFWMQRRQVPCN5KBR5PFXAEPE/action/citation_signature","submit_replication":"https://pith.science/pith/UDAFWMQRRQVPCN5KBR5PFXAEPE/action/replication_record"}},"created_at":"2026-07-05T11:58:50.416598+00:00","updated_at":"2026-07-05T11:58:50.416598+00:00"}