{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VPFNGDGAAXFEGZHXU63Y45ZNFC","short_pith_number":"pith:VPFNGDGA","schema_version":"1.0","canonical_sha256":"abcad30cc005ca4364f7a7b78e772d28b3a3ef1cae1fdb952c5d417b2419b5cf","source":{"kind":"arxiv","id":"2405.12461","version":1},"attestation_state":"computed","paper":{"title":"WorldAfford: Affordance Grounding based on Natural Language Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changmao Chen, Yuren Cong, Zhen Kan","submitted_at":"2024-05-21T02:37:45Z","abstract_excerpt":"Affordance grounding aims to localize the interaction regions for the manipulated objects in the scene image according to given instructions. A critical challenge in affordance grounding is that the embodied agent should understand human instructions and analyze which tools in the environment can be used, as well as how to use these tools to accomplish the instructions. Most recent works primarily supports simple action labels as input instructions for localizing affordance regions, failing to capture complex human objectives. Moreover, these approaches typically identify affordance regions of"},"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":"2405.12461","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-21T02:37:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a2b95ce99df57cc7adc67f2ae583011f88c445bbb848566d51d1744c8d3db41c","abstract_canon_sha256":"ea8118286b371dba2f914e3f3e28923bddf09475bf99f8bc8d8e5408358663e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:20.533279Z","signature_b64":"jU/gkAAv2m11eznxBmbC9OfTdPeh2r37CvxXWy3gDgkfSupihAWu4tx/jKEveMCRP5H1qEdA7lgtM/U8tf8BCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abcad30cc005ca4364f7a7b78e772d28b3a3ef1cae1fdb952c5d417b2419b5cf","last_reissued_at":"2026-07-05T08:21:20.532854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:20.532854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WorldAfford: Affordance Grounding based on Natural Language Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changmao Chen, Yuren Cong, Zhen Kan","submitted_at":"2024-05-21T02:37:45Z","abstract_excerpt":"Affordance grounding aims to localize the interaction regions for the manipulated objects in the scene image according to given instructions. A critical challenge in affordance grounding is that the embodied agent should understand human instructions and analyze which tools in the environment can be used, as well as how to use these tools to accomplish the instructions. Most recent works primarily supports simple action labels as input instructions for localizing affordance regions, failing to capture complex human objectives. Moreover, these approaches typically identify affordance regions of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12461","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/2405.12461/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":"2405.12461","created_at":"2026-07-05T08:21:20.532910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.12461v1","created_at":"2026-07-05T08:21:20.532910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12461","created_at":"2026-07-05T08:21:20.532910+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPFNGDGAAXFE","created_at":"2026-07-05T08:21:20.532910+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPFNGDGAAXFEGZHX","created_at":"2026-07-05T08:21:20.532910+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPFNGDGA","created_at":"2026-07-05T08:21:20.532910+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24103","citing_title":"Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VPFNGDGAAXFEGZHXU63Y45ZNFC","json":"https://pith.science/pith/VPFNGDGAAXFEGZHXU63Y45ZNFC.json","graph_json":"https://pith.science/api/pith-number/VPFNGDGAAXFEGZHXU63Y45ZNFC/graph.json","events_json":"https://pith.science/api/pith-number/VPFNGDGAAXFEGZHXU63Y45ZNFC/events.json","paper":"https://pith.science/paper/VPFNGDGA"},"agent_actions":{"view_html":"https://pith.science/pith/VPFNGDGAAXFEGZHXU63Y45ZNFC","download_json":"https://pith.science/pith/VPFNGDGAAXFEGZHXU63Y45ZNFC.json","view_paper":"https://pith.science/paper/VPFNGDGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.12461&json=true","fetch_graph":"https://pith.science/api/pith-number/VPFNGDGAAXFEGZHXU63Y45ZNFC/graph.json","fetch_events":"https://pith.science/api/pith-number/VPFNGDGAAXFEGZHXU63Y45ZNFC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPFNGDGAAXFEGZHXU63Y45ZNFC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPFNGDGAAXFEGZHXU63Y45ZNFC/action/storage_attestation","attest_author":"https://pith.science/pith/VPFNGDGAAXFEGZHXU63Y45ZNFC/action/author_attestation","sign_citation":"https://pith.science/pith/VPFNGDGAAXFEGZHXU63Y45ZNFC/action/citation_signature","submit_replication":"https://pith.science/pith/VPFNGDGAAXFEGZHXU63Y45ZNFC/action/replication_record"}},"created_at":"2026-07-05T08:21:20.532910+00:00","updated_at":"2026-07-05T08:21:20.532910+00:00"}