{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IC6N4PR6Q4RF4BMKXM4NLCVMCW","short_pith_number":"pith:IC6N4PR6","schema_version":"1.0","canonical_sha256":"40bcde3e3e87225e058abb38d58aac15a7da6638ce108af04a7f7a027c2d2f71","source":{"kind":"arxiv","id":"2404.05603","version":1},"attestation_state":"computed","paper":{"title":"Self-Explainable Affordance Learning with Embodied Caption","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guolei Sun, Luc Van Gool, Peng Wang, Zhimin Wei, Zhipeng Zhang","submitted_at":"2024-04-08T15:22:38Z","abstract_excerpt":"In the field of visual affordance learning, previous methods mainly used abundant images or videos that delineate human behavior patterns to identify action possibility regions for object manipulation, with a variety of applications in robotic tasks. However, they encounter a main challenge of action ambiguity, illustrated by the vagueness like whether to beat or carry a drum, and the complexities involved in processing intricate scenes. Moreover, it is important for human intervention to rectify robot errors in time. To address these issues, we introduce Self-Explainable Affordance learning ("},"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":"2404.05603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T15:22:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4f923d8bfc6ab7b182569bd6b6f7f8c05be9754da51d165a876e396d82df19a1","abstract_canon_sha256":"dda5e4831e56e215073f9d7102bc3530f28cf9124e55360aa5be2839b83bee8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:43.175541Z","signature_b64":"rIQZVZgeES3D3YUBQYWFvIUMperTk09Jj8OTl3HrRVIYYd7XH16OqlBH3Xc1aQhODHs4O5nJXhDSPolwC7O0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40bcde3e3e87225e058abb38d58aac15a7da6638ce108af04a7f7a027c2d2f71","last_reissued_at":"2026-07-05T08:05:43.175105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:43.175105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Explainable Affordance Learning with Embodied Caption","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guolei Sun, Luc Van Gool, Peng Wang, Zhimin Wei, Zhipeng Zhang","submitted_at":"2024-04-08T15:22:38Z","abstract_excerpt":"In the field of visual affordance learning, previous methods mainly used abundant images or videos that delineate human behavior patterns to identify action possibility regions for object manipulation, with a variety of applications in robotic tasks. However, they encounter a main challenge of action ambiguity, illustrated by the vagueness like whether to beat or carry a drum, and the complexities involved in processing intricate scenes. Moreover, it is important for human intervention to rectify robot errors in time. To address these issues, we introduce Self-Explainable Affordance learning ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05603","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/2404.05603/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":"2404.05603","created_at":"2026-07-05T08:05:43.175165+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05603v1","created_at":"2026-07-05T08:05:43.175165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05603","created_at":"2026-07-05T08:05:43.175165+00:00"},{"alias_kind":"pith_short_12","alias_value":"IC6N4PR6Q4RF","created_at":"2026-07-05T08:05:43.175165+00:00"},{"alias_kind":"pith_short_16","alias_value":"IC6N4PR6Q4RF4BMK","created_at":"2026-07-05T08:05:43.175165+00:00"},{"alias_kind":"pith_short_8","alias_value":"IC6N4PR6","created_at":"2026-07-05T08:05:43.175165+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IC6N4PR6Q4RF4BMKXM4NLCVMCW","json":"https://pith.science/pith/IC6N4PR6Q4RF4BMKXM4NLCVMCW.json","graph_json":"https://pith.science/api/pith-number/IC6N4PR6Q4RF4BMKXM4NLCVMCW/graph.json","events_json":"https://pith.science/api/pith-number/IC6N4PR6Q4RF4BMKXM4NLCVMCW/events.json","paper":"https://pith.science/paper/IC6N4PR6"},"agent_actions":{"view_html":"https://pith.science/pith/IC6N4PR6Q4RF4BMKXM4NLCVMCW","download_json":"https://pith.science/pith/IC6N4PR6Q4RF4BMKXM4NLCVMCW.json","view_paper":"https://pith.science/paper/IC6N4PR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05603&json=true","fetch_graph":"https://pith.science/api/pith-number/IC6N4PR6Q4RF4BMKXM4NLCVMCW/graph.json","fetch_events":"https://pith.science/api/pith-number/IC6N4PR6Q4RF4BMKXM4NLCVMCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IC6N4PR6Q4RF4BMKXM4NLCVMCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IC6N4PR6Q4RF4BMKXM4NLCVMCW/action/storage_attestation","attest_author":"https://pith.science/pith/IC6N4PR6Q4RF4BMKXM4NLCVMCW/action/author_attestation","sign_citation":"https://pith.science/pith/IC6N4PR6Q4RF4BMKXM4NLCVMCW/action/citation_signature","submit_replication":"https://pith.science/pith/IC6N4PR6Q4RF4BMKXM4NLCVMCW/action/replication_record"}},"created_at":"2026-07-05T08:05:43.175165+00:00","updated_at":"2026-07-05T08:05:43.175165+00:00"}