{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W2PYYCKMTAMNRCHRRXKPJR4RAA","short_pith_number":"pith:W2PYYCKM","schema_version":"1.0","canonical_sha256":"b69f8c094c9818d888f18dd4f4c791001264e53a4e87f2ab078ee863d7a4fa1c","source":{"kind":"arxiv","id":"2407.18911","version":1},"attestation_state":"computed","paper":{"title":"HRP: Human Affordances for Robotic Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Abhinav Gupta, Mohan Kumar Srirama, Shikhar Bahl, Sudeep Dasari","submitted_at":"2024-07-26T17:59:52Z","abstract_excerpt":"In order to *generalize* to various tasks in the wild, robotic agents will need a suitable representation (i.e., vision network) that enables the robot to predict optimal actions given high dimensional vision inputs. However, learning such a representation requires an extreme amount of diverse training data, which is prohibitively expensive to collect on a real robot. How can we overcome this problem? Instead of collecting more robot data, this paper proposes using internet-scale, human videos to extract \"affordances,\" both at the environment and agent level, and distill them into a pre-traine"},"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":"2407.18911","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-07-26T17:59:52Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5ce83b7e77864e543bd266a290e0c6a19a09945859337852d974f93f416b6e5a","abstract_canon_sha256":"4852d2f881bf05897ae4744c665e0a93ca1e0f56d524e3685180990b96f7bb54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:56.255342Z","signature_b64":"Z0pwZaDnesgQo3pZV8bR2tWSFri25syhI+v/GrIZ+vAOCrfXzRXOXws8OxqeEgDVa+T/H6UIuBSvkjMOjBclDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b69f8c094c9818d888f18dd4f4c791001264e53a4e87f2ab078ee863d7a4fa1c","last_reissued_at":"2026-07-05T08:48:56.254843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:56.254843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HRP: Human Affordances for Robotic Pre-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Abhinav Gupta, Mohan Kumar Srirama, Shikhar Bahl, Sudeep Dasari","submitted_at":"2024-07-26T17:59:52Z","abstract_excerpt":"In order to *generalize* to various tasks in the wild, robotic agents will need a suitable representation (i.e., vision network) that enables the robot to predict optimal actions given high dimensional vision inputs. However, learning such a representation requires an extreme amount of diverse training data, which is prohibitively expensive to collect on a real robot. How can we overcome this problem? Instead of collecting more robot data, this paper proposes using internet-scale, human videos to extract \"affordances,\" both at the environment and agent level, and distill them into a pre-traine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18911","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/2407.18911/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":"2407.18911","created_at":"2026-07-05T08:48:56.254904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.18911v1","created_at":"2026-07-05T08:48:56.254904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18911","created_at":"2026-07-05T08:48:56.254904+00:00"},{"alias_kind":"pith_short_12","alias_value":"W2PYYCKMTAMN","created_at":"2026-07-05T08:48:56.254904+00:00"},{"alias_kind":"pith_short_16","alias_value":"W2PYYCKMTAMNRCHR","created_at":"2026-07-05T08:48:56.254904+00:00"},{"alias_kind":"pith_short_8","alias_value":"W2PYYCKM","created_at":"2026-07-05T08:48:56.254904+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17256","citing_title":"Contrastive Action-Image Pre-training for Visuomotor Control","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12499","citing_title":"Action-Effect Memory Pretraining for Robot Manipulation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2505.11237","citing_title":"Concept Drift Guided LayerNorm Tuning for Efficient Multimodal Metaphor Identification","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00990","citing_title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15659","citing_title":"FLARE: Robot Learning with Implicit World Modeling","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2505.12705","citing_title":"DreamGen: Unlocking Generalization in Robot Learning through Video World Models","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W2PYYCKMTAMNRCHRRXKPJR4RAA","json":"https://pith.science/pith/W2PYYCKMTAMNRCHRRXKPJR4RAA.json","graph_json":"https://pith.science/api/pith-number/W2PYYCKMTAMNRCHRRXKPJR4RAA/graph.json","events_json":"https://pith.science/api/pith-number/W2PYYCKMTAMNRCHRRXKPJR4RAA/events.json","paper":"https://pith.science/paper/W2PYYCKM"},"agent_actions":{"view_html":"https://pith.science/pith/W2PYYCKMTAMNRCHRRXKPJR4RAA","download_json":"https://pith.science/pith/W2PYYCKMTAMNRCHRRXKPJR4RAA.json","view_paper":"https://pith.science/paper/W2PYYCKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.18911&json=true","fetch_graph":"https://pith.science/api/pith-number/W2PYYCKMTAMNRCHRRXKPJR4RAA/graph.json","fetch_events":"https://pith.science/api/pith-number/W2PYYCKMTAMNRCHRRXKPJR4RAA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W2PYYCKMTAMNRCHRRXKPJR4RAA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W2PYYCKMTAMNRCHRRXKPJR4RAA/action/storage_attestation","attest_author":"https://pith.science/pith/W2PYYCKMTAMNRCHRRXKPJR4RAA/action/author_attestation","sign_citation":"https://pith.science/pith/W2PYYCKMTAMNRCHRRXKPJR4RAA/action/citation_signature","submit_replication":"https://pith.science/pith/W2PYYCKMTAMNRCHRRXKPJR4RAA/action/replication_record"}},"created_at":"2026-07-05T08:48:56.254904+00:00","updated_at":"2026-07-05T08:48:56.254904+00:00"}