{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:EEJUYERTLNTVWSOZZBPNOWUXA3","short_pith_number":"pith:EEJUYERT","schema_version":"1.0","canonical_sha256":"21134c12335b675b49d9c85ed75a9706ce8fda0f07f01255f74e1d7e5e2b64cb","source":{"kind":"arxiv","id":"1909.05829","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Suraj Nair","submitted_at":"2019-09-12T17:36:45Z","abstract_excerpt":"Video prediction models combined with planning algorithms have shown promise in enabling robots to learn to perform many vision-based tasks through only self-supervision, reaching novel goals in cluttered scenes with unseen objects. However, due to the compounding uncertainty in long horizon video prediction and poor scalability of sampling-based planning optimizers, one significant limitation of these approaches is the ability to plan over long horizons to reach distant goals. To that end, we propose a framework for subgoal generation and planning, hierarchical visual foresight (HVF), which g"},"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":"1909.05829","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-12T17:36:45Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO","stat.ML"],"title_canon_sha256":"bff71e24cb8dd25c89dbd285c19784b71c6ac8df34fa2482a6a03ac19cb7a1be","abstract_canon_sha256":"c0a681a48696f6c3acea714f0d9652411f3768ed19457dd3a227a0c002de7b12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:18.926107Z","signature_b64":"Smt1/UUVhOyJ+WwaNZL8RApQ6QvDi5eSMJZQpK4YfT0XRziNefmC/07ll+o3dVEnUxvfEzutQ0V29ay8HuSTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21134c12335b675b49d9c85ed75a9706ce8fda0f07f01255f74e1d7e5e2b64cb","last_reissued_at":"2026-07-05T00:04:18.925634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:18.925634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Suraj Nair","submitted_at":"2019-09-12T17:36:45Z","abstract_excerpt":"Video prediction models combined with planning algorithms have shown promise in enabling robots to learn to perform many vision-based tasks through only self-supervision, reaching novel goals in cluttered scenes with unseen objects. However, due to the compounding uncertainty in long horizon video prediction and poor scalability of sampling-based planning optimizers, one significant limitation of these approaches is the ability to plan over long horizons to reach distant goals. To that end, we propose a framework for subgoal generation and planning, hierarchical visual foresight (HVF), which g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.05829","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/1909.05829/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":"1909.05829","created_at":"2026-07-05T00:04:18.925707+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.05829v1","created_at":"2026-07-05T00:04:18.925707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.05829","created_at":"2026-07-05T00:04:18.925707+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEJUYERTLNTV","created_at":"2026-07-05T00:04:18.925707+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEJUYERTLNTVWSOZ","created_at":"2026-07-05T00:04:18.925707+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEJUYERT","created_at":"2026-07-05T00:04:18.925707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22488","citing_title":"SCOPE: Evolving Symbolic World for Planning in Open-Ended Environments","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2310.10639","citing_title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05608","citing_title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2204.01691","citing_title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EEJUYERTLNTVWSOZZBPNOWUXA3","json":"https://pith.science/pith/EEJUYERTLNTVWSOZZBPNOWUXA3.json","graph_json":"https://pith.science/api/pith-number/EEJUYERTLNTVWSOZZBPNOWUXA3/graph.json","events_json":"https://pith.science/api/pith-number/EEJUYERTLNTVWSOZZBPNOWUXA3/events.json","paper":"https://pith.science/paper/EEJUYERT"},"agent_actions":{"view_html":"https://pith.science/pith/EEJUYERTLNTVWSOZZBPNOWUXA3","download_json":"https://pith.science/pith/EEJUYERTLNTVWSOZZBPNOWUXA3.json","view_paper":"https://pith.science/paper/EEJUYERT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.05829&json=true","fetch_graph":"https://pith.science/api/pith-number/EEJUYERTLNTVWSOZZBPNOWUXA3/graph.json","fetch_events":"https://pith.science/api/pith-number/EEJUYERTLNTVWSOZZBPNOWUXA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEJUYERTLNTVWSOZZBPNOWUXA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEJUYERTLNTVWSOZZBPNOWUXA3/action/storage_attestation","attest_author":"https://pith.science/pith/EEJUYERTLNTVWSOZZBPNOWUXA3/action/author_attestation","sign_citation":"https://pith.science/pith/EEJUYERTLNTVWSOZZBPNOWUXA3/action/citation_signature","submit_replication":"https://pith.science/pith/EEJUYERTLNTVWSOZZBPNOWUXA3/action/replication_record"}},"created_at":"2026-07-05T00:04:18.925707+00:00","updated_at":"2026-07-05T00:04:18.925707+00:00"}