{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JFA7T2W6RWDP2RHCK5ZWXJS7TT","short_pith_number":"pith:JFA7T2W6","schema_version":"1.0","canonical_sha256":"4941f9eade8d86fd44e257736ba65f9ce7e6a7e0a987f5c041316f368988f0b1","source":{"kind":"arxiv","id":"2006.04843","version":2},"attestation_state":"computed","paper":{"title":"Modeling Long-horizon Tasks as Sequential Interaction Landscapes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Alexander Toshev, Karol Hausman, Mohi Khansari, S\\\"oren Pirk","submitted_at":"2020-06-08T18:07:18Z","abstract_excerpt":"Complex object manipulation tasks often span over long sequences of operations. Task planning over long-time horizons is a challenging and open problem in robotics, and its complexity grows exponentially with an increasing number of subtasks. In this paper we present a deep learning network that learns dependencies and transitions across subtasks solely from a set of demonstration videos. We represent each subtask as an action symbol (e.g. move cup), and show that these symbols can be learned and predicted directly from image observations. Learning from demonstrations and visual observations a"},"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":"2006.04843","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-06-08T18:07:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5639abdef436203c78825a2733d53f7f2cca04a4a45258298ea3fe506a275e77","abstract_canon_sha256":"25aee72302dfb8d1e8dc0e741b173d087213f92533e50181611c9a5c697807c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:43.091163Z","signature_b64":"NdyUjqGv7iiRLZKU0cnO+JHGkONMrWP6uwka5lTIBrpfGnAkcG5Nj26NgS4xG3w037tiH2K0Fvvc070v5MdtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4941f9eade8d86fd44e257736ba65f9ce7e6a7e0a987f5c041316f368988f0b1","last_reissued_at":"2026-07-05T01:45:43.090760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:43.090760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Long-horizon Tasks as Sequential Interaction Landscapes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Alexander Toshev, Karol Hausman, Mohi Khansari, S\\\"oren Pirk","submitted_at":"2020-06-08T18:07:18Z","abstract_excerpt":"Complex object manipulation tasks often span over long sequences of operations. Task planning over long-time horizons is a challenging and open problem in robotics, and its complexity grows exponentially with an increasing number of subtasks. In this paper we present a deep learning network that learns dependencies and transitions across subtasks solely from a set of demonstration videos. We represent each subtask as an action symbol (e.g. move cup), and show that these symbols can be learned and predicted directly from image observations. Learning from demonstrations and visual observations a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04843","kind":"arxiv","version":2},"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/2006.04843/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":"2006.04843","created_at":"2026-07-05T01:45:43.090817+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.04843v2","created_at":"2026-07-05T01:45:43.090817+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04843","created_at":"2026-07-05T01:45:43.090817+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFA7T2W6RWDP","created_at":"2026-07-05T01:45:43.090817+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFA7T2W6RWDP2RHC","created_at":"2026-07-05T01:45:43.090817+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFA7T2W6","created_at":"2026-07-05T01:45:43.090817+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2207.05608","citing_title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFA7T2W6RWDP2RHCK5ZWXJS7TT","json":"https://pith.science/pith/JFA7T2W6RWDP2RHCK5ZWXJS7TT.json","graph_json":"https://pith.science/api/pith-number/JFA7T2W6RWDP2RHCK5ZWXJS7TT/graph.json","events_json":"https://pith.science/api/pith-number/JFA7T2W6RWDP2RHCK5ZWXJS7TT/events.json","paper":"https://pith.science/paper/JFA7T2W6"},"agent_actions":{"view_html":"https://pith.science/pith/JFA7T2W6RWDP2RHCK5ZWXJS7TT","download_json":"https://pith.science/pith/JFA7T2W6RWDP2RHCK5ZWXJS7TT.json","view_paper":"https://pith.science/paper/JFA7T2W6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.04843&json=true","fetch_graph":"https://pith.science/api/pith-number/JFA7T2W6RWDP2RHCK5ZWXJS7TT/graph.json","fetch_events":"https://pith.science/api/pith-number/JFA7T2W6RWDP2RHCK5ZWXJS7TT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFA7T2W6RWDP2RHCK5ZWXJS7TT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFA7T2W6RWDP2RHCK5ZWXJS7TT/action/storage_attestation","attest_author":"https://pith.science/pith/JFA7T2W6RWDP2RHCK5ZWXJS7TT/action/author_attestation","sign_citation":"https://pith.science/pith/JFA7T2W6RWDP2RHCK5ZWXJS7TT/action/citation_signature","submit_replication":"https://pith.science/pith/JFA7T2W6RWDP2RHCK5ZWXJS7TT/action/replication_record"}},"created_at":"2026-07-05T01:45:43.090817+00:00","updated_at":"2026-07-05T01:45:43.090817+00:00"}