{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4ID2JR6DWBAXSZ5DWYEAT23RQI","short_pith_number":"pith:4ID2JR6D","schema_version":"1.0","canonical_sha256":"e207a4c7c3b0417967a3b60809eb71820e2170b3e0079add18a03b86da834aac","source":{"kind":"arxiv","id":"2006.05398","version":1},"attestation_state":"computed","paper":{"title":"Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Image","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":"Danny Driess, Jung-Su Ha, Marc Toussaint","submitted_at":"2020-06-09T16:52:02Z","abstract_excerpt":"In this paper, we propose a deep convolutional recurrent neural network that predicts action sequences for task and motion planning (TAMP) from an initial scene image. Typical TAMP problems are formalized by combining reasoning on a symbolic, discrete level (e.g. first-order logic) with continuous motion planning such as nonlinear trajectory optimization. Due to the great combinatorial complexity of possible discrete action sequences, a large number of optimization/motion planning problems have to be solved to find a solution, which limits the scalability of these approaches.\n  To circumvent t"},"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":"2006.05398","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-09T16:52:02Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO","stat.ML"],"title_canon_sha256":"a0db5059600f9cb5123c1836931a8e92308b8566b2ade1ed20802c46e1a1c634","abstract_canon_sha256":"8574c206066bf8d60ecc5ab3220ab79a4a6adf330afaff2e2a00624ca672d65b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:13.520325Z","signature_b64":"QDCZorv3ZG+be7IKtXcISXWsFUn2zfjWlmBuqA1798bZbyV+EO/0DNv24UJ0+qv/geP4naSSaOPpUnQ5Mqs8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e207a4c7c3b0417967a3b60809eb71820e2170b3e0079add18a03b86da834aac","last_reissued_at":"2026-07-05T01:09:13.519916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:13.519916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Image","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":"Danny Driess, Jung-Su Ha, Marc Toussaint","submitted_at":"2020-06-09T16:52:02Z","abstract_excerpt":"In this paper, we propose a deep convolutional recurrent neural network that predicts action sequences for task and motion planning (TAMP) from an initial scene image. Typical TAMP problems are formalized by combining reasoning on a symbolic, discrete level (e.g. first-order logic) with continuous motion planning such as nonlinear trajectory optimization. Due to the great combinatorial complexity of possible discrete action sequences, a large number of optimization/motion planning problems have to be solved to find a solution, which limits the scalability of these approaches.\n  To circumvent t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.05398","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/2006.05398/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":"2006.05398","created_at":"2026-07-05T01:09:13.519972+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.05398v1","created_at":"2026-07-05T01:09:13.519972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.05398","created_at":"2026-07-05T01:09:13.519972+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ID2JR6DWBAX","created_at":"2026-07-05T01:09:13.519972+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ID2JR6DWBAXSZ5D","created_at":"2026-07-05T01:09:13.519972+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ID2JR6D","created_at":"2026-07-05T01:09:13.519972+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01746","citing_title":"Fail2Progress: Learning from Real-World Robot Failures with Stein Variational Inference","ref_index":76,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ID2JR6DWBAXSZ5DWYEAT23RQI","json":"https://pith.science/pith/4ID2JR6DWBAXSZ5DWYEAT23RQI.json","graph_json":"https://pith.science/api/pith-number/4ID2JR6DWBAXSZ5DWYEAT23RQI/graph.json","events_json":"https://pith.science/api/pith-number/4ID2JR6DWBAXSZ5DWYEAT23RQI/events.json","paper":"https://pith.science/paper/4ID2JR6D"},"agent_actions":{"view_html":"https://pith.science/pith/4ID2JR6DWBAXSZ5DWYEAT23RQI","download_json":"https://pith.science/pith/4ID2JR6DWBAXSZ5DWYEAT23RQI.json","view_paper":"https://pith.science/paper/4ID2JR6D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.05398&json=true","fetch_graph":"https://pith.science/api/pith-number/4ID2JR6DWBAXSZ5DWYEAT23RQI/graph.json","fetch_events":"https://pith.science/api/pith-number/4ID2JR6DWBAXSZ5DWYEAT23RQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ID2JR6DWBAXSZ5DWYEAT23RQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ID2JR6DWBAXSZ5DWYEAT23RQI/action/storage_attestation","attest_author":"https://pith.science/pith/4ID2JR6DWBAXSZ5DWYEAT23RQI/action/author_attestation","sign_citation":"https://pith.science/pith/4ID2JR6DWBAXSZ5DWYEAT23RQI/action/citation_signature","submit_replication":"https://pith.science/pith/4ID2JR6DWBAXSZ5DWYEAT23RQI/action/replication_record"}},"created_at":"2026-07-05T01:09:13.519972+00:00","updated_at":"2026-07-05T01:09:13.519972+00:00"}