{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:D2R2OS5WVE5ZCRU5ZL2A6FUJGD","short_pith_number":"pith:D2R2OS5W","schema_version":"1.0","canonical_sha256":"1ea3a74bb6a93b91469dcaf40f168930ee00437167088704491d92aea0efa8f3","source":{"kind":"arxiv","id":"2109.07578","version":1},"attestation_state":"computed","paper":{"title":"Multi-Task Learning with Sequence-Conditioned Transporter Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Aleksandra Faust, Andy Zeng, Brian Ichter, Claire Tomlin, Erwin Coumans, Maryam Bandari, Michael H. Lim, Stefan Schaal","submitted_at":"2021-09-15T21:19:11Z","abstract_excerpt":"Enabling robots to solve multiple manipulation tasks has a wide range of industrial applications. While learning-based approaches enjoy flexibility and generalizability, scaling these approaches to solve such compositional tasks remains a challenge. In this work, we aim to solve multi-task learning through the lens of sequence-conditioning and weighted sampling. First, we propose a new suite of benchmark specifically aimed at compositional tasks, MultiRavens, which allows defining custom task combinations through task modules that are inspired by industrial tasks and exemplify the difficulties"},"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":"2109.07578","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-15T21:19:11Z","cross_cats_sorted":["cs.AI","cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"83cb4bd1761f17cbd33b222264601bcb78723df62acaf4d5b463e7e124ef740a","abstract_canon_sha256":"8791ee2c0c6f5c3bc33750ff1eb89eb42a4a5a6b22c4b0e6d714bcc250c7192b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:14:58.741092Z","signature_b64":"/JsVrP1kdWyoR56j70B5RzQJ2LD1A1P2sq+3VyjMtn4SPPSJI5CV1GLBB3PwbIvOwVv2QpaI/QZUEaCYt6JsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ea3a74bb6a93b91469dcaf40f168930ee00437167088704491d92aea0efa8f3","last_reissued_at":"2026-07-05T03:14:58.740675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:14:58.740675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Learning with Sequence-Conditioned Transporter Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Aleksandra Faust, Andy Zeng, Brian Ichter, Claire Tomlin, Erwin Coumans, Maryam Bandari, Michael H. Lim, Stefan Schaal","submitted_at":"2021-09-15T21:19:11Z","abstract_excerpt":"Enabling robots to solve multiple manipulation tasks has a wide range of industrial applications. While learning-based approaches enjoy flexibility and generalizability, scaling these approaches to solve such compositional tasks remains a challenge. In this work, we aim to solve multi-task learning through the lens of sequence-conditioning and weighted sampling. First, we propose a new suite of benchmark specifically aimed at compositional tasks, MultiRavens, which allows defining custom task combinations through task modules that are inspired by industrial tasks and exemplify the difficulties"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.07578","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/2109.07578/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":"2109.07578","created_at":"2026-07-05T03:14:58.740735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.07578v1","created_at":"2026-07-05T03:14:58.740735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.07578","created_at":"2026-07-05T03:14:58.740735+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2R2OS5WVE5Z","created_at":"2026-07-05T03:14:58.740735+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2R2OS5WVE5ZCRU5","created_at":"2026-07-05T03:14:58.740735+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2R2OS5W","created_at":"2026-07-05T03:14:58.740735+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/D2R2OS5WVE5ZCRU5ZL2A6FUJGD","json":"https://pith.science/pith/D2R2OS5WVE5ZCRU5ZL2A6FUJGD.json","graph_json":"https://pith.science/api/pith-number/D2R2OS5WVE5ZCRU5ZL2A6FUJGD/graph.json","events_json":"https://pith.science/api/pith-number/D2R2OS5WVE5ZCRU5ZL2A6FUJGD/events.json","paper":"https://pith.science/paper/D2R2OS5W"},"agent_actions":{"view_html":"https://pith.science/pith/D2R2OS5WVE5ZCRU5ZL2A6FUJGD","download_json":"https://pith.science/pith/D2R2OS5WVE5ZCRU5ZL2A6FUJGD.json","view_paper":"https://pith.science/paper/D2R2OS5W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.07578&json=true","fetch_graph":"https://pith.science/api/pith-number/D2R2OS5WVE5ZCRU5ZL2A6FUJGD/graph.json","fetch_events":"https://pith.science/api/pith-number/D2R2OS5WVE5ZCRU5ZL2A6FUJGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2R2OS5WVE5ZCRU5ZL2A6FUJGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2R2OS5WVE5ZCRU5ZL2A6FUJGD/action/storage_attestation","attest_author":"https://pith.science/pith/D2R2OS5WVE5ZCRU5ZL2A6FUJGD/action/author_attestation","sign_citation":"https://pith.science/pith/D2R2OS5WVE5ZCRU5ZL2A6FUJGD/action/citation_signature","submit_replication":"https://pith.science/pith/D2R2OS5WVE5ZCRU5ZL2A6FUJGD/action/replication_record"}},"created_at":"2026-07-05T03:14:58.740735+00:00","updated_at":"2026-07-05T03:14:58.740735+00:00"}