{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:D5HIIN3TGS7GCYD7NAQ5CDHDVC","short_pith_number":"pith:D5HIIN3T","schema_version":"1.0","canonical_sha256":"1f4e84377334be61607f6821d10ce3a88f12744a2f63be3713c26591ac592a0e","source":{"kind":"arxiv","id":"1609.09025","version":1},"attestation_state":"computed","paper":{"title":"Learning to Push by Grasping: Using multiple tasks for effective learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Abhinav Gupta, Lerrel Pinto","submitted_at":"2016-09-28T18:13:02Z","abstract_excerpt":"Recently, end-to-end learning frameworks are gaining prevalence in the field of robot control. These frameworks input states/images and directly predict the torques or the action parameters. However, these approaches are often critiqued due to their huge data requirements for learning a task. The argument of the difficulty in scalability to multiple tasks is well founded, since training these tasks often require hundreds or thousands of examples. But do end-to-end approaches need to learn a unique model for every task? Intuitively, it seems that sharing across tasks should help since all tasks"},"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":"1609.09025","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2016-09-28T18:13:02Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"e9611a5596c8369876a4d59645fedf8caed14430316e600459de59a9c04138aa","abstract_canon_sha256":"ab257e1acd9233c0d8d4ee3685de644c440836df3056fac525d9bd9150fab636"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:41.385093Z","signature_b64":"prpCg8cXPPNoiSiIUtKoB0isTxopBVQgMUqvAZBK0grIscsUxwXW0TtPbZgFvDwwijgeFPA+0B9ad4cw7RKoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f4e84377334be61607f6821d10ce3a88f12744a2f63be3713c26591ac592a0e","last_reissued_at":"2026-05-18T01:03:41.384657Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:41.384657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Push by Grasping: Using multiple tasks for effective learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Abhinav Gupta, Lerrel Pinto","submitted_at":"2016-09-28T18:13:02Z","abstract_excerpt":"Recently, end-to-end learning frameworks are gaining prevalence in the field of robot control. These frameworks input states/images and directly predict the torques or the action parameters. However, these approaches are often critiqued due to their huge data requirements for learning a task. The argument of the difficulty in scalability to multiple tasks is well founded, since training these tasks often require hundreds or thousands of examples. But do end-to-end approaches need to learn a unique model for every task? Intuitively, it seems that sharing across tasks should help since all tasks"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.09025","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":""},"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":"1609.09025","created_at":"2026-05-18T01:03:41.384741+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.09025v1","created_at":"2026-05-18T01:03:41.384741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.09025","created_at":"2026-05-18T01:03:41.384741+00:00"},{"alias_kind":"pith_short_12","alias_value":"D5HIIN3TGS7G","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_16","alias_value":"D5HIIN3TGS7GCYD7","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_8","alias_value":"D5HIIN3T","created_at":"2026-05-18T12:30:09.641336+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/D5HIIN3TGS7GCYD7NAQ5CDHDVC","json":"https://pith.science/pith/D5HIIN3TGS7GCYD7NAQ5CDHDVC.json","graph_json":"https://pith.science/api/pith-number/D5HIIN3TGS7GCYD7NAQ5CDHDVC/graph.json","events_json":"https://pith.science/api/pith-number/D5HIIN3TGS7GCYD7NAQ5CDHDVC/events.json","paper":"https://pith.science/paper/D5HIIN3T"},"agent_actions":{"view_html":"https://pith.science/pith/D5HIIN3TGS7GCYD7NAQ5CDHDVC","download_json":"https://pith.science/pith/D5HIIN3TGS7GCYD7NAQ5CDHDVC.json","view_paper":"https://pith.science/paper/D5HIIN3T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.09025&json=true","fetch_graph":"https://pith.science/api/pith-number/D5HIIN3TGS7GCYD7NAQ5CDHDVC/graph.json","fetch_events":"https://pith.science/api/pith-number/D5HIIN3TGS7GCYD7NAQ5CDHDVC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D5HIIN3TGS7GCYD7NAQ5CDHDVC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D5HIIN3TGS7GCYD7NAQ5CDHDVC/action/storage_attestation","attest_author":"https://pith.science/pith/D5HIIN3TGS7GCYD7NAQ5CDHDVC/action/author_attestation","sign_citation":"https://pith.science/pith/D5HIIN3TGS7GCYD7NAQ5CDHDVC/action/citation_signature","submit_replication":"https://pith.science/pith/D5HIIN3TGS7GCYD7NAQ5CDHDVC/action/replication_record"}},"created_at":"2026-05-18T01:03:41.384741+00:00","updated_at":"2026-05-18T01:03:41.384741+00:00"}