{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WANE5K5ZP3KPBUXOVNELX4UOU5","short_pith_number":"pith:WANE5K5Z","schema_version":"1.0","canonical_sha256":"b01a4eabb97ed4f0d2eeab48bbf28ea75b82deeb29c2ea5aec3bc485c9fed9d5","source":{"kind":"arxiv","id":"1710.04157","version":1},"attestation_state":"computed","paper":{"title":"Neural Program Meta-Induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jacob Devlin, Matthew Hausknecht, Pushmeet Kohli, Rishabh Singh, Rudy Bunel","submitted_at":"2017-10-11T16:29:38Z","abstract_excerpt":"Most recently proposed methods for Neural Program Induction work under the assumption of having a large set of input/output (I/O) examples for learning any underlying input-output mapping. This paper aims to address the problem of data and computation efficiency of program induction by leveraging information from related tasks. Specifically, we propose two approaches for cross-task knowledge transfer to improve program induction in limited-data scenarios. In our first proposal, portfolio adaptation, a set of induction models is pretrained on a set of related tasks, and the best model is adapte"},"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":"1710.04157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-11T16:29:38Z","cross_cats_sorted":[],"title_canon_sha256":"8686c7c74f85a65a4690e5f9de285e0f4dc9645f6db1a69a52b0fa13fa5761ca","abstract_canon_sha256":"48774136288b728ce3c78c915b1fbe17ee9b8493ef048a3591310ebe846a4ba5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:04.738953Z","signature_b64":"w9V5/3De2QlK7W/ij1ITDwA7CJcLOiAzDnM2/faSl/EB9zrTzpKDTYp5sF9TWOakV1zxTcr5fDGGowrrxNCUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b01a4eabb97ed4f0d2eeab48bbf28ea75b82deeb29c2ea5aec3bc485c9fed9d5","last_reissued_at":"2026-05-18T00:33:04.738432Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:04.738432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Program Meta-Induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jacob Devlin, Matthew Hausknecht, Pushmeet Kohli, Rishabh Singh, Rudy Bunel","submitted_at":"2017-10-11T16:29:38Z","abstract_excerpt":"Most recently proposed methods for Neural Program Induction work under the assumption of having a large set of input/output (I/O) examples for learning any underlying input-output mapping. This paper aims to address the problem of data and computation efficiency of program induction by leveraging information from related tasks. Specifically, we propose two approaches for cross-task knowledge transfer to improve program induction in limited-data scenarios. In our first proposal, portfolio adaptation, a set of induction models is pretrained on a set of related tasks, and the best model is adapte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.04157","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":"1710.04157","created_at":"2026-05-18T00:33:04.738513+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.04157v1","created_at":"2026-05-18T00:33:04.738513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.04157","created_at":"2026-05-18T00:33:04.738513+00:00"},{"alias_kind":"pith_short_12","alias_value":"WANE5K5ZP3KP","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WANE5K5ZP3KPBUXO","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WANE5K5Z","created_at":"2026-05-18T12:31:53.515858+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/WANE5K5ZP3KPBUXOVNELX4UOU5","json":"https://pith.science/pith/WANE5K5ZP3KPBUXOVNELX4UOU5.json","graph_json":"https://pith.science/api/pith-number/WANE5K5ZP3KPBUXOVNELX4UOU5/graph.json","events_json":"https://pith.science/api/pith-number/WANE5K5ZP3KPBUXOVNELX4UOU5/events.json","paper":"https://pith.science/paper/WANE5K5Z"},"agent_actions":{"view_html":"https://pith.science/pith/WANE5K5ZP3KPBUXOVNELX4UOU5","download_json":"https://pith.science/pith/WANE5K5ZP3KPBUXOVNELX4UOU5.json","view_paper":"https://pith.science/paper/WANE5K5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.04157&json=true","fetch_graph":"https://pith.science/api/pith-number/WANE5K5ZP3KPBUXOVNELX4UOU5/graph.json","fetch_events":"https://pith.science/api/pith-number/WANE5K5ZP3KPBUXOVNELX4UOU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WANE5K5ZP3KPBUXOVNELX4UOU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WANE5K5ZP3KPBUXOVNELX4UOU5/action/storage_attestation","attest_author":"https://pith.science/pith/WANE5K5ZP3KPBUXOVNELX4UOU5/action/author_attestation","sign_citation":"https://pith.science/pith/WANE5K5ZP3KPBUXOVNELX4UOU5/action/citation_signature","submit_replication":"https://pith.science/pith/WANE5K5ZP3KPBUXOVNELX4UOU5/action/replication_record"}},"created_at":"2026-05-18T00:33:04.738513+00:00","updated_at":"2026-05-18T00:33:04.738513+00:00"}