{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:75EGXQSKH6RTYBJZDRZ6JXQNS2","short_pith_number":"pith:75EGXQSK","schema_version":"1.0","canonical_sha256":"ff486bc24a3fa33c05391c73e4de0d9686ca1e140ceeed9d66a245186e233c1e","source":{"kind":"arxiv","id":"2110.14056","version":1},"attestation_state":"computed","paper":{"title":"How to transfer algorithmic reasoning knowledge to learn new algorithms?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreea Deac, Jian Tang, Louis-Pascal A. C. Xhonneux, Petar Velickovic","submitted_at":"2021-10-26T22:14:47Z","abstract_excerpt":"Learning to execute algorithms is a fundamental problem that has been widely studied. Prior work~\\cite{veli19neural} has shown that to enable systematic generalisation on graph algorithms it is critical to have access to the intermediate steps of the program/algorithm. In many reasoning tasks, where algorithmic-style reasoning is important, we only have access to the input and output examples. Thus, inspired by the success of pre-training on similar tasks or data in Natural Language Processing (NLP) and Computer Vision, we set out to study how we can transfer algorithmic reasoning knowledge. S"},"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":"2110.14056","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-26T22:14:47Z","cross_cats_sorted":[],"title_canon_sha256":"a76bf49b5bf7bc2409a3dd951b1762d7343ce42ac270fb5818409503c3a32aed","abstract_canon_sha256":"fb39b9643e64ee8576e6f5e088398227fcafc0122f987eb7fc43f9878084945e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:23.309013Z","signature_b64":"gcsIBTByAYFB0DTxsq86truNqFw330PDqGMDJGvNSTlKo0kMvwmQ0Rop344FZB7jYFZAsk1kwxQ40w5EG0pAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff486bc24a3fa33c05391c73e4de0d9686ca1e140ceeed9d66a245186e233c1e","last_reissued_at":"2026-07-05T03:26:23.308598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:23.308598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to transfer algorithmic reasoning knowledge to learn new algorithms?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreea Deac, Jian Tang, Louis-Pascal A. C. Xhonneux, Petar Velickovic","submitted_at":"2021-10-26T22:14:47Z","abstract_excerpt":"Learning to execute algorithms is a fundamental problem that has been widely studied. Prior work~\\cite{veli19neural} has shown that to enable systematic generalisation on graph algorithms it is critical to have access to the intermediate steps of the program/algorithm. In many reasoning tasks, where algorithmic-style reasoning is important, we only have access to the input and output examples. Thus, inspired by the success of pre-training on similar tasks or data in Natural Language Processing (NLP) and Computer Vision, we set out to study how we can transfer algorithmic reasoning knowledge. S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14056","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/2110.14056/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":"2110.14056","created_at":"2026-07-05T03:26:23.308658+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.14056v1","created_at":"2026-07-05T03:26:23.308658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14056","created_at":"2026-07-05T03:26:23.308658+00:00"},{"alias_kind":"pith_short_12","alias_value":"75EGXQSKH6RT","created_at":"2026-07-05T03:26:23.308658+00:00"},{"alias_kind":"pith_short_16","alias_value":"75EGXQSKH6RTYBJZ","created_at":"2026-07-05T03:26:23.308658+00:00"},{"alias_kind":"pith_short_8","alias_value":"75EGXQSK","created_at":"2026-07-05T03:26:23.308658+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/75EGXQSKH6RTYBJZDRZ6JXQNS2","json":"https://pith.science/pith/75EGXQSKH6RTYBJZDRZ6JXQNS2.json","graph_json":"https://pith.science/api/pith-number/75EGXQSKH6RTYBJZDRZ6JXQNS2/graph.json","events_json":"https://pith.science/api/pith-number/75EGXQSKH6RTYBJZDRZ6JXQNS2/events.json","paper":"https://pith.science/paper/75EGXQSK"},"agent_actions":{"view_html":"https://pith.science/pith/75EGXQSKH6RTYBJZDRZ6JXQNS2","download_json":"https://pith.science/pith/75EGXQSKH6RTYBJZDRZ6JXQNS2.json","view_paper":"https://pith.science/paper/75EGXQSK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.14056&json=true","fetch_graph":"https://pith.science/api/pith-number/75EGXQSKH6RTYBJZDRZ6JXQNS2/graph.json","fetch_events":"https://pith.science/api/pith-number/75EGXQSKH6RTYBJZDRZ6JXQNS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75EGXQSKH6RTYBJZDRZ6JXQNS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75EGXQSKH6RTYBJZDRZ6JXQNS2/action/storage_attestation","attest_author":"https://pith.science/pith/75EGXQSKH6RTYBJZDRZ6JXQNS2/action/author_attestation","sign_citation":"https://pith.science/pith/75EGXQSKH6RTYBJZDRZ6JXQNS2/action/citation_signature","submit_replication":"https://pith.science/pith/75EGXQSKH6RTYBJZDRZ6JXQNS2/action/replication_record"}},"created_at":"2026-07-05T03:26:23.308658+00:00","updated_at":"2026-07-05T03:26:23.308658+00:00"}