{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YSFJUMWQVSF4JKO35WEBO47SON","short_pith_number":"pith:YSFJUMWQ","schema_version":"1.0","canonical_sha256":"c48a9a32d0ac8bc4a9dbed881773f2737e28cb7d129fe0ee5b8bc688661d0d34","source":{"kind":"arxiv","id":"1909.07328","version":2},"attestation_state":"computed","paper":{"title":"Learning Invariants through Soft Unification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandra Russo, Nuri Cingillioglu","submitted_at":"2019-09-16T16:48:52Z","abstract_excerpt":"Human reasoning involves recognising common underlying principles across many examples. The by-products of such reasoning are invariants that capture patterns such as \"if someone went somewhere then they are there\", expressed using variables \"someone\" and \"somewhere\" instead of mentioning specific people or places. Humans learn what variables are and how to use them at a young age. This paper explores whether machines can also learn and use variables solely from examples without requiring human pre-engineering. We propose Unification Networks, an end-to-end differentiable neural network approa"},"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":"1909.07328","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-16T16:48:52Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3179164da17b727e1bccf569d140b9e8899f1db296bbb84402d1f1c1535402b4","abstract_canon_sha256":"b8b70eb344fd25428e66781a647bd469a00b3edfb75e4fa88e796848d5c9aa16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:40.387506Z","signature_b64":"7hqObC/2uOoN617y9Spv6fOBiakW+/NCNDUaNLD9vk/Bc/FNYRssE1z9m9zsUOhI7vq4kDKsz4iC2ZTsEjVaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c48a9a32d0ac8bc4a9dbed881773f2737e28cb7d129fe0ee5b8bc688661d0d34","last_reissued_at":"2026-07-05T01:45:40.387083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:40.387083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Invariants through Soft Unification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandra Russo, Nuri Cingillioglu","submitted_at":"2019-09-16T16:48:52Z","abstract_excerpt":"Human reasoning involves recognising common underlying principles across many examples. The by-products of such reasoning are invariants that capture patterns such as \"if someone went somewhere then they are there\", expressed using variables \"someone\" and \"somewhere\" instead of mentioning specific people or places. Humans learn what variables are and how to use them at a young age. This paper explores whether machines can also learn and use variables solely from examples without requiring human pre-engineering. We propose Unification Networks, an end-to-end differentiable neural network approa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.07328","kind":"arxiv","version":2},"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/1909.07328/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":"1909.07328","created_at":"2026-07-05T01:45:40.387139+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.07328v2","created_at":"2026-07-05T01:45:40.387139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.07328","created_at":"2026-07-05T01:45:40.387139+00:00"},{"alias_kind":"pith_short_12","alias_value":"YSFJUMWQVSF4","created_at":"2026-07-05T01:45:40.387139+00:00"},{"alias_kind":"pith_short_16","alias_value":"YSFJUMWQVSF4JKO3","created_at":"2026-07-05T01:45:40.387139+00:00"},{"alias_kind":"pith_short_8","alias_value":"YSFJUMWQ","created_at":"2026-07-05T01:45:40.387139+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09209","citing_title":"On LLM-generated Logic Programs and their Inference Execution Methods","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YSFJUMWQVSF4JKO35WEBO47SON","json":"https://pith.science/pith/YSFJUMWQVSF4JKO35WEBO47SON.json","graph_json":"https://pith.science/api/pith-number/YSFJUMWQVSF4JKO35WEBO47SON/graph.json","events_json":"https://pith.science/api/pith-number/YSFJUMWQVSF4JKO35WEBO47SON/events.json","paper":"https://pith.science/paper/YSFJUMWQ"},"agent_actions":{"view_html":"https://pith.science/pith/YSFJUMWQVSF4JKO35WEBO47SON","download_json":"https://pith.science/pith/YSFJUMWQVSF4JKO35WEBO47SON.json","view_paper":"https://pith.science/paper/YSFJUMWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.07328&json=true","fetch_graph":"https://pith.science/api/pith-number/YSFJUMWQVSF4JKO35WEBO47SON/graph.json","fetch_events":"https://pith.science/api/pith-number/YSFJUMWQVSF4JKO35WEBO47SON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YSFJUMWQVSF4JKO35WEBO47SON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YSFJUMWQVSF4JKO35WEBO47SON/action/storage_attestation","attest_author":"https://pith.science/pith/YSFJUMWQVSF4JKO35WEBO47SON/action/author_attestation","sign_citation":"https://pith.science/pith/YSFJUMWQVSF4JKO35WEBO47SON/action/citation_signature","submit_replication":"https://pith.science/pith/YSFJUMWQVSF4JKO35WEBO47SON/action/replication_record"}},"created_at":"2026-07-05T01:45:40.387139+00:00","updated_at":"2026-07-05T01:45:40.387139+00:00"}