{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5IFOTA7L276BOKSRR3P3GIY72T","short_pith_number":"pith:5IFOTA7L","schema_version":"1.0","canonical_sha256":"ea0ae983ebd7fc172a518edfb3231fd4f875df20b1c277b3a3efd3a245e6a431","source":{"kind":"arxiv","id":"2007.06477","version":3},"attestation_state":"computed","paper":{"title":"Learning Reasoning Strategies in End-to-End Differentiable Proving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.NE","cs.SC"],"primary_cat":"cs.AI","authors_text":"Edward Grefenstette, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel, Tim Rockt\\\"aschel","submitted_at":"2020-07-13T16:22:14Z","abstract_excerpt":"Attempts to render deep learning models interpretable, data-efficient, and robust have seen some success through hybridisation with rule-based systems, for example, in Neural Theorem Provers (NTPs). These neuro-symbolic models can induce interpretable rules and learn representations from data via back-propagation, while providing logical explanations for their predictions. However, they are restricted by their computational complexity, as they need to consider all possible proof paths for explaining a goal, thus rendering them unfit for large-scale applications. We present Conditional Theorem "},"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":"2007.06477","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-07-13T16:22:14Z","cross_cats_sorted":["cs.CL","cs.LG","cs.NE","cs.SC"],"title_canon_sha256":"404fec07b0231e462fa36595a31c6168c9e20c68fe4ed9303a40b8600a8cbdf4","abstract_canon_sha256":"c6b7a798f643959695dcf3a4aa4a9f25760cd4c6bb9b479b3e2e36efb8a58148"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:29:13.590892Z","signature_b64":"8djjmhwHMtTvUKqJ49VlRf+f4k+qZKKpQ0Z1BxwAmEL1ydwPzF8MHQIEYpYjGZuxwNr9EwIp/Mkrf8LQJbPtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea0ae983ebd7fc172a518edfb3231fd4f875df20b1c277b3a3efd3a245e6a431","last_reissued_at":"2026-07-05T01:29:13.590451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:29:13.590451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Reasoning Strategies in End-to-End Differentiable Proving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.NE","cs.SC"],"primary_cat":"cs.AI","authors_text":"Edward Grefenstette, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel, Tim Rockt\\\"aschel","submitted_at":"2020-07-13T16:22:14Z","abstract_excerpt":"Attempts to render deep learning models interpretable, data-efficient, and robust have seen some success through hybridisation with rule-based systems, for example, in Neural Theorem Provers (NTPs). These neuro-symbolic models can induce interpretable rules and learn representations from data via back-propagation, while providing logical explanations for their predictions. However, they are restricted by their computational complexity, as they need to consider all possible proof paths for explaining a goal, thus rendering them unfit for large-scale applications. We present Conditional Theorem "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.06477","kind":"arxiv","version":3},"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/2007.06477/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":"2007.06477","created_at":"2026-07-05T01:29:13.590515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.06477v3","created_at":"2026-07-05T01:29:13.590515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.06477","created_at":"2026-07-05T01:29:13.590515+00:00"},{"alias_kind":"pith_short_12","alias_value":"5IFOTA7L276B","created_at":"2026-07-05T01:29:13.590515+00:00"},{"alias_kind":"pith_short_16","alias_value":"5IFOTA7L276BOKSR","created_at":"2026-07-05T01:29:13.590515+00:00"},{"alias_kind":"pith_short_8","alias_value":"5IFOTA7L","created_at":"2026-07-05T01:29:13.590515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.01246","citing_title":"Large Language Model-Enhanced Symbolic Reasoning for Knowledge Base Completion","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5IFOTA7L276BOKSRR3P3GIY72T","json":"https://pith.science/pith/5IFOTA7L276BOKSRR3P3GIY72T.json","graph_json":"https://pith.science/api/pith-number/5IFOTA7L276BOKSRR3P3GIY72T/graph.json","events_json":"https://pith.science/api/pith-number/5IFOTA7L276BOKSRR3P3GIY72T/events.json","paper":"https://pith.science/paper/5IFOTA7L"},"agent_actions":{"view_html":"https://pith.science/pith/5IFOTA7L276BOKSRR3P3GIY72T","download_json":"https://pith.science/pith/5IFOTA7L276BOKSRR3P3GIY72T.json","view_paper":"https://pith.science/paper/5IFOTA7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.06477&json=true","fetch_graph":"https://pith.science/api/pith-number/5IFOTA7L276BOKSRR3P3GIY72T/graph.json","fetch_events":"https://pith.science/api/pith-number/5IFOTA7L276BOKSRR3P3GIY72T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5IFOTA7L276BOKSRR3P3GIY72T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5IFOTA7L276BOKSRR3P3GIY72T/action/storage_attestation","attest_author":"https://pith.science/pith/5IFOTA7L276BOKSRR3P3GIY72T/action/author_attestation","sign_citation":"https://pith.science/pith/5IFOTA7L276BOKSRR3P3GIY72T/action/citation_signature","submit_replication":"https://pith.science/pith/5IFOTA7L276BOKSRR3P3GIY72T/action/replication_record"}},"created_at":"2026-07-05T01:29:13.590515+00:00","updated_at":"2026-07-05T01:29:13.590515+00:00"}