{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WWHYDUO6BQJYXDC3OB3ECKTUIV","short_pith_number":"pith:WWHYDUO6","schema_version":"1.0","canonical_sha256":"b58f81d1de0c138b8c5b7076412a74457281d082fc60ec320d17ac434b600833","source":{"kind":"arxiv","id":"1712.09687","version":1},"attestation_state":"computed","paper":{"title":"Combining Representation Learning with Logic for Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.LO"],"primary_cat":"cs.NE","authors_text":"Tim Rockt\\\"aschel","submitted_at":"2017-12-27T21:09:36Z","abstract_excerpt":"The current state-of-the-art in many natural language processing and automated knowledge base completion tasks is held by representation learning methods which learn distributed vector representations of symbols via gradient-based optimization. They require little or no hand-crafted features, thus avoiding the need for most preprocessing steps and task-specific assumptions. However, in many cases representation learning requires a large amount of annotated training data to generalize well to unseen data. Such labeled training data is provided by human annotators who often use formal logic as t"},"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":"1712.09687","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2017-12-27T21:09:36Z","cross_cats_sorted":["cs.CL","cs.LG","cs.LO"],"title_canon_sha256":"678b20981ddf389aaf94d2569ccda5d2ae17805cc2ffea955e1a8fb0ba6d80bb","abstract_canon_sha256":"060a79f005179c56ce7dece2e6c68fce7c42f241fa8a5e5ffc15e809524e3ab9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:07.605306Z","signature_b64":"jAgpQzxINH8RsVpQXWA8Dbf7JPr8abCPYgr6utPzzEybip8lrihmNmWDPXpuU2R9Cbvgyc+NYubJCL0+/0fiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b58f81d1de0c138b8c5b7076412a74457281d082fc60ec320d17ac434b600833","last_reissued_at":"2026-05-18T00:27:07.604639Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:07.604639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Combining Representation Learning with Logic for Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.LO"],"primary_cat":"cs.NE","authors_text":"Tim Rockt\\\"aschel","submitted_at":"2017-12-27T21:09:36Z","abstract_excerpt":"The current state-of-the-art in many natural language processing and automated knowledge base completion tasks is held by representation learning methods which learn distributed vector representations of symbols via gradient-based optimization. They require little or no hand-crafted features, thus avoiding the need for most preprocessing steps and task-specific assumptions. However, in many cases representation learning requires a large amount of annotated training data to generalize well to unseen data. Such labeled training data is provided by human annotators who often use formal logic as t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09687","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":"1712.09687","created_at":"2026-05-18T00:27:07.604756+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.09687v1","created_at":"2026-05-18T00:27:07.604756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09687","created_at":"2026-05-18T00:27:07.604756+00:00"},{"alias_kind":"pith_short_12","alias_value":"WWHYDUO6BQJY","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WWHYDUO6BQJYXDC3","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WWHYDUO6","created_at":"2026-05-18T12:31:53.515858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.04700","citing_title":"Semi-Supervised Learning using Differentiable Reasoning","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WWHYDUO6BQJYXDC3OB3ECKTUIV","json":"https://pith.science/pith/WWHYDUO6BQJYXDC3OB3ECKTUIV.json","graph_json":"https://pith.science/api/pith-number/WWHYDUO6BQJYXDC3OB3ECKTUIV/graph.json","events_json":"https://pith.science/api/pith-number/WWHYDUO6BQJYXDC3OB3ECKTUIV/events.json","paper":"https://pith.science/paper/WWHYDUO6"},"agent_actions":{"view_html":"https://pith.science/pith/WWHYDUO6BQJYXDC3OB3ECKTUIV","download_json":"https://pith.science/pith/WWHYDUO6BQJYXDC3OB3ECKTUIV.json","view_paper":"https://pith.science/paper/WWHYDUO6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.09687&json=true","fetch_graph":"https://pith.science/api/pith-number/WWHYDUO6BQJYXDC3OB3ECKTUIV/graph.json","fetch_events":"https://pith.science/api/pith-number/WWHYDUO6BQJYXDC3OB3ECKTUIV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WWHYDUO6BQJYXDC3OB3ECKTUIV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WWHYDUO6BQJYXDC3OB3ECKTUIV/action/storage_attestation","attest_author":"https://pith.science/pith/WWHYDUO6BQJYXDC3OB3ECKTUIV/action/author_attestation","sign_citation":"https://pith.science/pith/WWHYDUO6BQJYXDC3OB3ECKTUIV/action/citation_signature","submit_replication":"https://pith.science/pith/WWHYDUO6BQJYXDC3OB3ECKTUIV/action/replication_record"}},"created_at":"2026-05-18T00:27:07.604756+00:00","updated_at":"2026-05-18T00:27:07.604756+00:00"}