{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:O7UXBD4NQYFGYZ5ZOS3UOBBHZY","short_pith_number":"pith:O7UXBD4N","schema_version":"1.0","canonical_sha256":"77e9708f8d860a6c67b974b7470427ce183d6418f058a7ead361cc2f74b85bda","source":{"kind":"arxiv","id":"1910.06611","version":2},"attestation_state":"computed","paper":{"title":"Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Imanol Schlag, Jianfeng Gao, J\\\"urgen Schmidhuber, Nebojsa Jojic, Paul Smolensky, Roland Fernandez","submitted_at":"2019-10-15T09:19:55Z","abstract_excerpt":"We incorporate Tensor-Product Representations within the Transformer in order to better support the explicit representation of relation structure. Our Tensor-Product Transformer (TP-Transformer) sets a new state of the art on the recently-introduced Mathematics Dataset containing 56 categories of free-form math word-problems. The essential component of the model is a novel attention mechanism, called TP-Attention, which explicitly encodes the relations between each Transformer cell and the other cells from which values have been retrieved by attention. TP-Attention goes beyond linear combinati"},"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":"1910.06611","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-10-15T09:19:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9fc5b92882ef927e2d83fa65b0931fa3e803ad6ec2ae696a46ee88c56b6ea742","abstract_canon_sha256":"500dc674caa688c3cdaf1f8de9a9ee8d8d925e7541f8d389676bef44247c5089"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:00.854142Z","signature_b64":"9pDe+2t+tQJJu+7Ha/l3lxa7xJ7YEsDwcwyqVoRMRcahN+JkTurvdAmpaiFYBXelySxW5PzMI26H3OZ6oJrCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77e9708f8d860a6c67b974b7470427ce183d6418f058a7ead361cc2f74b85bda","last_reissued_at":"2026-07-05T01:49:00.853696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:00.853696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Imanol Schlag, Jianfeng Gao, J\\\"urgen Schmidhuber, Nebojsa Jojic, Paul Smolensky, Roland Fernandez","submitted_at":"2019-10-15T09:19:55Z","abstract_excerpt":"We incorporate Tensor-Product Representations within the Transformer in order to better support the explicit representation of relation structure. Our Tensor-Product Transformer (TP-Transformer) sets a new state of the art on the recently-introduced Mathematics Dataset containing 56 categories of free-form math word-problems. The essential component of the model is a novel attention mechanism, called TP-Attention, which explicitly encodes the relations between each Transformer cell and the other cells from which values have been retrieved by attention. TP-Attention goes beyond linear combinati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.06611","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/1910.06611/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":"1910.06611","created_at":"2026-07-05T01:49:00.853752+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.06611v2","created_at":"2026-07-05T01:49:00.853752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.06611","created_at":"2026-07-05T01:49:00.853752+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7UXBD4NQYFG","created_at":"2026-07-05T01:49:00.853752+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7UXBD4NQYFGYZ5Z","created_at":"2026-07-05T01:49:00.853752+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7UXBD4N","created_at":"2026-07-05T01:49:00.853752+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.07143","citing_title":"Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2102.01293","citing_title":"Scaling Laws for Transfer","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2010.14701","citing_title":"Scaling Laws for Autoregressive Generative Modeling","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2006.03654","citing_title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09967","citing_title":"Tensor Product Representation Probes Reveal Shared Structure Across Linear Directions","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2112.00861","citing_title":"A General Language Assistant as a Laboratory for Alignment","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05221","citing_title":"Language Models (Mostly) Know What They Know","ref_index":119,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7UXBD4NQYFGYZ5ZOS3UOBBHZY","json":"https://pith.science/pith/O7UXBD4NQYFGYZ5ZOS3UOBBHZY.json","graph_json":"https://pith.science/api/pith-number/O7UXBD4NQYFGYZ5ZOS3UOBBHZY/graph.json","events_json":"https://pith.science/api/pith-number/O7UXBD4NQYFGYZ5ZOS3UOBBHZY/events.json","paper":"https://pith.science/paper/O7UXBD4N"},"agent_actions":{"view_html":"https://pith.science/pith/O7UXBD4NQYFGYZ5ZOS3UOBBHZY","download_json":"https://pith.science/pith/O7UXBD4NQYFGYZ5ZOS3UOBBHZY.json","view_paper":"https://pith.science/paper/O7UXBD4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.06611&json=true","fetch_graph":"https://pith.science/api/pith-number/O7UXBD4NQYFGYZ5ZOS3UOBBHZY/graph.json","fetch_events":"https://pith.science/api/pith-number/O7UXBD4NQYFGYZ5ZOS3UOBBHZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7UXBD4NQYFGYZ5ZOS3UOBBHZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7UXBD4NQYFGYZ5ZOS3UOBBHZY/action/storage_attestation","attest_author":"https://pith.science/pith/O7UXBD4NQYFGYZ5ZOS3UOBBHZY/action/author_attestation","sign_citation":"https://pith.science/pith/O7UXBD4NQYFGYZ5ZOS3UOBBHZY/action/citation_signature","submit_replication":"https://pith.science/pith/O7UXBD4NQYFGYZ5ZOS3UOBBHZY/action/replication_record"}},"created_at":"2026-07-05T01:49:00.853752+00:00","updated_at":"2026-07-05T01:49:00.853752+00:00"}