{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SFEIQNEAT7EGH5AOQVSUEDWGLT","short_pith_number":"pith:SFEIQNEA","schema_version":"1.0","canonical_sha256":"91488834809fc863f40e8565420ec65cefe7e83d3c32792f88865b78417efe7e","source":{"kind":"arxiv","id":"1809.00653","version":1},"attestation_state":"computed","paper":{"title":"Towards Dynamic Computation Graphs via Sparse Latent Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Andr\\'e F. T. Martins, Claire Cardie, Vlad Niculae","submitted_at":"2018-09-03T16:52:19Z","abstract_excerpt":"Deep NLP models benefit from underlying structures in the data---e.g., parse trees---typically extracted using off-the-shelf parsers. Recent attempts to jointly learn the latent structure encounter a tradeoff: either make factorization assumptions that limit expressiveness, or sacrifice end-to-end differentiability. Using the recently proposed SparseMAP inference, which retrieves a sparse distribution over latent structures, we propose a novel approach for end-to-end learning of latent structure predictors jointly with a downstream predictor. To the best of our knowledge, our method is the fir"},"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":"1809.00653","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-03T16:52:19Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f6aa6f6549c9068b06e572fe0d8faa8e1e086006f7a78bd2c5e9315b43543e1b","abstract_canon_sha256":"3509c595d733b83177a9528099ddef67630fa9d46f2be9bd22ccad78ed801d84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:32.863080Z","signature_b64":"zZ3LuT1LBpvuGNRdk7JehaQrelIYsZpbYPDxfc+fO02D/Xy8ScuKUjppWJPLAELmX6GX6iRdtEMXQnBS26dKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91488834809fc863f40e8565420ec65cefe7e83d3c32792f88865b78417efe7e","last_reissued_at":"2026-05-18T00:06:32.862371Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:32.862371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Dynamic Computation Graphs via Sparse Latent Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Andr\\'e F. T. Martins, Claire Cardie, Vlad Niculae","submitted_at":"2018-09-03T16:52:19Z","abstract_excerpt":"Deep NLP models benefit from underlying structures in the data---e.g., parse trees---typically extracted using off-the-shelf parsers. Recent attempts to jointly learn the latent structure encounter a tradeoff: either make factorization assumptions that limit expressiveness, or sacrifice end-to-end differentiability. Using the recently proposed SparseMAP inference, which retrieves a sparse distribution over latent structures, we propose a novel approach for end-to-end learning of latent structure predictors jointly with a downstream predictor. To the best of our knowledge, our method is the fir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.00653","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":"1809.00653","created_at":"2026-05-18T00:06:32.862485+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.00653v1","created_at":"2026-05-18T00:06:32.862485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.00653","created_at":"2026-05-18T00:06:32.862485+00:00"},{"alias_kind":"pith_short_12","alias_value":"SFEIQNEAT7EG","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SFEIQNEAT7EGH5AO","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SFEIQNEA","created_at":"2026-05-18T12:32:53.628368+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/SFEIQNEAT7EGH5AOQVSUEDWGLT","json":"https://pith.science/pith/SFEIQNEAT7EGH5AOQVSUEDWGLT.json","graph_json":"https://pith.science/api/pith-number/SFEIQNEAT7EGH5AOQVSUEDWGLT/graph.json","events_json":"https://pith.science/api/pith-number/SFEIQNEAT7EGH5AOQVSUEDWGLT/events.json","paper":"https://pith.science/paper/SFEIQNEA"},"agent_actions":{"view_html":"https://pith.science/pith/SFEIQNEAT7EGH5AOQVSUEDWGLT","download_json":"https://pith.science/pith/SFEIQNEAT7EGH5AOQVSUEDWGLT.json","view_paper":"https://pith.science/paper/SFEIQNEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.00653&json=true","fetch_graph":"https://pith.science/api/pith-number/SFEIQNEAT7EGH5AOQVSUEDWGLT/graph.json","fetch_events":"https://pith.science/api/pith-number/SFEIQNEAT7EGH5AOQVSUEDWGLT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SFEIQNEAT7EGH5AOQVSUEDWGLT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SFEIQNEAT7EGH5AOQVSUEDWGLT/action/storage_attestation","attest_author":"https://pith.science/pith/SFEIQNEAT7EGH5AOQVSUEDWGLT/action/author_attestation","sign_citation":"https://pith.science/pith/SFEIQNEAT7EGH5AOQVSUEDWGLT/action/citation_signature","submit_replication":"https://pith.science/pith/SFEIQNEAT7EGH5AOQVSUEDWGLT/action/replication_record"}},"created_at":"2026-05-18T00:06:32.862485+00:00","updated_at":"2026-05-18T00:06:32.862485+00:00"}