{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FOJWSEPDEEMEU4V2RCKBPM6LPU","short_pith_number":"pith:FOJWSEPD","schema_version":"1.0","canonical_sha256":"2b936911e321184a72ba889417b3cb7d09fc28c828a47922d987171fbbdeb3db","source":{"kind":"arxiv","id":"1709.01121","version":2},"attestation_state":"computed","paper":{"title":"Do latent tree learning models identify meaningful structure in sentences?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adina Williams, Andrew Drozdov, Samuel R. Bowman","submitted_at":"2017-09-04T19:05:39Z","abstract_excerpt":"Recent work on the problem of latent tree learning has made it possible to train neural networks that learn to both parse a sentence and use the resulting parse to interpret the sentence, all without exposure to ground-truth parse trees at training time. Surprisingly, these models often perform better at sentence understanding tasks than models that use parse trees from conventional parsers. This paper aims to investigate what these latent tree learning models learn. We replicate two such models in a shared codebase and find that (i) only one of these models outperforms conventional tree-struc"},"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":"1709.01121","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-04T19:05:39Z","cross_cats_sorted":[],"title_canon_sha256":"3cecd1d897eaf614bfdd0dd860e24503a247911a8d1255fcea03cc6a9ca173c3","abstract_canon_sha256":"9665b4cc1ad40326618a50e9e1f63609546f953dab63fbdd4fbce9658756b9e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:39.586880Z","signature_b64":"m3177RdaRS8y6hTMjfIoSdQLhkMR2VIbebaGaEI6C/TgXAqjAiDTl18XC9BvygE+ptaruf+O0mVOTq1+XlbbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b936911e321184a72ba889417b3cb7d09fc28c828a47922d987171fbbdeb3db","last_reissued_at":"2026-05-18T00:22:39.586532Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:39.586532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do latent tree learning models identify meaningful structure in sentences?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adina Williams, Andrew Drozdov, Samuel R. Bowman","submitted_at":"2017-09-04T19:05:39Z","abstract_excerpt":"Recent work on the problem of latent tree learning has made it possible to train neural networks that learn to both parse a sentence and use the resulting parse to interpret the sentence, all without exposure to ground-truth parse trees at training time. Surprisingly, these models often perform better at sentence understanding tasks than models that use parse trees from conventional parsers. This paper aims to investigate what these latent tree learning models learn. We replicate two such models in a shared codebase and find that (i) only one of these models outperforms conventional tree-struc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.01121","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":""},"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":"1709.01121","created_at":"2026-05-18T00:22:39.586587+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.01121v2","created_at":"2026-05-18T00:22:39.586587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.01121","created_at":"2026-05-18T00:22:39.586587+00:00"},{"alias_kind":"pith_short_12","alias_value":"FOJWSEPDEEME","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FOJWSEPDEEMEU4V2","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FOJWSEPD","created_at":"2026-05-18T12:31:15.632608+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/FOJWSEPDEEMEU4V2RCKBPM6LPU","json":"https://pith.science/pith/FOJWSEPDEEMEU4V2RCKBPM6LPU.json","graph_json":"https://pith.science/api/pith-number/FOJWSEPDEEMEU4V2RCKBPM6LPU/graph.json","events_json":"https://pith.science/api/pith-number/FOJWSEPDEEMEU4V2RCKBPM6LPU/events.json","paper":"https://pith.science/paper/FOJWSEPD"},"agent_actions":{"view_html":"https://pith.science/pith/FOJWSEPDEEMEU4V2RCKBPM6LPU","download_json":"https://pith.science/pith/FOJWSEPDEEMEU4V2RCKBPM6LPU.json","view_paper":"https://pith.science/paper/FOJWSEPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.01121&json=true","fetch_graph":"https://pith.science/api/pith-number/FOJWSEPDEEMEU4V2RCKBPM6LPU/graph.json","fetch_events":"https://pith.science/api/pith-number/FOJWSEPDEEMEU4V2RCKBPM6LPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FOJWSEPDEEMEU4V2RCKBPM6LPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FOJWSEPDEEMEU4V2RCKBPM6LPU/action/storage_attestation","attest_author":"https://pith.science/pith/FOJWSEPDEEMEU4V2RCKBPM6LPU/action/author_attestation","sign_citation":"https://pith.science/pith/FOJWSEPDEEMEU4V2RCKBPM6LPU/action/citation_signature","submit_replication":"https://pith.science/pith/FOJWSEPDEEMEU4V2RCKBPM6LPU/action/replication_record"}},"created_at":"2026-05-18T00:22:39.586587+00:00","updated_at":"2026-05-18T00:22:39.586587+00:00"}