{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ARJHFYMGKYH2JWTNKQOZZP3ATK","short_pith_number":"pith:ARJHFYMG","schema_version":"1.0","canonical_sha256":"045272e186560fa4da6d541d9cbf609ab5b8eee96f7987673f85d9ee43a927d7","source":{"kind":"arxiv","id":"2109.01982","version":3},"attestation_state":"computed","paper":{"title":"Learning Hierarchical Structures with Differentiable Nondeterministic Stacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brian DuSell, David Chiang","submitted_at":"2021-09-05T03:25:23Z","abstract_excerpt":"Learning hierarchical structures in sequential data -- from simple algorithmic patterns to natural language -- in a reliable, generalizable way remains a challenging problem for neural language models. Past work has shown that recurrent neural networks (RNNs) struggle to generalize on held-out algorithmic or syntactic patterns without supervision or some inductive bias. To remedy this, many papers have explored augmenting RNNs with various differentiable stacks, by analogy with finite automata and pushdown automata (PDAs). In this paper, we improve the performance of our recently proposed Nond"},"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":"2109.01982","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-05T03:25:23Z","cross_cats_sorted":[],"title_canon_sha256":"c224b131a7f32ad22b1f02dad5c6f7924a7f2b4c4dc9388fb184d793b3243c14","abstract_canon_sha256":"f7ffe01a8bfc67dbef75bdccc5cba3bdbd4361c9322249d81998bb53b5d2e49a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:20:58.581588Z","signature_b64":"mODDAAcTeTzPtgD+Qazi6W6//j7C8dQSHhPVwjXRpwRi1tiKLzt9U0ShgVFWoT1l/ASFsIbx3bdLCDL4gzfuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"045272e186560fa4da6d541d9cbf609ab5b8eee96f7987673f85d9ee43a927d7","last_reissued_at":"2026-07-05T05:20:58.581222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:20:58.581222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Hierarchical Structures with Differentiable Nondeterministic Stacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brian DuSell, David Chiang","submitted_at":"2021-09-05T03:25:23Z","abstract_excerpt":"Learning hierarchical structures in sequential data -- from simple algorithmic patterns to natural language -- in a reliable, generalizable way remains a challenging problem for neural language models. Past work has shown that recurrent neural networks (RNNs) struggle to generalize on held-out algorithmic or syntactic patterns without supervision or some inductive bias. To remedy this, many papers have explored augmenting RNNs with various differentiable stacks, by analogy with finite automata and pushdown automata (PDAs). In this paper, we improve the performance of our recently proposed Nond"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.01982","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/2109.01982/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":"2109.01982","created_at":"2026-07-05T05:20:58.581277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.01982v3","created_at":"2026-07-05T05:20:58.581277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01982","created_at":"2026-07-05T05:20:58.581277+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARJHFYMGKYH2","created_at":"2026-07-05T05:20:58.581277+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARJHFYMGKYH2JWTN","created_at":"2026-07-05T05:20:58.581277+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARJHFYMG","created_at":"2026-07-05T05:20:58.581277+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22978","citing_title":"A Systematic Study of Compositional Syntactic Transformer Language Models","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ARJHFYMGKYH2JWTNKQOZZP3ATK","json":"https://pith.science/pith/ARJHFYMGKYH2JWTNKQOZZP3ATK.json","graph_json":"https://pith.science/api/pith-number/ARJHFYMGKYH2JWTNKQOZZP3ATK/graph.json","events_json":"https://pith.science/api/pith-number/ARJHFYMGKYH2JWTNKQOZZP3ATK/events.json","paper":"https://pith.science/paper/ARJHFYMG"},"agent_actions":{"view_html":"https://pith.science/pith/ARJHFYMGKYH2JWTNKQOZZP3ATK","download_json":"https://pith.science/pith/ARJHFYMGKYH2JWTNKQOZZP3ATK.json","view_paper":"https://pith.science/paper/ARJHFYMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.01982&json=true","fetch_graph":"https://pith.science/api/pith-number/ARJHFYMGKYH2JWTNKQOZZP3ATK/graph.json","fetch_events":"https://pith.science/api/pith-number/ARJHFYMGKYH2JWTNKQOZZP3ATK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARJHFYMGKYH2JWTNKQOZZP3ATK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARJHFYMGKYH2JWTNKQOZZP3ATK/action/storage_attestation","attest_author":"https://pith.science/pith/ARJHFYMGKYH2JWTNKQOZZP3ATK/action/author_attestation","sign_citation":"https://pith.science/pith/ARJHFYMGKYH2JWTNKQOZZP3ATK/action/citation_signature","submit_replication":"https://pith.science/pith/ARJHFYMGKYH2JWTNKQOZZP3ATK/action/replication_record"}},"created_at":"2026-07-05T05:20:58.581277+00:00","updated_at":"2026-07-05T05:20:58.581277+00:00"}