{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FKP6CGJEWRMLCH4TJLDDSTTHB6","short_pith_number":"pith:FKP6CGJE","schema_version":"1.0","canonical_sha256":"2a9fe11924b458b11f934ac6394e670fa490ac7e6c0969463cdc1b76f79fb9a9","source":{"kind":"arxiv","id":"1809.02836","version":1},"attestation_state":"computed","paper":{"title":"Context-Free Transductions with Neural Stacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.NE","authors_text":"Andrew Benz, Dana Angluin, Noah Amsel, Robert Frank, Simon Mendelsohn, William Merrill, Yiding Hao","submitted_at":"2018-09-08T17:04:53Z","abstract_excerpt":"This paper analyzes the behavior of stack-augmented recurrent neural network (RNN) models. Due to the architectural similarity between stack RNNs and pushdown transducers, we train stack RNN models on a number of tasks, including string reversal, context-free language modelling, and cumulative XOR evaluation. Examining the behavior of our networks, we show that stack-augmented RNNs can discover intuitive stack-based strategies for solving our tasks. However, stack RNNs are more difficult to train than classical architectures such as LSTMs. Rather than employ stack-based strategies, more comple"},"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":"1809.02836","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-09-08T17:04:53Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"c395ea0305612645fefc744a3e38d626b379c29e66048375357a103929cb825e","abstract_canon_sha256":"bb0b4a340a23eb80e89d06f64872cacc4ee3f4421b10e76adc9269a0fe41e937"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:15.151869Z","signature_b64":"+huoMnVgA9zQnGoNHdaQujn6ICUWnUMEBZJ/YjoLULAzDGisMrBO4s3sZoLVo8CurhFRnQOIc+UryXfZ4HivCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a9fe11924b458b11f934ac6394e670fa490ac7e6c0969463cdc1b76f79fb9a9","last_reissued_at":"2026-05-18T00:06:15.151124Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:15.151124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-Free Transductions with Neural Stacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.NE","authors_text":"Andrew Benz, Dana Angluin, Noah Amsel, Robert Frank, Simon Mendelsohn, William Merrill, Yiding Hao","submitted_at":"2018-09-08T17:04:53Z","abstract_excerpt":"This paper analyzes the behavior of stack-augmented recurrent neural network (RNN) models. Due to the architectural similarity between stack RNNs and pushdown transducers, we train stack RNN models on a number of tasks, including string reversal, context-free language modelling, and cumulative XOR evaluation. Examining the behavior of our networks, we show that stack-augmented RNNs can discover intuitive stack-based strategies for solving our tasks. However, stack RNNs are more difficult to train than classical architectures such as LSTMs. Rather than employ stack-based strategies, more comple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02836","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":"1809.02836","created_at":"2026-05-18T00:06:15.151228+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.02836v1","created_at":"2026-05-18T00:06:15.151228+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02836","created_at":"2026-05-18T00:06:15.151228+00:00"},{"alias_kind":"pith_short_12","alias_value":"FKP6CGJEWRML","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"FKP6CGJEWRMLCH4T","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"FKP6CGJE","created_at":"2026-05-18T12:32:22.470017+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/FKP6CGJEWRMLCH4TJLDDSTTHB6","json":"https://pith.science/pith/FKP6CGJEWRMLCH4TJLDDSTTHB6.json","graph_json":"https://pith.science/api/pith-number/FKP6CGJEWRMLCH4TJLDDSTTHB6/graph.json","events_json":"https://pith.science/api/pith-number/FKP6CGJEWRMLCH4TJLDDSTTHB6/events.json","paper":"https://pith.science/paper/FKP6CGJE"},"agent_actions":{"view_html":"https://pith.science/pith/FKP6CGJEWRMLCH4TJLDDSTTHB6","download_json":"https://pith.science/pith/FKP6CGJEWRMLCH4TJLDDSTTHB6.json","view_paper":"https://pith.science/paper/FKP6CGJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.02836&json=true","fetch_graph":"https://pith.science/api/pith-number/FKP6CGJEWRMLCH4TJLDDSTTHB6/graph.json","fetch_events":"https://pith.science/api/pith-number/FKP6CGJEWRMLCH4TJLDDSTTHB6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FKP6CGJEWRMLCH4TJLDDSTTHB6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FKP6CGJEWRMLCH4TJLDDSTTHB6/action/storage_attestation","attest_author":"https://pith.science/pith/FKP6CGJEWRMLCH4TJLDDSTTHB6/action/author_attestation","sign_citation":"https://pith.science/pith/FKP6CGJEWRMLCH4TJLDDSTTHB6/action/citation_signature","submit_replication":"https://pith.science/pith/FKP6CGJEWRMLCH4TJLDDSTTHB6/action/replication_record"}},"created_at":"2026-05-18T00:06:15.151228+00:00","updated_at":"2026-05-18T00:06:15.151228+00:00"}