{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:T7I6RFJ4FEOCPKRLABH2GWJK5N","short_pith_number":"pith:T7I6RFJ4","schema_version":"1.0","canonical_sha256":"9fd1e8953c291c27aa2b004fa3592aeb5383a047a0d42fe7c17fafb608cde947","source":{"kind":"arxiv","id":"1803.03067","version":2},"attestation_state":"computed","paper":{"title":"Compositional Attention Networks for Machine Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Christopher D. Manning, Drew A. Hudson","submitted_at":"2018-03-08T12:37:14Z","abstract_excerpt":"We present the MAC network, a novel fully differentiable neural network architecture, designed to facilitate explicit and expressive reasoning. MAC moves away from monolithic black-box neural architectures towards a design that encourages both transparency and versatility. The model approaches problems by decomposing them into a series of attention-based reasoning steps, each performed by a novel recurrent Memory, Attention, and Composition (MAC) cell that maintains a separation between control and memory. By stringing the cells together and imposing structural constraints that regulate their "},"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":"1803.03067","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-03-08T12:37:14Z","cross_cats_sorted":[],"title_canon_sha256":"6e31474288b5c18ead85321cbecfd64a3d74c24874fc71eeb1816da461ea3bcb","abstract_canon_sha256":"f25a457bebebeefa7a87e40f9fdcde5247b1f15daa033c53de7d7472cdeae717"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:38.379550Z","signature_b64":"hVj4uulEKjsXUFFxS74nQAN+azoiXwp9wm6/0Wk7wIMo66XG3TQIRjnVd+bE5h79Hs4xZ3OmJZeKK2E3hl7rBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fd1e8953c291c27aa2b004fa3592aeb5383a047a0d42fe7c17fafb608cde947","last_reissued_at":"2026-05-18T00:17:38.378968Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:38.378968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional Attention Networks for Machine Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Christopher D. Manning, Drew A. Hudson","submitted_at":"2018-03-08T12:37:14Z","abstract_excerpt":"We present the MAC network, a novel fully differentiable neural network architecture, designed to facilitate explicit and expressive reasoning. MAC moves away from monolithic black-box neural architectures towards a design that encourages both transparency and versatility. The model approaches problems by decomposing them into a series of attention-based reasoning steps, each performed by a novel recurrent Memory, Attention, and Composition (MAC) cell that maintains a separation between control and memory. By stringing the cells together and imposing structural constraints that regulate their "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.03067","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":"1803.03067","created_at":"2026-05-18T00:17:38.379079+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.03067v2","created_at":"2026-05-18T00:17:38.379079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.03067","created_at":"2026-05-18T00:17:38.379079+00:00"},{"alias_kind":"pith_short_12","alias_value":"T7I6RFJ4FEOC","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"T7I6RFJ4FEOCPKRL","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"T7I6RFJ4","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.00490","citing_title":"ICDAR 2019 Competition on Scene Text Visual Question Answering","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T7I6RFJ4FEOCPKRLABH2GWJK5N","json":"https://pith.science/pith/T7I6RFJ4FEOCPKRLABH2GWJK5N.json","graph_json":"https://pith.science/api/pith-number/T7I6RFJ4FEOCPKRLABH2GWJK5N/graph.json","events_json":"https://pith.science/api/pith-number/T7I6RFJ4FEOCPKRLABH2GWJK5N/events.json","paper":"https://pith.science/paper/T7I6RFJ4"},"agent_actions":{"view_html":"https://pith.science/pith/T7I6RFJ4FEOCPKRLABH2GWJK5N","download_json":"https://pith.science/pith/T7I6RFJ4FEOCPKRLABH2GWJK5N.json","view_paper":"https://pith.science/paper/T7I6RFJ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.03067&json=true","fetch_graph":"https://pith.science/api/pith-number/T7I6RFJ4FEOCPKRLABH2GWJK5N/graph.json","fetch_events":"https://pith.science/api/pith-number/T7I6RFJ4FEOCPKRLABH2GWJK5N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T7I6RFJ4FEOCPKRLABH2GWJK5N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T7I6RFJ4FEOCPKRLABH2GWJK5N/action/storage_attestation","attest_author":"https://pith.science/pith/T7I6RFJ4FEOCPKRLABH2GWJK5N/action/author_attestation","sign_citation":"https://pith.science/pith/T7I6RFJ4FEOCPKRLABH2GWJK5N/action/citation_signature","submit_replication":"https://pith.science/pith/T7I6RFJ4FEOCPKRLABH2GWJK5N/action/replication_record"}},"created_at":"2026-05-18T00:17:38.379079+00:00","updated_at":"2026-05-18T00:17:38.379079+00:00"}