{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ESSXXWP3ULWD3QKUSQZXD5BMGY","short_pith_number":"pith:ESSXXWP3","schema_version":"1.0","canonical_sha256":"24a57bd9fba2ec3dc154943371f42c36019b137067f7e5b492fc2852e82cc87c","source":{"kind":"arxiv","id":"1905.11382","version":1},"attestation_state":"computed","paper":{"title":"State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Lamb, Anirudh Goyal, Denis Kazakov, Ioannis Mitliagkas, Jonathan Binas, Michael C. Mozer, Sandeep Subramanian, Yoshua Bengio","submitted_at":"2019-05-26T09:13:41Z","abstract_excerpt":"Machine learning promises methods that generalize well from finite labeled data. However, the brittleness of existing neural net approaches is revealed by notable failures, such as the existence of adversarial examples that are misclassified despite being nearly identical to a training example, or the inability of recurrent sequence-processing nets to stay on track without teacher forcing. We introduce a method, which we refer to as \\emph{state reification}, that involves modeling the distribution of hidden states over the training data and then projecting hidden states observed during testing"},"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":"1905.11382","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-26T09:13:41Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"9ffad2a7662f7e021537c3572b197dc1699ae0588bbcc08b3bcd8aba6fa79043","abstract_canon_sha256":"ca2e53e48255065f1e8aba1121ed53f7d0d58f74c0ad3b5c0c2107207f2cab80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:53.509121Z","signature_b64":"oEo05ZXCpXwcWIWsJYmHlFpGenYlYJ0qG6wok4y18wTKe/UfJQoTjwzItt3ZV65CTiMMxLeQrLWoCLbhv9kPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24a57bd9fba2ec3dc154943371f42c36019b137067f7e5b492fc2852e82cc87c","last_reissued_at":"2026-05-17T23:44:53.508387Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:53.508387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Lamb, Anirudh Goyal, Denis Kazakov, Ioannis Mitliagkas, Jonathan Binas, Michael C. Mozer, Sandeep Subramanian, Yoshua Bengio","submitted_at":"2019-05-26T09:13:41Z","abstract_excerpt":"Machine learning promises methods that generalize well from finite labeled data. However, the brittleness of existing neural net approaches is revealed by notable failures, such as the existence of adversarial examples that are misclassified despite being nearly identical to a training example, or the inability of recurrent sequence-processing nets to stay on track without teacher forcing. We introduce a method, which we refer to as \\emph{state reification}, that involves modeling the distribution of hidden states over the training data and then projecting hidden states observed during testing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11382","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":"1905.11382","created_at":"2026-05-17T23:44:53.508505+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11382v1","created_at":"2026-05-17T23:44:53.508505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11382","created_at":"2026-05-17T23:44:53.508505+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESSXXWP3ULWD","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESSXXWP3ULWD3QKU","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESSXXWP3","created_at":"2026-05-18T12:33:15.570797+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/ESSXXWP3ULWD3QKUSQZXD5BMGY","json":"https://pith.science/pith/ESSXXWP3ULWD3QKUSQZXD5BMGY.json","graph_json":"https://pith.science/api/pith-number/ESSXXWP3ULWD3QKUSQZXD5BMGY/graph.json","events_json":"https://pith.science/api/pith-number/ESSXXWP3ULWD3QKUSQZXD5BMGY/events.json","paper":"https://pith.science/paper/ESSXXWP3"},"agent_actions":{"view_html":"https://pith.science/pith/ESSXXWP3ULWD3QKUSQZXD5BMGY","download_json":"https://pith.science/pith/ESSXXWP3ULWD3QKUSQZXD5BMGY.json","view_paper":"https://pith.science/paper/ESSXXWP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11382&json=true","fetch_graph":"https://pith.science/api/pith-number/ESSXXWP3ULWD3QKUSQZXD5BMGY/graph.json","fetch_events":"https://pith.science/api/pith-number/ESSXXWP3ULWD3QKUSQZXD5BMGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESSXXWP3ULWD3QKUSQZXD5BMGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESSXXWP3ULWD3QKUSQZXD5BMGY/action/storage_attestation","attest_author":"https://pith.science/pith/ESSXXWP3ULWD3QKUSQZXD5BMGY/action/author_attestation","sign_citation":"https://pith.science/pith/ESSXXWP3ULWD3QKUSQZXD5BMGY/action/citation_signature","submit_replication":"https://pith.science/pith/ESSXXWP3ULWD3QKUSQZXD5BMGY/action/replication_record"}},"created_at":"2026-05-17T23:44:53.508505+00:00","updated_at":"2026-05-17T23:44:53.508505+00:00"}