{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:U5PN44TYCA2I2DJPKOYOK7LEIU","short_pith_number":"pith:U5PN44TY","schema_version":"1.0","canonical_sha256":"a75ede727810348d0d2f53b0e57d6445277d7014b7f760475b90f527692766db","source":{"kind":"arxiv","id":"2012.06921","version":2},"attestation_state":"computed","paper":{"title":"Learning Symbolic Expressions via Gumbel-Max Equation Learner Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gang Chen","submitted_at":"2020-12-12T23:36:20Z","abstract_excerpt":"Most of the neural networks (NNs) learned via state-of-the-art machine learning techniques are black-box models. For a widespread success of machine learning in science and engineering, it is important to develop new NN architectures to effectively extract high-level mathematical knowledge from complex datasets. Motivated by this understanding, this paper develops a new NN architecture called the Gumbel-Max Equation Learner (GMEQL) network. Different from previously proposed Equation Learner (EQL) networks, GMEQL applies continuous relaxation to the network structure via the Gumbel-Max trick a"},"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":"2012.06921","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-12T23:36:20Z","cross_cats_sorted":[],"title_canon_sha256":"cee983e29228b6fc238650a129efabb8e96f65e7d89a18f18c4e4c7c9e014c40","abstract_canon_sha256":"8de2f084c1dd5a5110fc387e4b4677092b01356c160f0a4eca15d4391cb80560"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:09.761144Z","signature_b64":"FrztrSYhKg66TTtMBFis2vhXtgTU3GYIYxRmteVsoIKR5hLXirOBV8j6L7EwQVMSdjbVamA4+/KtqLaRwFBQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a75ede727810348d0d2f53b0e57d6445277d7014b7f760475b90f527692766db","last_reissued_at":"2026-07-05T02:40:09.760570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:09.760570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Symbolic Expressions via Gumbel-Max Equation Learner Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gang Chen","submitted_at":"2020-12-12T23:36:20Z","abstract_excerpt":"Most of the neural networks (NNs) learned via state-of-the-art machine learning techniques are black-box models. For a widespread success of machine learning in science and engineering, it is important to develop new NN architectures to effectively extract high-level mathematical knowledge from complex datasets. Motivated by this understanding, this paper develops a new NN architecture called the Gumbel-Max Equation Learner (GMEQL) network. Different from previously proposed Equation Learner (EQL) networks, GMEQL applies continuous relaxation to the network structure via the Gumbel-Max trick a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.06921","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.06921/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":"2012.06921","created_at":"2026-07-05T02:40:09.760635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.06921v2","created_at":"2026-07-05T02:40:09.760635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.06921","created_at":"2026-07-05T02:40:09.760635+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5PN44TYCA2I","created_at":"2026-07-05T02:40:09.760635+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5PN44TYCA2I2DJP","created_at":"2026-07-05T02:40:09.760635+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5PN44TY","created_at":"2026-07-05T02:40:09.760635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.03366","citing_title":"A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoning","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5PN44TYCA2I2DJPKOYOK7LEIU","json":"https://pith.science/pith/U5PN44TYCA2I2DJPKOYOK7LEIU.json","graph_json":"https://pith.science/api/pith-number/U5PN44TYCA2I2DJPKOYOK7LEIU/graph.json","events_json":"https://pith.science/api/pith-number/U5PN44TYCA2I2DJPKOYOK7LEIU/events.json","paper":"https://pith.science/paper/U5PN44TY"},"agent_actions":{"view_html":"https://pith.science/pith/U5PN44TYCA2I2DJPKOYOK7LEIU","download_json":"https://pith.science/pith/U5PN44TYCA2I2DJPKOYOK7LEIU.json","view_paper":"https://pith.science/paper/U5PN44TY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.06921&json=true","fetch_graph":"https://pith.science/api/pith-number/U5PN44TYCA2I2DJPKOYOK7LEIU/graph.json","fetch_events":"https://pith.science/api/pith-number/U5PN44TYCA2I2DJPKOYOK7LEIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5PN44TYCA2I2DJPKOYOK7LEIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5PN44TYCA2I2DJPKOYOK7LEIU/action/storage_attestation","attest_author":"https://pith.science/pith/U5PN44TYCA2I2DJPKOYOK7LEIU/action/author_attestation","sign_citation":"https://pith.science/pith/U5PN44TYCA2I2DJPKOYOK7LEIU/action/citation_signature","submit_replication":"https://pith.science/pith/U5PN44TYCA2I2DJPKOYOK7LEIU/action/replication_record"}},"created_at":"2026-07-05T02:40:09.760635+00:00","updated_at":"2026-07-05T02:40:09.760635+00:00"}