{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:FT4B6HEWOMMZYRULMDSYA43777","short_pith_number":"pith:FT4B6HEW","schema_version":"1.0","canonical_sha256":"2cf81f1c9673199c468b60e580737fffc6706c50115265dfca3777b7453cc67d","source":{"kind":"arxiv","id":"1410.3831","version":1},"attestation_state":"computed","paper":{"title":"An exact mapping between the Variational Renormalization Group and Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"David J. Schwab, Pankaj Mehta","submitted_at":"2014-10-14T20:00:09Z","abstract_excerpt":"Deep learning is a broad set of techniques that uses multiple layers of representation to automatically learn relevant features directly from structured data. Recently, such techniques have yielded record-breaking results on a diverse set of difficult machine learning tasks in computer vision, speech recognition, and natural language processing. Despite the enormous success of deep learning, relatively little is understood theoretically about why these techniques are so successful at feature learning and compression. Here, we show that deep learning is intimately related to one of the most imp"},"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":"1410.3831","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-10-14T20:00:09Z","cross_cats_sorted":["cond-mat.stat-mech","cs.LG","cs.NE"],"title_canon_sha256":"fa3fbcc122c8dabcdf1a4c1f0c997a13835d7fc8f0179d0a8f901de24f7f4cb3","abstract_canon_sha256":"7187219bf26e907f5283fe28b2b92106b7091e25a57a78ccb138ee0ac791e039"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:40:03.771173Z","signature_b64":"X1eWeWtpLMs/EbAS9cZG2YJXTsLSCPU+n4kYXFoqJrCID7ITocbvxpNn6eAjwf2VHosi4ciikaypRf2ZBnbPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cf81f1c9673199c468b60e580737fffc6706c50115265dfca3777b7453cc67d","last_reissued_at":"2026-05-18T02:40:03.770666Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:40:03.770666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An exact mapping between the Variational Renormalization Group and Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"David J. Schwab, Pankaj Mehta","submitted_at":"2014-10-14T20:00:09Z","abstract_excerpt":"Deep learning is a broad set of techniques that uses multiple layers of representation to automatically learn relevant features directly from structured data. Recently, such techniques have yielded record-breaking results on a diverse set of difficult machine learning tasks in computer vision, speech recognition, and natural language processing. Despite the enormous success of deep learning, relatively little is understood theoretically about why these techniques are so successful at feature learning and compression. Here, we show that deep learning is intimately related to one of the most imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.3831","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":"1410.3831","created_at":"2026-05-18T02:40:03.770749+00:00"},{"alias_kind":"arxiv_version","alias_value":"1410.3831v1","created_at":"2026-05-18T02:40:03.770749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.3831","created_at":"2026-05-18T02:40:03.770749+00:00"},{"alias_kind":"pith_short_12","alias_value":"FT4B6HEWOMMZ","created_at":"2026-05-18T12:28:28.263976+00:00"},{"alias_kind":"pith_short_16","alias_value":"FT4B6HEWOMMZYRUL","created_at":"2026-05-18T12:28:28.263976+00:00"},{"alias_kind":"pith_short_8","alias_value":"FT4B6HEW","created_at":"2026-05-18T12:28:28.263976+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2505.23728","citing_title":"Group Convolutional Neural Network for the Low-Energy Spectrum in the Quantum Dimer Model","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2506.04016","citing_title":"Dreaming up scale invariance via inverse renormalization group","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2512.13883","citing_title":"Renormalization group for spectral collapse in random matrices with power-law variance profiles","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14567","citing_title":"Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model","ref_index":127,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06394","citing_title":"Lecture Notes on Statistical Physics and Neural Networks","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00333","citing_title":"Borrowed Geometry: Cross-Distribution Head-Importance Fingerprints of Frozen Pretrained Gemma 4 31B","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FT4B6HEWOMMZYRULMDSYA43777","json":"https://pith.science/pith/FT4B6HEWOMMZYRULMDSYA43777.json","graph_json":"https://pith.science/api/pith-number/FT4B6HEWOMMZYRULMDSYA43777/graph.json","events_json":"https://pith.science/api/pith-number/FT4B6HEWOMMZYRULMDSYA43777/events.json","paper":"https://pith.science/paper/FT4B6HEW"},"agent_actions":{"view_html":"https://pith.science/pith/FT4B6HEWOMMZYRULMDSYA43777","download_json":"https://pith.science/pith/FT4B6HEWOMMZYRULMDSYA43777.json","view_paper":"https://pith.science/paper/FT4B6HEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1410.3831&json=true","fetch_graph":"https://pith.science/api/pith-number/FT4B6HEWOMMZYRULMDSYA43777/graph.json","fetch_events":"https://pith.science/api/pith-number/FT4B6HEWOMMZYRULMDSYA43777/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FT4B6HEWOMMZYRULMDSYA43777/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FT4B6HEWOMMZYRULMDSYA43777/action/storage_attestation","attest_author":"https://pith.science/pith/FT4B6HEWOMMZYRULMDSYA43777/action/author_attestation","sign_citation":"https://pith.science/pith/FT4B6HEWOMMZYRULMDSYA43777/action/citation_signature","submit_replication":"https://pith.science/pith/FT4B6HEWOMMZYRULMDSYA43777/action/replication_record"}},"created_at":"2026-05-18T02:40:03.770749+00:00","updated_at":"2026-05-18T02:40:03.770749+00:00"}