{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:B264255I2CYFDSKSZSW255ZXTY","short_pith_number":"pith:B264255I","schema_version":"1.0","canonical_sha256":"0ebdcd77a8d0b051c952ccadaef7379e212f769c3ab740a752f24f6329e9c23a","source":{"kind":"arxiv","id":"1908.09772","version":1},"attestation_state":"computed","paper":{"title":"A Probabilistic Representation of Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kenneth E. Barner, Xinjie Lan","submitted_at":"2019-08-26T16:18:22Z","abstract_excerpt":"In this work, we introduce a novel probabilistic representation of deep learning, which provides an explicit explanation for the Deep Neural Networks (DNNs) in three aspects: (i) neurons define the energy of a Gibbs distribution; (ii) the hidden layers of DNNs formulate Gibbs distributions; and (iii) the whole architecture of DNNs can be interpreted as a Bayesian neural network. Based on the proposed probabilistic representation, we investigate two fundamental properties of deep learning: hierarchy and generalization. First, we explicitly formulate the hierarchy property from the Bayesian pers"},"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":"1908.09772","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-26T16:18:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d6d04a0a91747037024e78e72fd516a1ee8c221de9108da1b62a45bc05748a8c","abstract_canon_sha256":"dad5416aa6bfaa1162bef63f681ce8a074beb59ebca36d854f6d20d86fb22992"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:44.739699Z","signature_b64":"GoKjT3ZD3VONuY9ocwEstJRGNqK11a3azQJQ5eDNoAD2OOyZ6RcHu1AdHcmTHSvp6OeIfs9wLwi9X58T+MOtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ebdcd77a8d0b051c952ccadaef7379e212f769c3ab740a752f24f6329e9c23a","last_reissued_at":"2026-07-04T23:59:44.739108Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:44.739108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Probabilistic Representation of Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kenneth E. Barner, Xinjie Lan","submitted_at":"2019-08-26T16:18:22Z","abstract_excerpt":"In this work, we introduce a novel probabilistic representation of deep learning, which provides an explicit explanation for the Deep Neural Networks (DNNs) in three aspects: (i) neurons define the energy of a Gibbs distribution; (ii) the hidden layers of DNNs formulate Gibbs distributions; and (iii) the whole architecture of DNNs can be interpreted as a Bayesian neural network. Based on the proposed probabilistic representation, we investigate two fundamental properties of deep learning: hierarchy and generalization. First, we explicitly formulate the hierarchy property from the Bayesian pers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09772","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.09772/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":"1908.09772","created_at":"2026-07-04T23:59:44.739358+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.09772v1","created_at":"2026-07-04T23:59:44.739358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09772","created_at":"2026-07-04T23:59:44.739358+00:00"},{"alias_kind":"pith_short_12","alias_value":"B264255I2CYF","created_at":"2026-07-04T23:59:44.739358+00:00"},{"alias_kind":"pith_short_16","alias_value":"B264255I2CYFDSKS","created_at":"2026-07-04T23:59:44.739358+00:00"},{"alias_kind":"pith_short_8","alias_value":"B264255I","created_at":"2026-07-04T23:59:44.739358+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/B264255I2CYFDSKSZSW255ZXTY","json":"https://pith.science/pith/B264255I2CYFDSKSZSW255ZXTY.json","graph_json":"https://pith.science/api/pith-number/B264255I2CYFDSKSZSW255ZXTY/graph.json","events_json":"https://pith.science/api/pith-number/B264255I2CYFDSKSZSW255ZXTY/events.json","paper":"https://pith.science/paper/B264255I"},"agent_actions":{"view_html":"https://pith.science/pith/B264255I2CYFDSKSZSW255ZXTY","download_json":"https://pith.science/pith/B264255I2CYFDSKSZSW255ZXTY.json","view_paper":"https://pith.science/paper/B264255I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.09772&json=true","fetch_graph":"https://pith.science/api/pith-number/B264255I2CYFDSKSZSW255ZXTY/graph.json","fetch_events":"https://pith.science/api/pith-number/B264255I2CYFDSKSZSW255ZXTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B264255I2CYFDSKSZSW255ZXTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B264255I2CYFDSKSZSW255ZXTY/action/storage_attestation","attest_author":"https://pith.science/pith/B264255I2CYFDSKSZSW255ZXTY/action/author_attestation","sign_citation":"https://pith.science/pith/B264255I2CYFDSKSZSW255ZXTY/action/citation_signature","submit_replication":"https://pith.science/pith/B264255I2CYFDSKSZSW255ZXTY/action/replication_record"}},"created_at":"2026-07-04T23:59:44.739358+00:00","updated_at":"2026-07-04T23:59:44.739358+00:00"}