{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:3R5LNVP6MOFEXAFEU4ZOLV5YM7","short_pith_number":"pith:3R5LNVP6","schema_version":"1.0","canonical_sha256":"dc7ab6d5fe638a4b80a4a732e5d7b867e0781585b18b22ca173530df10822321","source":{"kind":"arxiv","id":"1511.05653","version":2},"attestation_state":"computed","paper":{"title":"Why are deep nets reversible: A simple theory, with implications for training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Sanjeev Arora, Tengyu Ma, Yingyu Liang","submitted_at":"2015-11-18T04:33:09Z","abstract_excerpt":"Generative models for deep learning are promising both to improve understanding of the model, and yield training methods requiring fewer labeled samples.\n  Recent works use generative model approaches to produce the deep net's input given the value of a hidden layer several levels above. However, there is no accompanying \"proof of correctness\" for the generative model, showing that the feedforward deep net is the correct inference method for recovering the hidden layer given the input. Furthermore, these models are complicated.\n  The current paper takes a more theoretical tack. It presents a v"},"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":"1511.05653","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-18T04:33:09Z","cross_cats_sorted":[],"title_canon_sha256":"84b1d16bf1c85ec6c2b715222dc16d7305a12904b73003a77e8a9b2ae89556d0","abstract_canon_sha256":"baf91d4aae1501b962c7e6a17a6e0fc4bf030cc879c97c0252d831443ca50efb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:24.646380Z","signature_b64":"ogyxa0zyhkCOIzn3A2ZkJ6oYsjoPE96qWgEQ1KVUW41NxcMkfXZDJOGTIoR5m9pel5TXt62jZbI+IRD3Sul7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc7ab6d5fe638a4b80a4a732e5d7b867e0781585b18b22ca173530df10822321","last_reissued_at":"2026-05-18T01:26:24.645912Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:24.645912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Why are deep nets reversible: A simple theory, with implications for training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Sanjeev Arora, Tengyu Ma, Yingyu Liang","submitted_at":"2015-11-18T04:33:09Z","abstract_excerpt":"Generative models for deep learning are promising both to improve understanding of the model, and yield training methods requiring fewer labeled samples.\n  Recent works use generative model approaches to produce the deep net's input given the value of a hidden layer several levels above. However, there is no accompanying \"proof of correctness\" for the generative model, showing that the feedforward deep net is the correct inference method for recovering the hidden layer given the input. Furthermore, these models are complicated.\n  The current paper takes a more theoretical tack. It presents a v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05653","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":"1511.05653","created_at":"2026-05-18T01:26:24.645993+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.05653v2","created_at":"2026-05-18T01:26:24.645993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05653","created_at":"2026-05-18T01:26:24.645993+00:00"},{"alias_kind":"pith_short_12","alias_value":"3R5LNVP6MOFE","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_16","alias_value":"3R5LNVP6MOFEXAFE","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_8","alias_value":"3R5LNVP6","created_at":"2026-05-18T12:29:02.477457+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/3R5LNVP6MOFEXAFEU4ZOLV5YM7","json":"https://pith.science/pith/3R5LNVP6MOFEXAFEU4ZOLV5YM7.json","graph_json":"https://pith.science/api/pith-number/3R5LNVP6MOFEXAFEU4ZOLV5YM7/graph.json","events_json":"https://pith.science/api/pith-number/3R5LNVP6MOFEXAFEU4ZOLV5YM7/events.json","paper":"https://pith.science/paper/3R5LNVP6"},"agent_actions":{"view_html":"https://pith.science/pith/3R5LNVP6MOFEXAFEU4ZOLV5YM7","download_json":"https://pith.science/pith/3R5LNVP6MOFEXAFEU4ZOLV5YM7.json","view_paper":"https://pith.science/paper/3R5LNVP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.05653&json=true","fetch_graph":"https://pith.science/api/pith-number/3R5LNVP6MOFEXAFEU4ZOLV5YM7/graph.json","fetch_events":"https://pith.science/api/pith-number/3R5LNVP6MOFEXAFEU4ZOLV5YM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3R5LNVP6MOFEXAFEU4ZOLV5YM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3R5LNVP6MOFEXAFEU4ZOLV5YM7/action/storage_attestation","attest_author":"https://pith.science/pith/3R5LNVP6MOFEXAFEU4ZOLV5YM7/action/author_attestation","sign_citation":"https://pith.science/pith/3R5LNVP6MOFEXAFEU4ZOLV5YM7/action/citation_signature","submit_replication":"https://pith.science/pith/3R5LNVP6MOFEXAFEU4ZOLV5YM7/action/replication_record"}},"created_at":"2026-05-18T01:26:24.645993+00:00","updated_at":"2026-05-18T01:26:24.645993+00:00"}