{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:UCA3QLRUI75PSW5VOHHDZAGRDF","short_pith_number":"pith:UCA3QLRU","canonical_record":{"source":{"id":"1612.09057","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-29T07:26:26Z","cross_cats_sorted":[],"title_canon_sha256":"2793a2119f94863152c793c7dd9dce2339dd50e11ca39e828029a3faaf996aab","abstract_canon_sha256":"7412a33c23ea9e9c7b65d374bc6e715c7ff014c2cc95cb37dfb8ec774e9f1735"},"schema_version":"1.0"},"canonical_sha256":"a081b82e3447faf95bb571ce3c80d1196622bd41cfea9589c75d6518bf908752","source":{"kind":"arxiv","id":"1612.09057","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.09057","created_at":"2026-05-18T00:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"1612.09057v4","created_at":"2026-05-18T00:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.09057","created_at":"2026-05-18T00:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"UCA3QLRUI75P","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"UCA3QLRUI75PSW5V","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"UCA3QLRU","created_at":"2026-05-18T12:30:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:UCA3QLRUI75PSW5VOHHDZAGRDF","target":"record","payload":{"canonical_record":{"source":{"id":"1612.09057","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-29T07:26:26Z","cross_cats_sorted":[],"title_canon_sha256":"2793a2119f94863152c793c7dd9dce2339dd50e11ca39e828029a3faaf996aab","abstract_canon_sha256":"7412a33c23ea9e9c7b65d374bc6e715c7ff014c2cc95cb37dfb8ec774e9f1735"},"schema_version":"1.0"},"canonical_sha256":"a081b82e3447faf95bb571ce3c80d1196622bd41cfea9589c75d6518bf908752","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:31.146131Z","signature_b64":"EoEREDQsWfxTtbAJkcmQZKswZl8klD9nj45D+kc6/lntMOeb7UVDGxLyt8yFHMLfq4nyzjNDxUmbqph/EDp/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a081b82e3447faf95bb571ce3c80d1196622bd41cfea9589c75d6518bf908752","last_reissued_at":"2026-05-18T00:06:31.145622Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:31.145622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.09057","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:06:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bam8c8ME6IwgfKmmlNa4QoWXZnfeTwvBFtHOeNC8PpSx08Fb5fU1M1JMc0WrOg+0RFm1MR0/G6cOg5PtQJb+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T12:47:25.576621Z"},"content_sha256":"bb4129d3826c94bdbdb83ec995981c4bf7aaefb4e431db21530365b29a31e30a","schema_version":"1.0","event_id":"sha256:bb4129d3826c94bdbdb83ec995981c4bf7aaefb4e431db21530365b29a31e30a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:UCA3QLRUI75PSW5VOHHDZAGRDF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Learning and Hierarchal Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Elchanan Mossel","submitted_at":"2016-12-29T07:26:26Z","abstract_excerpt":"It is argued that deep learning is efficient for data that is generated from hierarchal generative models. Examples of such generative models include wavelet scattering networks, functions of compositional structure, and deep rendering models. Unfortunately so far, for all such models, it is either not rigorously known that they can be learned efficiently, or it is not known that \"deep algorithms\" are required in order to learn them.\n  We propose a simple family of \"generative hierarchal models\" which can be efficiently learned and where \"deep\" algorithm are necessary for learning. Our definit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.09057","kind":"arxiv","version":4},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:06:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p7luujZlGd2EMS+CE8suqUW9oR0NNq8S/ogZINXwKaJAUeUvx8vkh1Jm8xSLyrEFTe3XskYrIq9OuSrKzMYbBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T12:47:25.577254Z"},"content_sha256":"9a3b8fd034fad8aff2d13b3f3d7e44ef8e3105dad98c9975c27f34754399f99d","schema_version":"1.0","event_id":"sha256:9a3b8fd034fad8aff2d13b3f3d7e44ef8e3105dad98c9975c27f34754399f99d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UCA3QLRUI75PSW5VOHHDZAGRDF/bundle.json","state_url":"https://pith.science/pith/UCA3QLRUI75PSW5VOHHDZAGRDF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UCA3QLRUI75PSW5VOHHDZAGRDF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-21T12:47:25Z","links":{"resolver":"https://pith.science/pith/UCA3QLRUI75PSW5VOHHDZAGRDF","bundle":"https://pith.science/pith/UCA3QLRUI75PSW5VOHHDZAGRDF/bundle.json","state":"https://pith.science/pith/UCA3QLRUI75PSW5VOHHDZAGRDF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UCA3QLRUI75PSW5VOHHDZAGRDF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:UCA3QLRUI75PSW5VOHHDZAGRDF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7412a33c23ea9e9c7b65d374bc6e715c7ff014c2cc95cb37dfb8ec774e9f1735","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-29T07:26:26Z","title_canon_sha256":"2793a2119f94863152c793c7dd9dce2339dd50e11ca39e828029a3faaf996aab"},"schema_version":"1.0","source":{"id":"1612.09057","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.09057","created_at":"2026-05-18T00:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"1612.09057v4","created_at":"2026-05-18T00:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.09057","created_at":"2026-05-18T00:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"UCA3QLRUI75P","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_16","alias_value":"UCA3QLRUI75PSW5V","created_at":"2026-05-18T12:30:46Z"},{"alias_kind":"pith_short_8","alias_value":"UCA3QLRU","created_at":"2026-05-18T12:30:46Z"}],"graph_snapshots":[{"event_id":"sha256:9a3b8fd034fad8aff2d13b3f3d7e44ef8e3105dad98c9975c27f34754399f99d","target":"graph","created_at":"2026-05-18T00:06:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"It is argued that deep learning is efficient for data that is generated from hierarchal generative models. Examples of such generative models include wavelet scattering networks, functions of compositional structure, and deep rendering models. Unfortunately so far, for all such models, it is either not rigorously known that they can be learned efficiently, or it is not known that \"deep algorithms\" are required in order to learn them.\n  We propose a simple family of \"generative hierarchal models\" which can be efficiently learned and where \"deep\" algorithm are necessary for learning. Our definit","authors_text":"Elchanan Mossel","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-29T07:26:26Z","title":"Deep Learning and Hierarchal Generative Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.09057","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bb4129d3826c94bdbdb83ec995981c4bf7aaefb4e431db21530365b29a31e30a","target":"record","created_at":"2026-05-18T00:06:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7412a33c23ea9e9c7b65d374bc6e715c7ff014c2cc95cb37dfb8ec774e9f1735","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-29T07:26:26Z","title_canon_sha256":"2793a2119f94863152c793c7dd9dce2339dd50e11ca39e828029a3faaf996aab"},"schema_version":"1.0","source":{"id":"1612.09057","kind":"arxiv","version":4}},"canonical_sha256":"a081b82e3447faf95bb571ce3c80d1196622bd41cfea9589c75d6518bf908752","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a081b82e3447faf95bb571ce3c80d1196622bd41cfea9589c75d6518bf908752","first_computed_at":"2026-05-18T00:06:31.145622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:31.145622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EoEREDQsWfxTtbAJkcmQZKswZl8klD9nj45D+kc6/lntMOeb7UVDGxLyt8yFHMLfq4nyzjNDxUmbqph/EDp/BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:31.146131Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.09057","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb4129d3826c94bdbdb83ec995981c4bf7aaefb4e431db21530365b29a31e30a","sha256:9a3b8fd034fad8aff2d13b3f3d7e44ef8e3105dad98c9975c27f34754399f99d"],"state_sha256":"3b03e1398653cdfcfa46367ad649b27e75a15e3c806b70c592f0bc1287179391"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uldRaDgEk9J5Twr8XnkY25Mi1C35Rw+vaj5Gv5n/dvsmWdCPXPLHZG/9AUny9egEOzq0rsXHiPqVMNN60H4eDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T12:47:25.580342Z","bundle_sha256":"84f7f3877b9bd33963bcc32238a0f13f87846ac1f885b615af77b6b9bc141a95"}}