{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:CPSP7B53C3T63NNX2OKRFSS4XS","short_pith_number":"pith:CPSP7B53","canonical_record":{"source":{"id":"1803.06120","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-16T09:22:47Z","cross_cats_sorted":[],"title_canon_sha256":"e52f79cc609b04e71d3cb68f5c3b21b01d5947e94d2c57fcedb00d5447e4d31e","abstract_canon_sha256":"af35cc7996e47f75ef8a8d2a6ffe5e0f53dd42641f2383f2206597c335b24b87"},"schema_version":"1.0"},"canonical_sha256":"13e4ff87bb16e7edb5b7d39512ca5cbca71feb43398a08fdbf9c6e64047070a5","source":{"kind":"arxiv","id":"1803.06120","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.06120","created_at":"2026-05-18T00:20:50Z"},{"alias_kind":"arxiv_version","alias_value":"1803.06120v1","created_at":"2026-05-18T00:20:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06120","created_at":"2026-05-18T00:20:50Z"},{"alias_kind":"pith_short_12","alias_value":"CPSP7B53C3T6","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CPSP7B53C3T63NNX","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CPSP7B53","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:CPSP7B53C3T63NNX2OKRFSS4XS","target":"record","payload":{"canonical_record":{"source":{"id":"1803.06120","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-16T09:22:47Z","cross_cats_sorted":[],"title_canon_sha256":"e52f79cc609b04e71d3cb68f5c3b21b01d5947e94d2c57fcedb00d5447e4d31e","abstract_canon_sha256":"af35cc7996e47f75ef8a8d2a6ffe5e0f53dd42641f2383f2206597c335b24b87"},"schema_version":"1.0"},"canonical_sha256":"13e4ff87bb16e7edb5b7d39512ca5cbca71feb43398a08fdbf9c6e64047070a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:50.555407Z","signature_b64":"VkjV1G6iJwMgvS7QVT9b3Ky23Z1TwkGm2PPDl5Wjt/7ffjw/4SoGN19BP9i1lrQVgfHVqj1GcOMi5xV2N2OkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13e4ff87bb16e7edb5b7d39512ca5cbca71feb43398a08fdbf9c6e64047070a5","last_reissued_at":"2026-05-18T00:20:50.554903Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:50.554903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.06120","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:20:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DsX0kofS04dWeabVG73bO9JSdXcEbw4qLInaU7lSngAAqMFc/QHSsLAiDofo+FjxpimzNYYN19DXmzm1TNw1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T12:28:24.503331Z"},"content_sha256":"f86561fc613e2a9279326efb75a6a090406719a1d02c3857fee378fce7e76a97","schema_version":"1.0","event_id":"sha256:f86561fc613e2a9279326efb75a6a090406719a1d02c3857fee378fce7e76a97"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:CPSP7B53C3T63NNX2OKRFSS4XS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Sparse Deep Feedforward Networks via Tree Skeleton Expansion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Nevin L. Zhang, Xiaopeng Li, Zhourong Chen","submitted_at":"2018-03-16T09:22:47Z","abstract_excerpt":"Despite the popularity of deep learning, structure learning for deep models remains a relatively under-explored area. In contrast, structure learning has been studied extensively for probabilistic graphical models (PGMs). In particular, an efficient algorithm has been developed for learning a class of tree-structured PGMs called hierarchical latent tree models (HLTMs), where there is a layer of observed variables at the bottom and multiple layers of latent variables on top. In this paper, we propose a simple method for learning the structures of feedforward neural networks (FNNs) based on HLTM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06120","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:20:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OpU9Rlsk/Y3kZiHQ6qj09UFwgikOCjooG7k4qpnc9I1tUfFVmt4pnm7bEfBEpedMmx++QtbsHIY0BaPoHs2/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T12:28:24.503693Z"},"content_sha256":"4b6e8de6215d638d46deae63da505abbc6e0aff6319f0b3f082180918834070c","schema_version":"1.0","event_id":"sha256:4b6e8de6215d638d46deae63da505abbc6e0aff6319f0b3f082180918834070c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CPSP7B53C3T63NNX2OKRFSS4XS/bundle.json","state_url":"https://pith.science/pith/CPSP7B53C3T63NNX2OKRFSS4XS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CPSP7B53C3T63NNX2OKRFSS4XS/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":"2026-06-05T12:28:24Z","links":{"resolver":"https://pith.science/pith/CPSP7B53C3T63NNX2OKRFSS4XS","bundle":"https://pith.science/pith/CPSP7B53C3T63NNX2OKRFSS4XS/bundle.json","state":"https://pith.science/pith/CPSP7B53C3T63NNX2OKRFSS4XS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CPSP7B53C3T63NNX2OKRFSS4XS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CPSP7B53C3T63NNX2OKRFSS4XS","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":"af35cc7996e47f75ef8a8d2a6ffe5e0f53dd42641f2383f2206597c335b24b87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-16T09:22:47Z","title_canon_sha256":"e52f79cc609b04e71d3cb68f5c3b21b01d5947e94d2c57fcedb00d5447e4d31e"},"schema_version":"1.0","source":{"id":"1803.06120","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.06120","created_at":"2026-05-18T00:20:50Z"},{"alias_kind":"arxiv_version","alias_value":"1803.06120v1","created_at":"2026-05-18T00:20:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06120","created_at":"2026-05-18T00:20:50Z"},{"alias_kind":"pith_short_12","alias_value":"CPSP7B53C3T6","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CPSP7B53C3T63NNX","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CPSP7B53","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:4b6e8de6215d638d46deae63da505abbc6e0aff6319f0b3f082180918834070c","target":"graph","created_at":"2026-05-18T00:20:50Z","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":"Despite the popularity of deep learning, structure learning for deep models remains a relatively under-explored area. In contrast, structure learning has been studied extensively for probabilistic graphical models (PGMs). In particular, an efficient algorithm has been developed for learning a class of tree-structured PGMs called hierarchical latent tree models (HLTMs), where there is a layer of observed variables at the bottom and multiple layers of latent variables on top. In this paper, we propose a simple method for learning the structures of feedforward neural networks (FNNs) based on HLTM","authors_text":"Nevin L. Zhang, Xiaopeng Li, Zhourong Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-16T09:22:47Z","title":"Learning Sparse Deep Feedforward Networks via Tree Skeleton Expansion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06120","kind":"arxiv","version":1},"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:f86561fc613e2a9279326efb75a6a090406719a1d02c3857fee378fce7e76a97","target":"record","created_at":"2026-05-18T00:20:50Z","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":"af35cc7996e47f75ef8a8d2a6ffe5e0f53dd42641f2383f2206597c335b24b87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-16T09:22:47Z","title_canon_sha256":"e52f79cc609b04e71d3cb68f5c3b21b01d5947e94d2c57fcedb00d5447e4d31e"},"schema_version":"1.0","source":{"id":"1803.06120","kind":"arxiv","version":1}},"canonical_sha256":"13e4ff87bb16e7edb5b7d39512ca5cbca71feb43398a08fdbf9c6e64047070a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13e4ff87bb16e7edb5b7d39512ca5cbca71feb43398a08fdbf9c6e64047070a5","first_computed_at":"2026-05-18T00:20:50.554903Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:50.554903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VkjV1G6iJwMgvS7QVT9b3Ky23Z1TwkGm2PPDl5Wjt/7ffjw/4SoGN19BP9i1lrQVgfHVqj1GcOMi5xV2N2OkDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:50.555407Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.06120","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f86561fc613e2a9279326efb75a6a090406719a1d02c3857fee378fce7e76a97","sha256:4b6e8de6215d638d46deae63da505abbc6e0aff6319f0b3f082180918834070c"],"state_sha256":"eca10f9121837140e60f3f75e9e99a6676235281ccaaf6fba9a9521860aa14fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/NAwNuVhy380IXbrYLau/lES55SsHt74JJ75RxhRN9TA94yo1r+wfLI+WWsWinXGD2yaPI067qYuDZvnvkKhCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T12:28:24.505794Z","bundle_sha256":"abe9acfe3c52ea35b5475d7be64fac5abc44720ec51066fa83dea238a003e814"}}