{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:SJV4XLEYQYGG7WFKTEGG4UMWQD","short_pith_number":"pith:SJV4XLEY","canonical_record":{"source":{"id":"1506.03412","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-10T17:59:57Z","cross_cats_sorted":["cs.CV","cs.NE","math.OC","stat.ML"],"title_canon_sha256":"0a26e4a6688f00fbdf7542158a8a646746fa5db9b9ec486efbba91fe16765347","abstract_canon_sha256":"d25437ca1d242a86c27585040e463e4c427d2d10bcbe3f17d812d5340def6b80"},"schema_version":"1.0"},"canonical_sha256":"926bcbac98860c6fd8aa990c6e519680d186c346ce428dc74df594048b5e4c55","source":{"kind":"arxiv","id":"1506.03412","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.03412","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"arxiv_version","alias_value":"1506.03412v3","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.03412","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"pith_short_12","alias_value":"SJV4XLEYQYGG","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"SJV4XLEYQYGG7WFK","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"SJV4XLEY","created_at":"2026-05-18T12:29:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:SJV4XLEYQYGG7WFKTEGG4UMWQD","target":"record","payload":{"canonical_record":{"source":{"id":"1506.03412","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-10T17:59:57Z","cross_cats_sorted":["cs.CV","cs.NE","math.OC","stat.ML"],"title_canon_sha256":"0a26e4a6688f00fbdf7542158a8a646746fa5db9b9ec486efbba91fe16765347","abstract_canon_sha256":"d25437ca1d242a86c27585040e463e4c427d2d10bcbe3f17d812d5340def6b80"},"schema_version":"1.0"},"canonical_sha256":"926bcbac98860c6fd8aa990c6e519680d186c346ce428dc74df594048b5e4c55","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:12.588642Z","signature_b64":"vmqv6C35gRkvPvFzcfEkFZxGmpnGwJjeJHZAZZM9nMoN8zhdkroqDn9IGri4PppnAyFJjuHiJSrchNfCsK2XCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"926bcbac98860c6fd8aa990c6e519680d186c346ce428dc74df594048b5e4c55","last_reissued_at":"2026-05-18T00:50:12.588168Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:12.588168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.03412","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:50:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SFQLDR3X/AtjIE0kuRpDpxo1ArNKNXGy9tBUysxrvBMn9cbmNs37RwTx4QVRQRacveb7ow+0Pez28ZqEOeOaBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T15:30:35.346457Z"},"content_sha256":"32de5214c57469caf5a4142586b73fc65a775ab3765a055c6c2ab28fd5323b9a","schema_version":"1.0","event_id":"sha256:32de5214c57469caf5a4142586b73fc65a775ab3765a055c6c2ab28fd5323b9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:SJV4XLEYQYGG7WFKTEGG4UMWQD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convergence rates for pretraining and dropout: Guiding learning parameters using network structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Sathya Ravi, Vamsi K. Ithapu, Vikas Singh","submitted_at":"2015-06-10T17:59:57Z","abstract_excerpt":"Unsupervised pretraining and dropout have been well studied, especially with respect to regularization and output consistency. However, our understanding about the explicit convergence rates of the parameter estimates, and their dependence on the learning (like denoising and dropout rate) and structural (like depth and layer lengths) aspects of the network is less mature. An interesting question in this context is to ask if the network structure could \"guide\" the choices of such learning parameters. In this work, we explore these gaps between network structure, the learning mechanisms and thei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.03412","kind":"arxiv","version":3},"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":"2026-05-18T00:50:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2aXYqe8M2SJ+zusnZQpx7cPVgrI+/QAzru3PRnkuJ4YdBJt+p0gzsRW6BU2gXzWg9+shmw0DDpG+Zw0YYfX4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T15:30:35.346840Z"},"content_sha256":"680e8739f4aef8db820e8532f70f992b575076dbfb3e8e2da075215f8bfbdad5","schema_version":"1.0","event_id":"sha256:680e8739f4aef8db820e8532f70f992b575076dbfb3e8e2da075215f8bfbdad5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SJV4XLEYQYGG7WFKTEGG4UMWQD/bundle.json","state_url":"https://pith.science/pith/SJV4XLEYQYGG7WFKTEGG4UMWQD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SJV4XLEYQYGG7WFKTEGG4UMWQD/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":"2026-06-02T15:30:35Z","links":{"resolver":"https://pith.science/pith/SJV4XLEYQYGG7WFKTEGG4UMWQD","bundle":"https://pith.science/pith/SJV4XLEYQYGG7WFKTEGG4UMWQD/bundle.json","state":"https://pith.science/pith/SJV4XLEYQYGG7WFKTEGG4UMWQD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SJV4XLEYQYGG7WFKTEGG4UMWQD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:SJV4XLEYQYGG7WFKTEGG4UMWQD","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":"d25437ca1d242a86c27585040e463e4c427d2d10bcbe3f17d812d5340def6b80","cross_cats_sorted":["cs.CV","cs.NE","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-10T17:59:57Z","title_canon_sha256":"0a26e4a6688f00fbdf7542158a8a646746fa5db9b9ec486efbba91fe16765347"},"schema_version":"1.0","source":{"id":"1506.03412","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.03412","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"arxiv_version","alias_value":"1506.03412v3","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.03412","created_at":"2026-05-18T00:50:12Z"},{"alias_kind":"pith_short_12","alias_value":"SJV4XLEYQYGG","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"SJV4XLEYQYGG7WFK","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"SJV4XLEY","created_at":"2026-05-18T12:29:42Z"}],"graph_snapshots":[{"event_id":"sha256:680e8739f4aef8db820e8532f70f992b575076dbfb3e8e2da075215f8bfbdad5","target":"graph","created_at":"2026-05-18T00:50:12Z","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":"Unsupervised pretraining and dropout have been well studied, especially with respect to regularization and output consistency. However, our understanding about the explicit convergence rates of the parameter estimates, and their dependence on the learning (like denoising and dropout rate) and structural (like depth and layer lengths) aspects of the network is less mature. An interesting question in this context is to ask if the network structure could \"guide\" the choices of such learning parameters. In this work, we explore these gaps between network structure, the learning mechanisms and thei","authors_text":"Sathya Ravi, Vamsi K. Ithapu, Vikas Singh","cross_cats":["cs.CV","cs.NE","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-10T17:59:57Z","title":"Convergence rates for pretraining and dropout: Guiding learning parameters using network structure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.03412","kind":"arxiv","version":3},"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":"sha256:32de5214c57469caf5a4142586b73fc65a775ab3765a055c6c2ab28fd5323b9a","target":"record","created_at":"2026-05-18T00:50:12Z","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":"d25437ca1d242a86c27585040e463e4c427d2d10bcbe3f17d812d5340def6b80","cross_cats_sorted":["cs.CV","cs.NE","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-10T17:59:57Z","title_canon_sha256":"0a26e4a6688f00fbdf7542158a8a646746fa5db9b9ec486efbba91fe16765347"},"schema_version":"1.0","source":{"id":"1506.03412","kind":"arxiv","version":3}},"canonical_sha256":"926bcbac98860c6fd8aa990c6e519680d186c346ce428dc74df594048b5e4c55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"926bcbac98860c6fd8aa990c6e519680d186c346ce428dc74df594048b5e4c55","first_computed_at":"2026-05-18T00:50:12.588168Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:12.588168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vmqv6C35gRkvPvFzcfEkFZxGmpnGwJjeJHZAZZM9nMoN8zhdkroqDn9IGri4PppnAyFJjuHiJSrchNfCsK2XCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:12.588642Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.03412","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32de5214c57469caf5a4142586b73fc65a775ab3765a055c6c2ab28fd5323b9a","sha256:680e8739f4aef8db820e8532f70f992b575076dbfb3e8e2da075215f8bfbdad5"],"state_sha256":"6a731426e4b123eee90579f2b3e9829f0a4a41794113f4e9cd70efacd0fa483b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L8ryOcl6BwRyOCaLYJjgZBT6SAs9dbwmv4gwYXEY/VznNA/q69furK0L4i2iylZRcY4YGGrEk4pLDtsmz/JFCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T15:30:35.350287Z","bundle_sha256":"221fc18d116760e410afb339de39d159c3d663076433a792f5f0973241d58b9f"}}