{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KBX3ZHT7JQCVFCQJDNWS5EMMTT","short_pith_number":"pith:KBX3ZHT7","canonical_record":{"source":{"id":"2007.00811","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-01T23:34:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a0b62cf64e1bad2e34c9954b50162ec53472f6dcb5016f83ac46e31577211b12","abstract_canon_sha256":"131c56fb834553bfb729d66d1269692521942921ce37b9f5dd64cb20779fe087"},"schema_version":"1.0"},"canonical_sha256":"506fbc9e7f4c05528a091b6d2e918c9cfc4543c1edbc932817f5f48913a02fe7","source":{"kind":"arxiv","id":"2007.00811","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.00811","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"arxiv_version","alias_value":"2007.00811v2","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.00811","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"pith_short_12","alias_value":"KBX3ZHT7JQCV","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"pith_short_16","alias_value":"KBX3ZHT7JQCVFCQJ","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"pith_short_8","alias_value":"KBX3ZHT7","created_at":"2026-07-05T01:27:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KBX3ZHT7JQCVFCQJDNWS5EMMTT","target":"record","payload":{"canonical_record":{"source":{"id":"2007.00811","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-01T23:34:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a0b62cf64e1bad2e34c9954b50162ec53472f6dcb5016f83ac46e31577211b12","abstract_canon_sha256":"131c56fb834553bfb729d66d1269692521942921ce37b9f5dd64cb20779fe087"},"schema_version":"1.0"},"canonical_sha256":"506fbc9e7f4c05528a091b6d2e918c9cfc4543c1edbc932817f5f48913a02fe7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:25.181698Z","signature_b64":"cjN1FvR8iGGjSngg7yZdTceYSb8nYbgXbq0xgPoLoDy65tfg6wm6oOPUaqpZllVjmlboiQ8h4UXh7F2vGc5FDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"506fbc9e7f4c05528a091b6d2e918c9cfc4543c1edbc932817f5f48913a02fe7","last_reissued_at":"2026-07-05T01:27:25.181263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:25.181263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.00811","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:27:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+MEFGfJboNT4y5T/qsu242EDMZ6HsULOBB58oz8tpBPKoaXAPBQukUYyjfrXQo6LadqFLPQ4B3FyWhWH1BbIBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T00:09:19.015721Z"},"content_sha256":"1419e418a3d38759ae96b3cd30d6356a0deef8be62243ce7b1e5fc1b82d03c3d","schema_version":"1.0","event_id":"sha256:1419e418a3d38759ae96b3cd30d6356a0deef8be62243ce7b1e5fc1b82d03c3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KBX3ZHT7JQCVFCQJDNWS5EMMTT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Go Wide, Then Narrow: Efficient Training of Deep Thin Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Chen, Dale Schuurmans, Denny Zhou, Mao Ye, Mingxing Tan, Qiang Liu, Quoc Le, Tianjian Meng, Xiaodan Song","submitted_at":"2020-07-01T23:34:35Z","abstract_excerpt":"For deploying a deep learning model into production, it needs to be both accurate and compact to meet the latency and memory constraints. This usually results in a network that is deep (to ensure performance) and yet thin (to improve computational efficiency). In this paper, we propose an efficient method to train a deep thin network with a theoretic guarantee. Our method is motivated by model compression. It consists of three stages. First, we sufficiently widen the deep thin network and train it until convergence. Then, we use this well-trained deep wide network to warm up (or initialize) th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.00811","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.00811/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:27:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vzFn0w9+DIc4LGFPbKe95/Jb530SVW0wfPMJCpiLzJlnOSvaY/gsmTRD5mXJi/ZOb85xGkBiW3jE0/BijrH5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T00:09:19.016106Z"},"content_sha256":"76d2dc4efc4f83a5f0ce7a91c516306e9f704913606e59329fb709b2f7cf89dc","schema_version":"1.0","event_id":"sha256:76d2dc4efc4f83a5f0ce7a91c516306e9f704913606e59329fb709b2f7cf89dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KBX3ZHT7JQCVFCQJDNWS5EMMTT/bundle.json","state_url":"https://pith.science/pith/KBX3ZHT7JQCVFCQJDNWS5EMMTT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KBX3ZHT7JQCVFCQJDNWS5EMMTT/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":"2026-07-09T00:09:19Z","links":{"resolver":"https://pith.science/pith/KBX3ZHT7JQCVFCQJDNWS5EMMTT","bundle":"https://pith.science/pith/KBX3ZHT7JQCVFCQJDNWS5EMMTT/bundle.json","state":"https://pith.science/pith/KBX3ZHT7JQCVFCQJDNWS5EMMTT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KBX3ZHT7JQCVFCQJDNWS5EMMTT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KBX3ZHT7JQCVFCQJDNWS5EMMTT","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":"131c56fb834553bfb729d66d1269692521942921ce37b9f5dd64cb20779fe087","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-01T23:34:35Z","title_canon_sha256":"a0b62cf64e1bad2e34c9954b50162ec53472f6dcb5016f83ac46e31577211b12"},"schema_version":"1.0","source":{"id":"2007.00811","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.00811","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"arxiv_version","alias_value":"2007.00811v2","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.00811","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"pith_short_12","alias_value":"KBX3ZHT7JQCV","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"pith_short_16","alias_value":"KBX3ZHT7JQCVFCQJ","created_at":"2026-07-05T01:27:25Z"},{"alias_kind":"pith_short_8","alias_value":"KBX3ZHT7","created_at":"2026-07-05T01:27:25Z"}],"graph_snapshots":[{"event_id":"sha256:76d2dc4efc4f83a5f0ce7a91c516306e9f704913606e59329fb709b2f7cf89dc","target":"graph","created_at":"2026-07-05T01:27:25Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2007.00811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For deploying a deep learning model into production, it needs to be both accurate and compact to meet the latency and memory constraints. This usually results in a network that is deep (to ensure performance) and yet thin (to improve computational efficiency). In this paper, we propose an efficient method to train a deep thin network with a theoretic guarantee. Our method is motivated by model compression. It consists of three stages. First, we sufficiently widen the deep thin network and train it until convergence. Then, we use this well-trained deep wide network to warm up (or initialize) th","authors_text":"Chen Chen, Dale Schuurmans, Denny Zhou, Mao Ye, Mingxing Tan, Qiang Liu, Quoc Le, Tianjian Meng, Xiaodan Song","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-01T23:34:35Z","title":"Go Wide, Then Narrow: Efficient Training of Deep Thin Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.00811","kind":"arxiv","version":2},"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":"sha256:1419e418a3d38759ae96b3cd30d6356a0deef8be62243ce7b1e5fc1b82d03c3d","target":"record","created_at":"2026-07-05T01:27:25Z","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":"131c56fb834553bfb729d66d1269692521942921ce37b9f5dd64cb20779fe087","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-01T23:34:35Z","title_canon_sha256":"a0b62cf64e1bad2e34c9954b50162ec53472f6dcb5016f83ac46e31577211b12"},"schema_version":"1.0","source":{"id":"2007.00811","kind":"arxiv","version":2}},"canonical_sha256":"506fbc9e7f4c05528a091b6d2e918c9cfc4543c1edbc932817f5f48913a02fe7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"506fbc9e7f4c05528a091b6d2e918c9cfc4543c1edbc932817f5f48913a02fe7","first_computed_at":"2026-07-05T01:27:25.181263Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:27:25.181263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cjN1FvR8iGGjSngg7yZdTceYSb8nYbgXbq0xgPoLoDy65tfg6wm6oOPUaqpZllVjmlboiQ8h4UXh7F2vGc5FDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:27:25.181698Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.00811","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1419e418a3d38759ae96b3cd30d6356a0deef8be62243ce7b1e5fc1b82d03c3d","sha256:76d2dc4efc4f83a5f0ce7a91c516306e9f704913606e59329fb709b2f7cf89dc"],"state_sha256":"854d1cb59065d3c628d771cf4e47893e049848d2de9215aa55b3309dc31f05b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NSoJcn6Od//RMdUWXPDFNc4i8oYtBtlcehbVwjSAVfUmlxWx9CQ++UYGFuecxSKxnHP7Ls2kJHPlfc+XfpdkDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T00:09:19.018200Z","bundle_sha256":"147408c29d1446db9c3ee10d4f406d1785f7d922c8a1d722c9acb16839176f1a"}}