{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:S3CSKF2DN46KDUSTQSRSLE4ISF","short_pith_number":"pith:S3CSKF2D","canonical_record":{"source":{"id":"1508.03721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-15T11:16:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"32a6c551f320385fcd2ec596d60fabe7d5926f0baac650e826f13427f00d849d","abstract_canon_sha256":"a24e6683446d67d54d2d2dce7bfac4d9f7f68e54aae4fe2bbd99023cc24047d9"},"schema_version":"1.0"},"canonical_sha256":"96c52517436f3ca1d25384a32593889151c905486599ee76635e8c6896cc47f0","source":{"kind":"arxiv","id":"1508.03721","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.03721","created_at":"2026-05-18T01:35:15Z"},{"alias_kind":"arxiv_version","alias_value":"1508.03721v1","created_at":"2026-05-18T01:35:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.03721","created_at":"2026-05-18T01:35:15Z"},{"alias_kind":"pith_short_12","alias_value":"S3CSKF2DN46K","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"S3CSKF2DN46KDUST","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"S3CSKF2D","created_at":"2026-05-18T12:29:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:S3CSKF2DN46KDUSTQSRSLE4ISF","target":"record","payload":{"canonical_record":{"source":{"id":"1508.03721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-15T11:16:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"32a6c551f320385fcd2ec596d60fabe7d5926f0baac650e826f13427f00d849d","abstract_canon_sha256":"a24e6683446d67d54d2d2dce7bfac4d9f7f68e54aae4fe2bbd99023cc24047d9"},"schema_version":"1.0"},"canonical_sha256":"96c52517436f3ca1d25384a32593889151c905486599ee76635e8c6896cc47f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:35:15.363950Z","signature_b64":"XzhPnR+OvJ2aguCMQYYad6ihhi3lNA16P2kXRnPNVteeRCS6CUqayO8DjGtYkq7LfCWajyjj9XoEWsg98zwtAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96c52517436f3ca1d25384a32593889151c905486599ee76635e8c6896cc47f0","last_reissued_at":"2026-05-18T01:35:15.363533Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:35:15.363533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1508.03721","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":"2026-05-18T01:35:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zW7j0LesWpZQ/wXlTD+xEv2U78tu+mCxsBA+kNHgZdG9hakxe48a+htxN7/GUQ7eGyqQGRo9sqh0PFou3eFYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:47:34.468484Z"},"content_sha256":"3a5fb333169996bccd64e88f2bbbf037a9d4f91b4e220315ce105a19216049e2","schema_version":"1.0","event_id":"sha256:3a5fb333169996bccd64e88f2bbbf037a9d4f91b4e220315ce105a19216049e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:S3CSKF2DN46KDUSTQSRSLE4ISF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparative Study on Regularization Strategies for Embedding-based Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ge Li, Hao Peng, Lili Mou, Yangyang Lu, Yunchuan Chen, Zhi Jin","submitted_at":"2015-08-15T11:16:39Z","abstract_excerpt":"This paper aims to compare different regularization strategies to address a common phenomenon, severe overfitting, in embedding-based neural networks for NLP. We chose two widely studied neural models and tasks as our testbed. We tried several frequently applied or newly proposed regularization strategies, including penalizing weights (embeddings excluded), penalizing embeddings, re-embedding words, and dropout. We also emphasized on incremental hyperparameter tuning, and combining different regularizations. The results provide a picture on tuning hyperparameters for neural NLP models."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.03721","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":"2026-05-18T01:35:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ul10enK8zDAPOSE++26sxw+SFinIF8C7BKyxl6yZjn2SVSz2CUc37d01b/RnmzyQIUeeDumrMedo/LCovp1mBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T17:47:34.468829Z"},"content_sha256":"352ef669d10042c1f6b4a0329f464b309e96fce5a1b56420b18d56ca6d241255","schema_version":"1.0","event_id":"sha256:352ef669d10042c1f6b4a0329f464b309e96fce5a1b56420b18d56ca6d241255"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S3CSKF2DN46KDUSTQSRSLE4ISF/bundle.json","state_url":"https://pith.science/pith/S3CSKF2DN46KDUSTQSRSLE4ISF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S3CSKF2DN46KDUSTQSRSLE4ISF/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":"2026-06-01T17:47:34Z","links":{"resolver":"https://pith.science/pith/S3CSKF2DN46KDUSTQSRSLE4ISF","bundle":"https://pith.science/pith/S3CSKF2DN46KDUSTQSRSLE4ISF/bundle.json","state":"https://pith.science/pith/S3CSKF2DN46KDUSTQSRSLE4ISF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S3CSKF2DN46KDUSTQSRSLE4ISF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:S3CSKF2DN46KDUSTQSRSLE4ISF","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":"a24e6683446d67d54d2d2dce7bfac4d9f7f68e54aae4fe2bbd99023cc24047d9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-15T11:16:39Z","title_canon_sha256":"32a6c551f320385fcd2ec596d60fabe7d5926f0baac650e826f13427f00d849d"},"schema_version":"1.0","source":{"id":"1508.03721","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.03721","created_at":"2026-05-18T01:35:15Z"},{"alias_kind":"arxiv_version","alias_value":"1508.03721v1","created_at":"2026-05-18T01:35:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.03721","created_at":"2026-05-18T01:35:15Z"},{"alias_kind":"pith_short_12","alias_value":"S3CSKF2DN46K","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"S3CSKF2DN46KDUST","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"S3CSKF2D","created_at":"2026-05-18T12:29:39Z"}],"graph_snapshots":[{"event_id":"sha256:352ef669d10042c1f6b4a0329f464b309e96fce5a1b56420b18d56ca6d241255","target":"graph","created_at":"2026-05-18T01:35:15Z","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":"This paper aims to compare different regularization strategies to address a common phenomenon, severe overfitting, in embedding-based neural networks for NLP. We chose two widely studied neural models and tasks as our testbed. We tried several frequently applied or newly proposed regularization strategies, including penalizing weights (embeddings excluded), penalizing embeddings, re-embedding words, and dropout. We also emphasized on incremental hyperparameter tuning, and combining different regularizations. The results provide a picture on tuning hyperparameters for neural NLP models.","authors_text":"Ge Li, Hao Peng, Lili Mou, Yangyang Lu, Yunchuan Chen, Zhi Jin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-15T11:16:39Z","title":"A Comparative Study on Regularization Strategies for Embedding-based Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.03721","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":"sha256:3a5fb333169996bccd64e88f2bbbf037a9d4f91b4e220315ce105a19216049e2","target":"record","created_at":"2026-05-18T01:35:15Z","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":"a24e6683446d67d54d2d2dce7bfac4d9f7f68e54aae4fe2bbd99023cc24047d9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-15T11:16:39Z","title_canon_sha256":"32a6c551f320385fcd2ec596d60fabe7d5926f0baac650e826f13427f00d849d"},"schema_version":"1.0","source":{"id":"1508.03721","kind":"arxiv","version":1}},"canonical_sha256":"96c52517436f3ca1d25384a32593889151c905486599ee76635e8c6896cc47f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96c52517436f3ca1d25384a32593889151c905486599ee76635e8c6896cc47f0","first_computed_at":"2026-05-18T01:35:15.363533Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:35:15.363533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XzhPnR+OvJ2aguCMQYYad6ihhi3lNA16P2kXRnPNVteeRCS6CUqayO8DjGtYkq7LfCWajyjj9XoEWsg98zwtAw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:35:15.363950Z","signed_message":"canonical_sha256_bytes"},"source_id":"1508.03721","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a5fb333169996bccd64e88f2bbbf037a9d4f91b4e220315ce105a19216049e2","sha256:352ef669d10042c1f6b4a0329f464b309e96fce5a1b56420b18d56ca6d241255"],"state_sha256":"fe7056f36dfd53d709e36b0320c122cd23a42895082149d13f5bef3a8581aa89"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OWKP0XNOH9CChvXrkgRiSA1FPdaJb3rt1J0t5BiFl1WcvettdSvzRdWz1x97c9d3AFHNKV/+ZfFplA8XXe2YBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T17:47:34.470737Z","bundle_sha256":"4572564d998b912480914e689b4730e66ac7f48ab069826a67177ff3cc166798"}}