{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:IF3FXLHG4NIH2H2RXLHJWO4LOU","short_pith_number":"pith:IF3FXLHG","canonical_record":{"source":{"id":"1609.06693","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-21T19:31:07Z","cross_cats_sorted":[],"title_canon_sha256":"0f598e78f0c978d7669ed5b1f7e15f6479616e1d358e0213dd8ab9947e578598","abstract_canon_sha256":"467ad40b00665db74fb060bc9e395aeda1981d112d19d1d9d8aeb18c881cefad"},"schema_version":"1.0"},"canonical_sha256":"41765bace6e3507d1f51bace9b3b8b7539e214be028e24a91a90eb73434563dc","source":{"kind":"arxiv","id":"1609.06693","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.06693","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"arxiv_version","alias_value":"1609.06693v3","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.06693","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"pith_short_12","alias_value":"IF3FXLHG4NIH","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"IF3FXLHG4NIH2H2R","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"IF3FXLHG","created_at":"2026-05-18T12:30:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:IF3FXLHG4NIH2H2RXLHJWO4LOU","target":"record","payload":{"canonical_record":{"source":{"id":"1609.06693","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-21T19:31:07Z","cross_cats_sorted":[],"title_canon_sha256":"0f598e78f0c978d7669ed5b1f7e15f6479616e1d358e0213dd8ab9947e578598","abstract_canon_sha256":"467ad40b00665db74fb060bc9e395aeda1981d112d19d1d9d8aeb18c881cefad"},"schema_version":"1.0"},"canonical_sha256":"41765bace6e3507d1f51bace9b3b8b7539e214be028e24a91a90eb73434563dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:57.610504Z","signature_b64":"3HCosdTEmQqtshAqhNv7rVi/E4GLantUjoQFQmy3inZrkJbxQEZ9fNp6ESLh8BmSlfhPHZL/VIXzhCcxQDcRAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41765bace6e3507d1f51bace9b3b8b7539e214be028e24a91a90eb73434563dc","last_reissued_at":"2026-05-18T00:55:57.610018Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:57.610018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.06693","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":"2026-05-18T00:55:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2YzmdlVJeWYMATSETrbpr1DKa51mxyjJcTPluS/wj6wDV+5hLOzeEnVaAMlembifb2Y5CV5k4bufoUd3D60MDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T23:23:01.496342Z"},"content_sha256":"f4eb13b65760988d9aa022ddecdd3f25c21f1b9287a94eaea796fa87102d0684","schema_version":"1.0","event_id":"sha256:f4eb13b65760988d9aa022ddecdd3f25c21f1b9287a94eaea796fa87102d0684"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:IF3FXLHG4NIH2H2RXLHJWO4LOU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SoftTarget Regularization: An Effective Technique to Reduce Over-Fitting in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Armen Aghajanyan","submitted_at":"2016-09-21T19:31:07Z","abstract_excerpt":"Deep neural networks are learning models with a very high capacity and therefore prone to over-fitting. Many regularization techniques such as Dropout, DropConnect, and weight decay all attempt to solve the problem of over-fitting by reducing the capacity of their respective models (Srivastava et al., 2014), (Wan et al., 2013), (Krogh & Hertz, 1992). In this paper we introduce a new form of regularization that guides the learning problem in a way that reduces over-fitting without sacrificing the capacity of the model. The mistakes that models make in early stages of training carry information "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.06693","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":"2026-05-18T00:55:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yGftH1BR1hrHho0jTGavNa2L7hEpYzdhwT/ZzFvTDfwpkJ5ZxZfqZosZqohnpX4/yOo5MrXA5U0GZ3K7yOhQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T23:23:01.496960Z"},"content_sha256":"c50e4374c8f0f6cfc9203f505b7889d73cb7e4effff1c0981a706b7d2af1d564","schema_version":"1.0","event_id":"sha256:c50e4374c8f0f6cfc9203f505b7889d73cb7e4effff1c0981a706b7d2af1d564"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IF3FXLHG4NIH2H2RXLHJWO4LOU/bundle.json","state_url":"https://pith.science/pith/IF3FXLHG4NIH2H2RXLHJWO4LOU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IF3FXLHG4NIH2H2RXLHJWO4LOU/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":"2026-05-26T23:23:01Z","links":{"resolver":"https://pith.science/pith/IF3FXLHG4NIH2H2RXLHJWO4LOU","bundle":"https://pith.science/pith/IF3FXLHG4NIH2H2RXLHJWO4LOU/bundle.json","state":"https://pith.science/pith/IF3FXLHG4NIH2H2RXLHJWO4LOU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IF3FXLHG4NIH2H2RXLHJWO4LOU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:IF3FXLHG4NIH2H2RXLHJWO4LOU","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":"467ad40b00665db74fb060bc9e395aeda1981d112d19d1d9d8aeb18c881cefad","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-21T19:31:07Z","title_canon_sha256":"0f598e78f0c978d7669ed5b1f7e15f6479616e1d358e0213dd8ab9947e578598"},"schema_version":"1.0","source":{"id":"1609.06693","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.06693","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"arxiv_version","alias_value":"1609.06693v3","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.06693","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"pith_short_12","alias_value":"IF3FXLHG4NIH","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"IF3FXLHG4NIH2H2R","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"IF3FXLHG","created_at":"2026-05-18T12:30:22Z"}],"graph_snapshots":[{"event_id":"sha256:c50e4374c8f0f6cfc9203f505b7889d73cb7e4effff1c0981a706b7d2af1d564","target":"graph","created_at":"2026-05-18T00:55:57Z","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":"Deep neural networks are learning models with a very high capacity and therefore prone to over-fitting. Many regularization techniques such as Dropout, DropConnect, and weight decay all attempt to solve the problem of over-fitting by reducing the capacity of their respective models (Srivastava et al., 2014), (Wan et al., 2013), (Krogh & Hertz, 1992). In this paper we introduce a new form of regularization that guides the learning problem in a way that reduces over-fitting without sacrificing the capacity of the model. The mistakes that models make in early stages of training carry information ","authors_text":"Armen Aghajanyan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-21T19:31:07Z","title":"SoftTarget Regularization: An Effective Technique to Reduce Over-Fitting in Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.06693","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:f4eb13b65760988d9aa022ddecdd3f25c21f1b9287a94eaea796fa87102d0684","target":"record","created_at":"2026-05-18T00:55:57Z","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":"467ad40b00665db74fb060bc9e395aeda1981d112d19d1d9d8aeb18c881cefad","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-21T19:31:07Z","title_canon_sha256":"0f598e78f0c978d7669ed5b1f7e15f6479616e1d358e0213dd8ab9947e578598"},"schema_version":"1.0","source":{"id":"1609.06693","kind":"arxiv","version":3}},"canonical_sha256":"41765bace6e3507d1f51bace9b3b8b7539e214be028e24a91a90eb73434563dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41765bace6e3507d1f51bace9b3b8b7539e214be028e24a91a90eb73434563dc","first_computed_at":"2026-05-18T00:55:57.610018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:55:57.610018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3HCosdTEmQqtshAqhNv7rVi/E4GLantUjoQFQmy3inZrkJbxQEZ9fNp6ESLh8BmSlfhPHZL/VIXzhCcxQDcRAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:55:57.610504Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.06693","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4eb13b65760988d9aa022ddecdd3f25c21f1b9287a94eaea796fa87102d0684","sha256:c50e4374c8f0f6cfc9203f505b7889d73cb7e4effff1c0981a706b7d2af1d564"],"state_sha256":"16b69aadbda2f54dcc79ba5743eaa67703c1dfdfd56866fec911129686df7dd2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oUAMwodbuIzsbes0LcIeMxzxE7pYorpcjfZrkA9B+KiQyb9tDU0XyelanSX/QgX5pwNtbipT1keZX65A0t5JBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T23:23:01.500355Z","bundle_sha256":"9035abf47140ca6d213f2ddb75afaccd6c128545fca090625ef1e29999a82d28"}}