{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:L24KRSJCT2HQU7QCI4HNITHO2O","short_pith_number":"pith:L24KRSJC","canonical_record":{"source":{"id":"1805.07880","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T03:41:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"71be4b1a04ff278d3d122ec2791195c84e7cfb190cf2826b0a9a5e9200a9c256","abstract_canon_sha256":"e38a010ed49ab9433e9cbe99776ec95cb4a4a85ac8af60fbb384b146e332d960"},"schema_version":"1.0"},"canonical_sha256":"5eb8a8c9229e8f0a7e02470ed44ceed39606cfdb10f515888636e38d70628e44","source":{"kind":"arxiv","id":"1805.07880","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07880","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07880v1","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07880","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"pith_short_12","alias_value":"L24KRSJCT2HQ","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"L24KRSJCT2HQU7QC","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"L24KRSJC","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:L24KRSJCT2HQU7QCI4HNITHO2O","target":"record","payload":{"canonical_record":{"source":{"id":"1805.07880","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T03:41:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"71be4b1a04ff278d3d122ec2791195c84e7cfb190cf2826b0a9a5e9200a9c256","abstract_canon_sha256":"e38a010ed49ab9433e9cbe99776ec95cb4a4a85ac8af60fbb384b146e332d960"},"schema_version":"1.0"},"canonical_sha256":"5eb8a8c9229e8f0a7e02470ed44ceed39606cfdb10f515888636e38d70628e44","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:32.297121Z","signature_b64":"w0sAesqYLqcdFoeP1rHNr4+0cepUL6JxWY/lNDLMyFxGl1AJb2K94c75RtBF2kSEciE2k4pXXjLymIQhuAVWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5eb8a8c9229e8f0a7e02470ed44ceed39606cfdb10f515888636e38d70628e44","last_reissued_at":"2026-05-18T00:15:32.296569Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:32.296569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.07880","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":"2026-05-18T00:15:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"54rjQldZF0ATBvK5UZP8R1ElUjcCjsYyvBZT8QIoJ8l6weBJo0Fl2EYkuJG3Y3wt6g47rhuJWOn0UkTk3G2tAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T20:52:49.590962Z"},"content_sha256":"d141b75d6698e9d31de372da97d3ba111fc4e7a9ff7dea7e10a1b2c88bbee7e7","schema_version":"1.0","event_id":"sha256:d141b75d6698e9d31de372da97d3ba111fc4e7a9ff7dea7e10a1b2c88bbee7e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:L24KRSJCT2HQU7QCI4HNITHO2O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning with Non-Convex Truncated Losses by SGD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi Zhang, Rong Jin, Sen Yang, Shenghuo Zhu, Tianbao Yang, Yi Xu","submitted_at":"2018-05-21T03:41:37Z","abstract_excerpt":"Learning with a {\\it convex loss} function has been a dominating paradigm for many years. It remains an interesting question how non-convex loss functions help improve the generalization of learning with broad applicability. In this paper, we study a family of objective functions formed by truncating traditional loss functions, which is applicable to both shallow learning and deep learning. Truncating loss functions has potential to be less vulnerable and more robust to large noise in observations that could be adversarial. More importantly, it is a generic technique without assuming the knowl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07880","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":"2026-05-18T00:15:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aFvOKcTVJ/GQBpiWHquRqFIA774qtTjLmsMCFCWY5UvvG2Tj41z2i2FzSxwCKHV/9tBZJEFBtnInJgh1CwypAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T20:52:49.591343Z"},"content_sha256":"6cb9249842a353a60ecbbc744ae2e9ecf7f025f995fdb0ae9490600f8383ea32","schema_version":"1.0","event_id":"sha256:6cb9249842a353a60ecbbc744ae2e9ecf7f025f995fdb0ae9490600f8383ea32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L24KRSJCT2HQU7QCI4HNITHO2O/bundle.json","state_url":"https://pith.science/pith/L24KRSJCT2HQU7QCI4HNITHO2O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L24KRSJCT2HQU7QCI4HNITHO2O/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":"2026-06-06T20:52:49Z","links":{"resolver":"https://pith.science/pith/L24KRSJCT2HQU7QCI4HNITHO2O","bundle":"https://pith.science/pith/L24KRSJCT2HQU7QCI4HNITHO2O/bundle.json","state":"https://pith.science/pith/L24KRSJCT2HQU7QCI4HNITHO2O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L24KRSJCT2HQU7QCI4HNITHO2O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:L24KRSJCT2HQU7QCI4HNITHO2O","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":"e38a010ed49ab9433e9cbe99776ec95cb4a4a85ac8af60fbb384b146e332d960","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T03:41:37Z","title_canon_sha256":"71be4b1a04ff278d3d122ec2791195c84e7cfb190cf2826b0a9a5e9200a9c256"},"schema_version":"1.0","source":{"id":"1805.07880","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07880","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07880v1","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07880","created_at":"2026-05-18T00:15:32Z"},{"alias_kind":"pith_short_12","alias_value":"L24KRSJCT2HQ","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"L24KRSJCT2HQU7QC","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"L24KRSJC","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:6cb9249842a353a60ecbbc744ae2e9ecf7f025f995fdb0ae9490600f8383ea32","target":"graph","created_at":"2026-05-18T00:15:32Z","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":"Learning with a {\\it convex loss} function has been a dominating paradigm for many years. It remains an interesting question how non-convex loss functions help improve the generalization of learning with broad applicability. In this paper, we study a family of objective functions formed by truncating traditional loss functions, which is applicable to both shallow learning and deep learning. Truncating loss functions has potential to be less vulnerable and more robust to large noise in observations that could be adversarial. More importantly, it is a generic technique without assuming the knowl","authors_text":"Chi Zhang, Rong Jin, Sen Yang, Shenghuo Zhu, Tianbao Yang, Yi Xu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T03:41:37Z","title":"Learning with Non-Convex Truncated Losses by SGD"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07880","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:d141b75d6698e9d31de372da97d3ba111fc4e7a9ff7dea7e10a1b2c88bbee7e7","target":"record","created_at":"2026-05-18T00:15:32Z","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":"e38a010ed49ab9433e9cbe99776ec95cb4a4a85ac8af60fbb384b146e332d960","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T03:41:37Z","title_canon_sha256":"71be4b1a04ff278d3d122ec2791195c84e7cfb190cf2826b0a9a5e9200a9c256"},"schema_version":"1.0","source":{"id":"1805.07880","kind":"arxiv","version":1}},"canonical_sha256":"5eb8a8c9229e8f0a7e02470ed44ceed39606cfdb10f515888636e38d70628e44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5eb8a8c9229e8f0a7e02470ed44ceed39606cfdb10f515888636e38d70628e44","first_computed_at":"2026-05-18T00:15:32.296569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:32.296569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w0sAesqYLqcdFoeP1rHNr4+0cepUL6JxWY/lNDLMyFxGl1AJb2K94c75RtBF2kSEciE2k4pXXjLymIQhuAVWAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:32.297121Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.07880","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d141b75d6698e9d31de372da97d3ba111fc4e7a9ff7dea7e10a1b2c88bbee7e7","sha256:6cb9249842a353a60ecbbc744ae2e9ecf7f025f995fdb0ae9490600f8383ea32"],"state_sha256":"916a0891b50a17b7b6e6c5ca94dc9d4a8911f4f862217af29fbfc97eab503e03"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eMsdEUg/tcTtcaVUTmwaj2GqognvQlBMDkTv1Ib9Scf/RBfHm5f0louqd9RmYidTOguOekptRzm0VYjYlAnMDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T20:52:49.594422Z","bundle_sha256":"24a876d093ab530861a9008bff1cbcadb9a8f1483e68e293ddb850a6c80ece3b"}}