{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GZTWIL7QJ2422EONJGI2G4FDQX","short_pith_number":"pith:GZTWIL7Q","canonical_record":{"source":{"id":"2607.16768","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-18T11:05:32Z","cross_cats_sorted":[],"title_canon_sha256":"6794c1cc815e6b1d54b926338d3b4d8d6e46ffa8e222c26066a90fc9331cfb0e","abstract_canon_sha256":"656db7e8887eb9cdbf08c543b65ff19264bba878fa3f35874a947af83d132c87"},"schema_version":"1.0"},"canonical_sha256":"3667642ff04eb9ad11cd4991a370a385ff111a11cd7478593ec149b6f764a704","source":{"kind":"arxiv","id":"2607.16768","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16768","created_at":"2026-07-21T01:20:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16768v1","created_at":"2026-07-21T01:20:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16768","created_at":"2026-07-21T01:20:58Z"},{"alias_kind":"pith_short_12","alias_value":"GZTWIL7QJ242","created_at":"2026-07-21T01:20:58Z"},{"alias_kind":"pith_short_16","alias_value":"GZTWIL7QJ2422EON","created_at":"2026-07-21T01:20:58Z"},{"alias_kind":"pith_short_8","alias_value":"GZTWIL7Q","created_at":"2026-07-21T01:20:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GZTWIL7QJ2422EONJGI2G4FDQX","target":"record","payload":{"canonical_record":{"source":{"id":"2607.16768","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-18T11:05:32Z","cross_cats_sorted":[],"title_canon_sha256":"6794c1cc815e6b1d54b926338d3b4d8d6e46ffa8e222c26066a90fc9331cfb0e","abstract_canon_sha256":"656db7e8887eb9cdbf08c543b65ff19264bba878fa3f35874a947af83d132c87"},"schema_version":"1.0"},"canonical_sha256":"3667642ff04eb9ad11cd4991a370a385ff111a11cd7478593ec149b6f764a704","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:20:58.201281Z","signature_b64":"HjHx62OjBzQRO0gaG+x5VYQn5Ej5vvNt3e/GdVg1s+1RLzKDpT04RUFU0dgnLfsIz1Ak9hgXHkUMNKQ98fthCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3667642ff04eb9ad11cd4991a370a385ff111a11cd7478593ec149b6f764a704","last_reissued_at":"2026-07-21T01:20:58.200409Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:20:58.200409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.16768","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":"2026-07-21T01:20:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mwBQbNv3eOKcosBrMwW8Dt8VP+PpTNoQCn4kDvQ/9s3u1dl1kNuEsL46WG9bGdA4jajfq6JTz+JlWDyfa/RGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:40:34.561509Z"},"content_sha256":"ac6a92a40a2a4da95623e826776230612036e7885d720f5ed68cd3306f34b472","schema_version":"1.0","event_id":"sha256:ac6a92a40a2a4da95623e826776230612036e7885d720f5ed68cd3306f34b472"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GZTWIL7QJ2422EONJGI2G4FDQX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Losses from Univariate Base Functions for Noisy-Label Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jianwei Ma, Peng Hu","submitted_at":"2026-07-18T11:05:32Z","abstract_excerpt":"Learning with noisy labels is a fundamental problem in training reliable deep neural networks. Robust loss functions provide a direct and effective way to mitigate the adverse effects of label noise. However, most existing robust losses are designed directly at the level of the final multiclass objective, which makes it difficult to systematically characterize and extend their robustness properties. In this paper, we propose a general framework that constructs robust multiclass losses from univariate base functions. By defining mapping operators from base functions to multiclass losses, the ro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16768","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.16768/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":"2026-07-21T01:20:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8zL1xz6+pZs1YK2g3mx22pn8SinCYmEpwr7g/5Pycl5CZmbRrQWgTayUOFASrEGAI7Xue3WtN+9oLIhbmKYeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:40:34.562018Z"},"content_sha256":"e232784d0f49f8fa12e00c6f471331c939bafda8a1833331e29073c54ecf6b06","schema_version":"1.0","event_id":"sha256:e232784d0f49f8fa12e00c6f471331c939bafda8a1833331e29073c54ecf6b06"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GZTWIL7QJ2422EONJGI2G4FDQX/bundle.json","state_url":"https://pith.science/pith/GZTWIL7QJ2422EONJGI2G4FDQX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GZTWIL7QJ2422EONJGI2G4FDQX/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":"2026-08-08T14:40:34Z","links":{"resolver":"https://pith.science/pith/GZTWIL7QJ2422EONJGI2G4FDQX","bundle":"https://pith.science/pith/GZTWIL7QJ2422EONJGI2G4FDQX/bundle.json","state":"https://pith.science/pith/GZTWIL7QJ2422EONJGI2G4FDQX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GZTWIL7QJ2422EONJGI2G4FDQX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GZTWIL7QJ2422EONJGI2G4FDQX","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":"656db7e8887eb9cdbf08c543b65ff19264bba878fa3f35874a947af83d132c87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-18T11:05:32Z","title_canon_sha256":"6794c1cc815e6b1d54b926338d3b4d8d6e46ffa8e222c26066a90fc9331cfb0e"},"schema_version":"1.0","source":{"id":"2607.16768","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16768","created_at":"2026-07-21T01:20:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16768v1","created_at":"2026-07-21T01:20:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16768","created_at":"2026-07-21T01:20:58Z"},{"alias_kind":"pith_short_12","alias_value":"GZTWIL7QJ242","created_at":"2026-07-21T01:20:58Z"},{"alias_kind":"pith_short_16","alias_value":"GZTWIL7QJ2422EON","created_at":"2026-07-21T01:20:58Z"},{"alias_kind":"pith_short_8","alias_value":"GZTWIL7Q","created_at":"2026-07-21T01:20:58Z"}],"graph_snapshots":[{"event_id":"sha256:e232784d0f49f8fa12e00c6f471331c939bafda8a1833331e29073c54ecf6b06","target":"graph","created_at":"2026-07-21T01:20:58Z","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/2607.16768/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning with noisy labels is a fundamental problem in training reliable deep neural networks. Robust loss functions provide a direct and effective way to mitigate the adverse effects of label noise. However, most existing robust losses are designed directly at the level of the final multiclass objective, which makes it difficult to systematically characterize and extend their robustness properties. In this paper, we propose a general framework that constructs robust multiclass losses from univariate base functions. By defining mapping operators from base functions to multiclass losses, the ro","authors_text":"Jianwei Ma, Peng Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-18T11:05:32Z","title":"Robust Losses from Univariate Base Functions for Noisy-Label Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16768","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:ac6a92a40a2a4da95623e826776230612036e7885d720f5ed68cd3306f34b472","target":"record","created_at":"2026-07-21T01:20:58Z","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":"656db7e8887eb9cdbf08c543b65ff19264bba878fa3f35874a947af83d132c87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-18T11:05:32Z","title_canon_sha256":"6794c1cc815e6b1d54b926338d3b4d8d6e46ffa8e222c26066a90fc9331cfb0e"},"schema_version":"1.0","source":{"id":"2607.16768","kind":"arxiv","version":1}},"canonical_sha256":"3667642ff04eb9ad11cd4991a370a385ff111a11cd7478593ec149b6f764a704","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3667642ff04eb9ad11cd4991a370a385ff111a11cd7478593ec149b6f764a704","first_computed_at":"2026-07-21T01:20:58.200409Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:20:58.200409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HjHx62OjBzQRO0gaG+x5VYQn5Ej5vvNt3e/GdVg1s+1RLzKDpT04RUFU0dgnLfsIz1Ak9hgXHkUMNKQ98fthCg==","signature_status":"signed_v1","signed_at":"2026-07-21T01:20:58.201281Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16768","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac6a92a40a2a4da95623e826776230612036e7885d720f5ed68cd3306f34b472","sha256:e232784d0f49f8fa12e00c6f471331c939bafda8a1833331e29073c54ecf6b06"],"state_sha256":"ca43cca5c2bd56d47ca2a81b1be07394d2b6bfdd17904fc77a94518c1433cf02"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YgJbIw9JbH/8pM9xzHxVALe2lMtvoQvV/ObqZ3tOrXuch3ZC4t6X93Yy9kgOO79HxCuT95rDmUYtuUS9sYpjBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T14:40:34.565888Z","bundle_sha256":"f2c6ced996cb3e3615a9709155e64779173e686bbf1519991abff8eb78389a84"}}