{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:SILQPHBOWCTKGP2LARKDE67IRL","short_pith_number":"pith:SILQPHBO","canonical_record":{"source":{"id":"2009.09496","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-20T18:42:13Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"245c4416812c8695c410238b66255579f463d16aa0f1571cca79838995db161f","abstract_canon_sha256":"98db338b7241ad3a2587cfe2e7228f4f24c3de15872b05fc382403625e30276b"},"schema_version":"1.0"},"canonical_sha256":"9217079c2eb0a6a33f4b0454327be88afcd9311cc4e4cd9f7f5a3e7f79a04c67","source":{"kind":"arxiv","id":"2009.09496","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.09496","created_at":"2026-07-05T01:36:41Z"},{"alias_kind":"arxiv_version","alias_value":"2009.09496v1","created_at":"2026-07-05T01:36:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.09496","created_at":"2026-07-05T01:36:41Z"},{"alias_kind":"pith_short_12","alias_value":"SILQPHBOWCTK","created_at":"2026-07-05T01:36:41Z"},{"alias_kind":"pith_short_16","alias_value":"SILQPHBOWCTKGP2L","created_at":"2026-07-05T01:36:41Z"},{"alias_kind":"pith_short_8","alias_value":"SILQPHBO","created_at":"2026-07-05T01:36:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:SILQPHBOWCTKGP2LARKDE67IRL","target":"record","payload":{"canonical_record":{"source":{"id":"2009.09496","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-20T18:42:13Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"245c4416812c8695c410238b66255579f463d16aa0f1571cca79838995db161f","abstract_canon_sha256":"98db338b7241ad3a2587cfe2e7228f4f24c3de15872b05fc382403625e30276b"},"schema_version":"1.0"},"canonical_sha256":"9217079c2eb0a6a33f4b0454327be88afcd9311cc4e4cd9f7f5a3e7f79a04c67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:36:41.205666Z","signature_b64":"I8fe/bYUi8ATpcCtXEQb1gC0rZiI6nDeHzwvDJ4edCFxq2HGCK9xlpRiB6T+t9rednxZ+8gUVk1ZOuKin9V7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9217079c2eb0a6a33f4b0454327be88afcd9311cc4e4cd9f7f5a3e7f79a04c67","last_reissued_at":"2026-07-05T01:36:41.205239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:36:41.205239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.09496","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":"2026-07-05T01:36:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xhdp9SZymF1VcrnySvJZO1Yn00VoJxwztt8PyNIk59WEI4qdVG3eZXS2eWdz7BaykBhswKKtnjckJCVLlHhzAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:17:06.606218Z"},"content_sha256":"c8022ed917d2619f9df95b51b55ee2098d2e71eda22620c530a61de021161446","schema_version":"1.0","event_id":"sha256:c8022ed917d2619f9df95b51b55ee2098d2e71eda22620c530a61de021161446"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:SILQPHBOWCTKGP2LARKDE67IRL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Soft Labels via Meta Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Nidhi Vyas, Shreyas Saxena, Thomas Voice","submitted_at":"2020-09-20T18:42:13Z","abstract_excerpt":"One-hot labels do not represent soft decision boundaries among concepts, and hence, models trained on them are prone to overfitting. Using soft labels as targets provide regularization, but different soft labels might be optimal at different stages of optimization. Also, training with fixed labels in the presence of noisy annotations leads to worse generalization. To address these limitations, we propose a framework, where we treat the labels as learnable parameters, and optimize them along with model parameters. The learned labels continuously adapt themselves to the model's state, thereby pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.09496","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/2009.09496/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":"2026-07-05T01:36:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+2xlyG0nuAaW/DPcYa3gqKT8FGtJFh2VFewAhwQGXuBneyHp41RkSJl3ecg8AUOcXZ95yNuxwUJzIvblkaphAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:17:06.606757Z"},"content_sha256":"4c2016d45997d26c8b5606beec4f152ad947c9c56572fbdd8c7e69fbf21371d3","schema_version":"1.0","event_id":"sha256:4c2016d45997d26c8b5606beec4f152ad947c9c56572fbdd8c7e69fbf21371d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SILQPHBOWCTKGP2LARKDE67IRL/bundle.json","state_url":"https://pith.science/pith/SILQPHBOWCTKGP2LARKDE67IRL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SILQPHBOWCTKGP2LARKDE67IRL/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":"2026-08-15T19:17:06Z","links":{"resolver":"https://pith.science/pith/SILQPHBOWCTKGP2LARKDE67IRL","bundle":"https://pith.science/pith/SILQPHBOWCTKGP2LARKDE67IRL/bundle.json","state":"https://pith.science/pith/SILQPHBOWCTKGP2LARKDE67IRL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SILQPHBOWCTKGP2LARKDE67IRL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SILQPHBOWCTKGP2LARKDE67IRL","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":"98db338b7241ad3a2587cfe2e7228f4f24c3de15872b05fc382403625e30276b","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-20T18:42:13Z","title_canon_sha256":"245c4416812c8695c410238b66255579f463d16aa0f1571cca79838995db161f"},"schema_version":"1.0","source":{"id":"2009.09496","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.09496","created_at":"2026-07-05T01:36:41Z"},{"alias_kind":"arxiv_version","alias_value":"2009.09496v1","created_at":"2026-07-05T01:36:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.09496","created_at":"2026-07-05T01:36:41Z"},{"alias_kind":"pith_short_12","alias_value":"SILQPHBOWCTK","created_at":"2026-07-05T01:36:41Z"},{"alias_kind":"pith_short_16","alias_value":"SILQPHBOWCTKGP2L","created_at":"2026-07-05T01:36:41Z"},{"alias_kind":"pith_short_8","alias_value":"SILQPHBO","created_at":"2026-07-05T01:36:41Z"}],"graph_snapshots":[{"event_id":"sha256:4c2016d45997d26c8b5606beec4f152ad947c9c56572fbdd8c7e69fbf21371d3","target":"graph","created_at":"2026-07-05T01:36:41Z","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/2009.09496/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One-hot labels do not represent soft decision boundaries among concepts, and hence, models trained on them are prone to overfitting. Using soft labels as targets provide regularization, but different soft labels might be optimal at different stages of optimization. Also, training with fixed labels in the presence of noisy annotations leads to worse generalization. To address these limitations, we propose a framework, where we treat the labels as learnable parameters, and optimize them along with model parameters. The learned labels continuously adapt themselves to the model's state, thereby pr","authors_text":"Nidhi Vyas, Shreyas Saxena, Thomas Voice","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-20T18:42:13Z","title":"Learning Soft Labels via Meta Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.09496","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:c8022ed917d2619f9df95b51b55ee2098d2e71eda22620c530a61de021161446","target":"record","created_at":"2026-07-05T01:36:41Z","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":"98db338b7241ad3a2587cfe2e7228f4f24c3de15872b05fc382403625e30276b","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-20T18:42:13Z","title_canon_sha256":"245c4416812c8695c410238b66255579f463d16aa0f1571cca79838995db161f"},"schema_version":"1.0","source":{"id":"2009.09496","kind":"arxiv","version":1}},"canonical_sha256":"9217079c2eb0a6a33f4b0454327be88afcd9311cc4e4cd9f7f5a3e7f79a04c67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9217079c2eb0a6a33f4b0454327be88afcd9311cc4e4cd9f7f5a3e7f79a04c67","first_computed_at":"2026-07-05T01:36:41.205239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:36:41.205239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I8fe/bYUi8ATpcCtXEQb1gC0rZiI6nDeHzwvDJ4edCFxq2HGCK9xlpRiB6T+t9rednxZ+8gUVk1ZOuKin9V7Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T01:36:41.205666Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.09496","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8022ed917d2619f9df95b51b55ee2098d2e71eda22620c530a61de021161446","sha256:4c2016d45997d26c8b5606beec4f152ad947c9c56572fbdd8c7e69fbf21371d3"],"state_sha256":"6d53a38fdf16eb015c5fada0030cef27cd46b37969f9738b5a470ca9bf649885"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HLtpKSynVrtHqDMQG77EOY3y8H/DR264ihemCM6cWLXQvlSuuRX01xlTY/W+/O3R7zVxO60B3DiKqBicEnuqCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T19:17:06.611405Z","bundle_sha256":"afd89d4dcb5c175a76e4dba29721e0c724e53d138b83fe6c5ffc4a50e88c5b86"}}