{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AZJ76JVBPIYKXYULCLG6PDEXZB","short_pith_number":"pith:AZJ76JVB","schema_version":"1.0","canonical_sha256":"0653ff26a17a30abe28b12cde78c97c85852ed6a989aac0e6a30c5beb3124d41","source":{"kind":"arxiv","id":"2606.28654","version":1},"attestation_state":"computed","paper":{"title":"FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Sachith Seneviratne, Saman Halgamuge, Thiru Thillai Nadarasar Bahavan","submitted_at":"2026-06-26T23:55:44Z","abstract_excerpt":"Deep Neural Network (DNN) classifiers suffer from poor calibration when their softmax outputs (predictive confidence) deviate from the empirical likelihoods. This manifests itself as either overconfident incorrect predictions or under-confident correct predictions. Label smoothing (LS) enhances model calibration by introducing entropy regularization during training through redistributing probability mass from the ground-truth label to the remaining classes. LS, including Margin-based LS (MbLS), have restrictive assumptions: they rely on predefined, uniform smoothing rules and only tackle overc"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.28654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-26T23:55:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0b0b3541d1b199798846ac92e1628af84e34101ca26b1e62a1e8bd606c130b7c","abstract_canon_sha256":"257fb2ce0d36bf382eb4529c4d829a029dbe8a58d371d7a9bc885bc4e6aebfa2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:46.034404Z","signature_b64":"RMCKNS/j/166Nh69NAwToEjEyRPK3oh2lSwEb6mWra4tRcamLOE/zZ8h5DuhrT+qkOty5sp4Nai/QoUqLUWaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0653ff26a17a30abe28b12cde78c97c85852ed6a989aac0e6a30c5beb3124d41","last_reissued_at":"2026-06-30T01:16:46.033627Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:46.033627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedLAS: Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Sachith Seneviratne, Saman Halgamuge, Thiru Thillai Nadarasar Bahavan","submitted_at":"2026-06-26T23:55:44Z","abstract_excerpt":"Deep Neural Network (DNN) classifiers suffer from poor calibration when their softmax outputs (predictive confidence) deviate from the empirical likelihoods. This manifests itself as either overconfident incorrect predictions or under-confident correct predictions. Label smoothing (LS) enhances model calibration by introducing entropy regularization during training through redistributing probability mass from the ground-truth label to the remaining classes. LS, including Margin-based LS (MbLS), have restrictive assumptions: they rely on predefined, uniform smoothing rules and only tackle overc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28654","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/2606.28654/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.28654","created_at":"2026-06-30T01:16:46.033732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28654v1","created_at":"2026-06-30T01:16:46.033732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28654","created_at":"2026-06-30T01:16:46.033732+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZJ76JVBPIYK","created_at":"2026-06-30T01:16:46.033732+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZJ76JVBPIYKXYUL","created_at":"2026-06-30T01:16:46.033732+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZJ76JVB","created_at":"2026-06-30T01:16:46.033732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZJ76JVBPIYKXYULCLG6PDEXZB","json":"https://pith.science/pith/AZJ76JVBPIYKXYULCLG6PDEXZB.json","graph_json":"https://pith.science/api/pith-number/AZJ76JVBPIYKXYULCLG6PDEXZB/graph.json","events_json":"https://pith.science/api/pith-number/AZJ76JVBPIYKXYULCLG6PDEXZB/events.json","paper":"https://pith.science/paper/AZJ76JVB"},"agent_actions":{"view_html":"https://pith.science/pith/AZJ76JVBPIYKXYULCLG6PDEXZB","download_json":"https://pith.science/pith/AZJ76JVBPIYKXYULCLG6PDEXZB.json","view_paper":"https://pith.science/paper/AZJ76JVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28654&json=true","fetch_graph":"https://pith.science/api/pith-number/AZJ76JVBPIYKXYULCLG6PDEXZB/graph.json","fetch_events":"https://pith.science/api/pith-number/AZJ76JVBPIYKXYULCLG6PDEXZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZJ76JVBPIYKXYULCLG6PDEXZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZJ76JVBPIYKXYULCLG6PDEXZB/action/storage_attestation","attest_author":"https://pith.science/pith/AZJ76JVBPIYKXYULCLG6PDEXZB/action/author_attestation","sign_citation":"https://pith.science/pith/AZJ76JVBPIYKXYULCLG6PDEXZB/action/citation_signature","submit_replication":"https://pith.science/pith/AZJ76JVBPIYKXYULCLG6PDEXZB/action/replication_record"}},"created_at":"2026-06-30T01:16:46.033732+00:00","updated_at":"2026-06-30T01:16:46.033732+00:00"}