{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NORNHE7GUA2MTTYYEFUBPWIVJH","short_pith_number":"pith:NORNHE7G","canonical_record":{"source":{"id":"2502.20604","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-28T00:07:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6992654b20ec7f8d3045dd5a0878dc9fd2719773ff13bb9a5277d7d0b378f82c","abstract_canon_sha256":"3faf48fec885b1814949c94e2a91b9bcd8764fa87a5844085caf71d9b4852fae"},"schema_version":"1.0"},"canonical_sha256":"6ba2d393e6a034c9cf18216817d91549d8c3ab1c501e28b20d352dbe50519c50","source":{"kind":"arxiv","id":"2502.20604","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20604","created_at":"2026-07-05T10:21:36Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20604v1","created_at":"2026-07-05T10:21:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20604","created_at":"2026-07-05T10:21:36Z"},{"alias_kind":"pith_short_12","alias_value":"NORNHE7GUA2M","created_at":"2026-07-05T10:21:36Z"},{"alias_kind":"pith_short_16","alias_value":"NORNHE7GUA2MTTYY","created_at":"2026-07-05T10:21:36Z"},{"alias_kind":"pith_short_8","alias_value":"NORNHE7G","created_at":"2026-07-05T10:21:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NORNHE7GUA2MTTYYEFUBPWIVJH","target":"record","payload":{"canonical_record":{"source":{"id":"2502.20604","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-28T00:07:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6992654b20ec7f8d3045dd5a0878dc9fd2719773ff13bb9a5277d7d0b378f82c","abstract_canon_sha256":"3faf48fec885b1814949c94e2a91b9bcd8764fa87a5844085caf71d9b4852fae"},"schema_version":"1.0"},"canonical_sha256":"6ba2d393e6a034c9cf18216817d91549d8c3ab1c501e28b20d352dbe50519c50","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:36.006149Z","signature_b64":"PFDKYg8D7JrU+TTzIMn4BkFCcYJDiGQA4kGDWuiWTrB8yxrIWKFP3wIl/orgjoX585a4vzxUiXheLU/+XKHTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ba2d393e6a034c9cf18216817d91549d8c3ab1c501e28b20d352dbe50519c50","last_reissued_at":"2026-07-05T10:21:36.005596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:36.005596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.20604","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":"2026-07-05T10:21:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3//qEOfwpcAcW2t9D/XHsSVOosHvCCefgZnuwUKWOdjg2yE3VVOqaUXNNC3R6yeUdsRYC5UCN6EbsJkfU8axDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:45:34.635171Z"},"content_sha256":"712d7ad36cebdf0d12452e9e018f3557839975bb6afe99288036231b70ce9bc4","schema_version":"1.0","event_id":"sha256:712d7ad36cebdf0d12452e9e018f3557839975bb6afe99288036231b70ce9bc4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NORNHE7GUA2MTTYYEFUBPWIVJH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring the Impact of Temperature Scaling in Softmax for Classification and Adversarial Robustness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bokai Yang, Hao Xuan, Xingyu Li","submitted_at":"2025-02-28T00:07:45Z","abstract_excerpt":"The softmax function is a fundamental component in deep learning. This study delves into the often-overlooked parameter within the softmax function, known as \"temperature,\" providing novel insights into the practical and theoretical aspects of temperature scaling for image classification. Our empirical studies, adopting convolutional neural networks and transformers on multiple benchmark datasets, reveal that moderate temperatures generally introduce better overall performance. Through extensive experiments and rigorous theoretical analysis, we explore the role of temperature scaling in model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20604","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/2502.20604/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":"2026-07-05T10:21:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FgOxVJ+4zp3II6WrswTa7Oz4ciIqcoL2sZz3FEOaU3FkJGb/Vtq3bL7VXEHDsjqj/OQiGKaAUjtFblVr53twBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T11:45:34.635931Z"},"content_sha256":"859b783f46bcb1cfba9745f880ad9b6c86ac17aa2956f09ba05a14353d8f674e","schema_version":"1.0","event_id":"sha256:859b783f46bcb1cfba9745f880ad9b6c86ac17aa2956f09ba05a14353d8f674e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NORNHE7GUA2MTTYYEFUBPWIVJH/bundle.json","state_url":"https://pith.science/pith/NORNHE7GUA2MTTYYEFUBPWIVJH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NORNHE7GUA2MTTYYEFUBPWIVJH/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":"2026-08-06T11:45:34Z","links":{"resolver":"https://pith.science/pith/NORNHE7GUA2MTTYYEFUBPWIVJH","bundle":"https://pith.science/pith/NORNHE7GUA2MTTYYEFUBPWIVJH/bundle.json","state":"https://pith.science/pith/NORNHE7GUA2MTTYYEFUBPWIVJH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NORNHE7GUA2MTTYYEFUBPWIVJH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NORNHE7GUA2MTTYYEFUBPWIVJH","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":"3faf48fec885b1814949c94e2a91b9bcd8764fa87a5844085caf71d9b4852fae","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-28T00:07:45Z","title_canon_sha256":"6992654b20ec7f8d3045dd5a0878dc9fd2719773ff13bb9a5277d7d0b378f82c"},"schema_version":"1.0","source":{"id":"2502.20604","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20604","created_at":"2026-07-05T10:21:36Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20604v1","created_at":"2026-07-05T10:21:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20604","created_at":"2026-07-05T10:21:36Z"},{"alias_kind":"pith_short_12","alias_value":"NORNHE7GUA2M","created_at":"2026-07-05T10:21:36Z"},{"alias_kind":"pith_short_16","alias_value":"NORNHE7GUA2MTTYY","created_at":"2026-07-05T10:21:36Z"},{"alias_kind":"pith_short_8","alias_value":"NORNHE7G","created_at":"2026-07-05T10:21:36Z"}],"graph_snapshots":[{"event_id":"sha256:859b783f46bcb1cfba9745f880ad9b6c86ac17aa2956f09ba05a14353d8f674e","target":"graph","created_at":"2026-07-05T10:21:36Z","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/2502.20604/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The softmax function is a fundamental component in deep learning. This study delves into the often-overlooked parameter within the softmax function, known as \"temperature,\" providing novel insights into the practical and theoretical aspects of temperature scaling for image classification. Our empirical studies, adopting convolutional neural networks and transformers on multiple benchmark datasets, reveal that moderate temperatures generally introduce better overall performance. Through extensive experiments and rigorous theoretical analysis, we explore the role of temperature scaling in model ","authors_text":"Bokai Yang, Hao Xuan, Xingyu Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-28T00:07:45Z","title":"Exploring the Impact of Temperature Scaling in Softmax for Classification and Adversarial Robustness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20604","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":"sha256:712d7ad36cebdf0d12452e9e018f3557839975bb6afe99288036231b70ce9bc4","target":"record","created_at":"2026-07-05T10:21:36Z","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":"3faf48fec885b1814949c94e2a91b9bcd8764fa87a5844085caf71d9b4852fae","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-28T00:07:45Z","title_canon_sha256":"6992654b20ec7f8d3045dd5a0878dc9fd2719773ff13bb9a5277d7d0b378f82c"},"schema_version":"1.0","source":{"id":"2502.20604","kind":"arxiv","version":1}},"canonical_sha256":"6ba2d393e6a034c9cf18216817d91549d8c3ab1c501e28b20d352dbe50519c50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ba2d393e6a034c9cf18216817d91549d8c3ab1c501e28b20d352dbe50519c50","first_computed_at":"2026-07-05T10:21:36.005596Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:36.005596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PFDKYg8D7JrU+TTzIMn4BkFCcYJDiGQA4kGDWuiWTrB8yxrIWKFP3wIl/orgjoX585a4vzxUiXheLU/+XKHTBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:36.006149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.20604","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:712d7ad36cebdf0d12452e9e018f3557839975bb6afe99288036231b70ce9bc4","sha256:859b783f46bcb1cfba9745f880ad9b6c86ac17aa2956f09ba05a14353d8f674e"],"state_sha256":"14ae05fcb3b5688a2c99585d6d1708917ba3b272505b847a8f4a36f8d8df06be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rnI/rJKBPnBBosr4h3muGfhSQCNZTIBjfOApLFwpqCPaPwc+u39QGmEmmpiJQSgrVPs5LXotaI2Itr4F82E2Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T11:45:34.640431Z","bundle_sha256":"df996df89353c52755067be52a9eaed49a7feee3757e0428df4cf9730e2a9abc"}}