{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2JY3P4BU737QJJUDIMB5J6LO3U","short_pith_number":"pith:2JY3P4BU","canonical_record":{"source":{"id":"2404.04575","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-06T09:55:03Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"fef2a89518505cfa4951558bccc83ee46fb914a7af9aebb0a08b0b52e4697568","abstract_canon_sha256":"f037e05592c69fe8b778aad469d6428a1834781c772f81b6a7da857cc7bb40a2"},"schema_version":"1.0"},"canonical_sha256":"d271b7f034feff04a6834303d4f96edd16b35fed3b0cf308392b8dde84c0ac6e","source":{"kind":"arxiv","id":"2404.04575","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04575","created_at":"2026-07-05T08:32:39Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04575v3","created_at":"2026-07-05T08:32:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04575","created_at":"2026-07-05T08:32:39Z"},{"alias_kind":"pith_short_12","alias_value":"2JY3P4BU737Q","created_at":"2026-07-05T08:32:39Z"},{"alias_kind":"pith_short_16","alias_value":"2JY3P4BU737QJJUD","created_at":"2026-07-05T08:32:39Z"},{"alias_kind":"pith_short_8","alias_value":"2JY3P4BU","created_at":"2026-07-05T08:32:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2JY3P4BU737QJJUDIMB5J6LO3U","target":"record","payload":{"canonical_record":{"source":{"id":"2404.04575","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-06T09:55:03Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"fef2a89518505cfa4951558bccc83ee46fb914a7af9aebb0a08b0b52e4697568","abstract_canon_sha256":"f037e05592c69fe8b778aad469d6428a1834781c772f81b6a7da857cc7bb40a2"},"schema_version":"1.0"},"canonical_sha256":"d271b7f034feff04a6834303d4f96edd16b35fed3b0cf308392b8dde84c0ac6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:39.302786Z","signature_b64":"b7lLrIaDl10eQhO31vkv8z2ZHi2g68WJTf5KSpQoCtaoLuSXcMazPRoy3YUXSikhwx6+1Wh/wBNKIHxw6jTYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d271b7f034feff04a6834303d4f96edd16b35fed3b0cf308392b8dde84c0ac6e","last_reissued_at":"2026-07-05T08:32:39.302297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:39.302297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.04575","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:32:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aTwcQF86vHmxKKlFKvPy1dqhKKszlY7ps4UPEp8I9PI0M1kZKv1vbtg6Kr8+PIuH/+Jy0ZclOW8b9yz1bMA1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:49:06.682768Z"},"content_sha256":"8c35a0d87271cb42fe909d297a57956a0c3b846d287a938ef69af7ffdd95d3c0","schema_version":"1.0","event_id":"sha256:8c35a0d87271cb42fe909d297a57956a0c3b846d287a938ef69af7ffdd95d3c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2JY3P4BU737QJJUDIMB5J6LO3U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Lijun Zhang, Mao Xu, Siqi Guo, Tianbao Yang, Tuo Zhao, Zi-Hao Qiu","submitted_at":"2024-04-06T09:55:03Z","abstract_excerpt":"The temperature parameter plays a profound role during training and/or inference with large foundation models (LFMs) such as large language models (LLMs) and CLIP models. Particularly, it adjusts the logits in the softmax function in LLMs, which is crucial for next token generation, and it scales the similarities in the contrastive loss for training CLIP models. A significant question remains: Is it viable to learn a neural network to predict a personalized temperature of any input data for enhancing LFMs\"? In this paper, we present a principled framework for learning a small yet generalizable"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04575","kind":"arxiv","version":3},"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/2404.04575/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":"2026-07-05T08:32:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7CzEnzcfqJ0g+W7ZbVhYLyvPzenki9jyh7fh8kPrbxTdg8FTKRXo0E4V+bUVKqqlMf/41IeCGIvscRJkAVK2BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:49:06.683278Z"},"content_sha256":"964cdb1010c05e6d65f7105512b4784a418dba7ebd9f7553defafe2e9b2d3ea9","schema_version":"1.0","event_id":"sha256:964cdb1010c05e6d65f7105512b4784a418dba7ebd9f7553defafe2e9b2d3ea9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2JY3P4BU737QJJUDIMB5J6LO3U/bundle.json","state_url":"https://pith.science/pith/2JY3P4BU737QJJUDIMB5J6LO3U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2JY3P4BU737QJJUDIMB5J6LO3U/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":"2026-08-10T23:49:06Z","links":{"resolver":"https://pith.science/pith/2JY3P4BU737QJJUDIMB5J6LO3U","bundle":"https://pith.science/pith/2JY3P4BU737QJJUDIMB5J6LO3U/bundle.json","state":"https://pith.science/pith/2JY3P4BU737QJJUDIMB5J6LO3U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2JY3P4BU737QJJUDIMB5J6LO3U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2JY3P4BU737QJJUDIMB5J6LO3U","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":"f037e05592c69fe8b778aad469d6428a1834781c772f81b6a7da857cc7bb40a2","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-06T09:55:03Z","title_canon_sha256":"fef2a89518505cfa4951558bccc83ee46fb914a7af9aebb0a08b0b52e4697568"},"schema_version":"1.0","source":{"id":"2404.04575","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04575","created_at":"2026-07-05T08:32:39Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04575v3","created_at":"2026-07-05T08:32:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04575","created_at":"2026-07-05T08:32:39Z"},{"alias_kind":"pith_short_12","alias_value":"2JY3P4BU737Q","created_at":"2026-07-05T08:32:39Z"},{"alias_kind":"pith_short_16","alias_value":"2JY3P4BU737QJJUD","created_at":"2026-07-05T08:32:39Z"},{"alias_kind":"pith_short_8","alias_value":"2JY3P4BU","created_at":"2026-07-05T08:32:39Z"}],"graph_snapshots":[{"event_id":"sha256:964cdb1010c05e6d65f7105512b4784a418dba7ebd9f7553defafe2e9b2d3ea9","target":"graph","created_at":"2026-07-05T08:32:39Z","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/2404.04575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The temperature parameter plays a profound role during training and/or inference with large foundation models (LFMs) such as large language models (LLMs) and CLIP models. Particularly, it adjusts the logits in the softmax function in LLMs, which is crucial for next token generation, and it scales the similarities in the contrastive loss for training CLIP models. A significant question remains: Is it viable to learn a neural network to predict a personalized temperature of any input data for enhancing LFMs\"? In this paper, we present a principled framework for learning a small yet generalizable","authors_text":"Lijun Zhang, Mao Xu, Siqi Guo, Tianbao Yang, Tuo Zhao, Zi-Hao Qiu","cross_cats":["cs.AI","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-06T09:55:03Z","title":"To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04575","kind":"arxiv","version":3},"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":"sha256:8c35a0d87271cb42fe909d297a57956a0c3b846d287a938ef69af7ffdd95d3c0","target":"record","created_at":"2026-07-05T08:32:39Z","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":"f037e05592c69fe8b778aad469d6428a1834781c772f81b6a7da857cc7bb40a2","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-06T09:55:03Z","title_canon_sha256":"fef2a89518505cfa4951558bccc83ee46fb914a7af9aebb0a08b0b52e4697568"},"schema_version":"1.0","source":{"id":"2404.04575","kind":"arxiv","version":3}},"canonical_sha256":"d271b7f034feff04a6834303d4f96edd16b35fed3b0cf308392b8dde84c0ac6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d271b7f034feff04a6834303d4f96edd16b35fed3b0cf308392b8dde84c0ac6e","first_computed_at":"2026-07-05T08:32:39.302297Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:39.302297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b7lLrIaDl10eQhO31vkv8z2ZHi2g68WJTf5KSpQoCtaoLuSXcMazPRoy3YUXSikhwx6+1Wh/wBNKIHxw6jTYDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:39.302786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.04575","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c35a0d87271cb42fe909d297a57956a0c3b846d287a938ef69af7ffdd95d3c0","sha256:964cdb1010c05e6d65f7105512b4784a418dba7ebd9f7553defafe2e9b2d3ea9"],"state_sha256":"315057b29a8c0bbe6c908f05534b47c646ef05b139b467648420365396da8767"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QaG39InvVzzw0zBI9mrd9vO7tvTtW75aH4XoHati/5b25xc42/FKOZ23+Xbgffob42Nsi1qJqTXdQGYdHOqNDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T23:49:06.687199Z","bundle_sha256":"a1f0a4614e254dbc1d4111854f0f1b267681785a1cf075b30ab668529a868de2"}}