{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RU376YHLB737JARKU2FRC5VENA","short_pith_number":"pith:RU376YHL","schema_version":"1.0","canonical_sha256":"8d37ff60eb0ff7f4822aa68b1176a468261033ffae5b48f6814252679dc9754c","source":{"kind":"arxiv","id":"2007.06059","version":2},"attestation_state":"computed","paper":{"title":"It Is Likely That Your Loss Should be a Likelihood","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Evan Shelhamer, Mark Hamilton, William T. Freeman","submitted_at":"2020-07-12T18:25:17Z","abstract_excerpt":"Many common loss functions such as mean-squared-error, cross-entropy, and reconstruction loss are unnecessarily rigid. Under a probabilistic interpretation, these common losses correspond to distributions with fixed shapes and scales. We instead argue for optimizing full likelihoods that include parameters like the normal variance and softmax temperature. Joint optimization of these \"likelihood parameters\" with model parameters can adaptively tune the scales and shapes of losses in addition to the strength of regularization. We explore and systematically evaluate how to parameterize and apply "},"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":"2007.06059","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-07-12T18:25:17Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"13efdb2fb2fea144b15d6da3a0622f6b8fd6a9fb45e8c5548008fdf3f8f6d1a8","abstract_canon_sha256":"89ce933b8f53e66f23b8e6212b0229343fa4ea3a34be7da9467aedbe226c241a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:44.399841Z","signature_b64":"uXv1NY2OIKaR0NrtB3mcUGcY/6m5b37aTKxOizXRIT38p010Fek79tv2juEGqpVUgTSOki7rtPBynmy9IP3PCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d37ff60eb0ff7f4822aa68b1176a468261033ffae5b48f6814252679dc9754c","last_reissued_at":"2026-07-05T01:39:44.399444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:44.399444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"It Is Likely That Your Loss Should be a Likelihood","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Evan Shelhamer, Mark Hamilton, William T. Freeman","submitted_at":"2020-07-12T18:25:17Z","abstract_excerpt":"Many common loss functions such as mean-squared-error, cross-entropy, and reconstruction loss are unnecessarily rigid. Under a probabilistic interpretation, these common losses correspond to distributions with fixed shapes and scales. We instead argue for optimizing full likelihoods that include parameters like the normal variance and softmax temperature. Joint optimization of these \"likelihood parameters\" with model parameters can adaptively tune the scales and shapes of losses in addition to the strength of regularization. We explore and systematically evaluate how to parameterize and apply "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.06059","kind":"arxiv","version":2},"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/2007.06059/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":"2007.06059","created_at":"2026-07-05T01:39:44.399504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.06059v2","created_at":"2026-07-05T01:39:44.399504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.06059","created_at":"2026-07-05T01:39:44.399504+00:00"},{"alias_kind":"pith_short_12","alias_value":"RU376YHLB737","created_at":"2026-07-05T01:39:44.399504+00:00"},{"alias_kind":"pith_short_16","alias_value":"RU376YHLB737JARK","created_at":"2026-07-05T01:39:44.399504+00:00"},{"alias_kind":"pith_short_8","alias_value":"RU376YHL","created_at":"2026-07-05T01:39:44.399504+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.04391","citing_title":"Plant-Centric Metaverse: A Biocentric-Creation Framework for Ecological Art and Digital Symbiosis","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RU376YHLB737JARKU2FRC5VENA","json":"https://pith.science/pith/RU376YHLB737JARKU2FRC5VENA.json","graph_json":"https://pith.science/api/pith-number/RU376YHLB737JARKU2FRC5VENA/graph.json","events_json":"https://pith.science/api/pith-number/RU376YHLB737JARKU2FRC5VENA/events.json","paper":"https://pith.science/paper/RU376YHL"},"agent_actions":{"view_html":"https://pith.science/pith/RU376YHLB737JARKU2FRC5VENA","download_json":"https://pith.science/pith/RU376YHLB737JARKU2FRC5VENA.json","view_paper":"https://pith.science/paper/RU376YHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.06059&json=true","fetch_graph":"https://pith.science/api/pith-number/RU376YHLB737JARKU2FRC5VENA/graph.json","fetch_events":"https://pith.science/api/pith-number/RU376YHLB737JARKU2FRC5VENA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RU376YHLB737JARKU2FRC5VENA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RU376YHLB737JARKU2FRC5VENA/action/storage_attestation","attest_author":"https://pith.science/pith/RU376YHLB737JARKU2FRC5VENA/action/author_attestation","sign_citation":"https://pith.science/pith/RU376YHLB737JARKU2FRC5VENA/action/citation_signature","submit_replication":"https://pith.science/pith/RU376YHLB737JARKU2FRC5VENA/action/replication_record"}},"created_at":"2026-07-05T01:39:44.399504+00:00","updated_at":"2026-07-05T01:39:44.399504+00:00"}