{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7KJKLZDBSHBDJOUFUNRJYVN4YU","short_pith_number":"pith:7KJKLZDB","schema_version":"1.0","canonical_sha256":"fa92a5e46191c234ba85a3629c55bcc51147d2fd9e712b3d454b32d078bdf32c","source":{"kind":"arxiv","id":"1906.02652","version":2},"attestation_state":"computed","paper":{"title":"Toward a Characterization of Loss Functions for Distribution Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Waggoner, Cameron Musco, Nika Haghtalab","submitted_at":"2019-06-06T15:36:08Z","abstract_excerpt":"In this work we study loss functions for learning and evaluating probability distributions over large discrete domains. Unlike classification or regression where a wide variety of loss functions are used, in the distribution learning and density estimation literature, very few losses outside the dominant $log\\ loss$ are applied. We aim to understand this fact, taking an axiomatic approach to the design of loss functions for learning distributions. We start by proposing a set of desirable criteria that any good loss function should satisfy. Intuitively, these criteria require that the loss func"},"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":"1906.02652","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-06T15:36:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2c8af58c267a29a1406230fbd3ae4c99887563096d726fac5b80d8b0b3b4083c","abstract_canon_sha256":"c277e5823c4e6a5939758a2e974df8e35dd8975110d430797b7257e3980a1ffa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:51:04.629027Z","signature_b64":"d83nNpR1tTWtLHRmy1B1KTqgeRFx2HdIaaM9Zw3FvDGkJyrLylfixhdVMB1AFxOY6QAbafalNFOYRDeqP1VmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa92a5e46191c234ba85a3629c55bcc51147d2fd9e712b3d454b32d078bdf32c","last_reissued_at":"2026-07-04T23:51:04.628618Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:51:04.628618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward a Characterization of Loss Functions for Distribution Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Waggoner, Cameron Musco, Nika Haghtalab","submitted_at":"2019-06-06T15:36:08Z","abstract_excerpt":"In this work we study loss functions for learning and evaluating probability distributions over large discrete domains. Unlike classification or regression where a wide variety of loss functions are used, in the distribution learning and density estimation literature, very few losses outside the dominant $log\\ loss$ are applied. We aim to understand this fact, taking an axiomatic approach to the design of loss functions for learning distributions. We start by proposing a set of desirable criteria that any good loss function should satisfy. Intuitively, these criteria require that the loss func"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02652","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/1906.02652/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":"1906.02652","created_at":"2026-07-04T23:51:04.628673+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.02652v2","created_at":"2026-07-04T23:51:04.628673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02652","created_at":"2026-07-04T23:51:04.628673+00:00"},{"alias_kind":"pith_short_12","alias_value":"7KJKLZDBSHBD","created_at":"2026-07-04T23:51:04.628673+00:00"},{"alias_kind":"pith_short_16","alias_value":"7KJKLZDBSHBDJOUF","created_at":"2026-07-04T23:51:04.628673+00:00"},{"alias_kind":"pith_short_8","alias_value":"7KJKLZDB","created_at":"2026-07-04T23:51:04.628673+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/7KJKLZDBSHBDJOUFUNRJYVN4YU","json":"https://pith.science/pith/7KJKLZDBSHBDJOUFUNRJYVN4YU.json","graph_json":"https://pith.science/api/pith-number/7KJKLZDBSHBDJOUFUNRJYVN4YU/graph.json","events_json":"https://pith.science/api/pith-number/7KJKLZDBSHBDJOUFUNRJYVN4YU/events.json","paper":"https://pith.science/paper/7KJKLZDB"},"agent_actions":{"view_html":"https://pith.science/pith/7KJKLZDBSHBDJOUFUNRJYVN4YU","download_json":"https://pith.science/pith/7KJKLZDBSHBDJOUFUNRJYVN4YU.json","view_paper":"https://pith.science/paper/7KJKLZDB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.02652&json=true","fetch_graph":"https://pith.science/api/pith-number/7KJKLZDBSHBDJOUFUNRJYVN4YU/graph.json","fetch_events":"https://pith.science/api/pith-number/7KJKLZDBSHBDJOUFUNRJYVN4YU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7KJKLZDBSHBDJOUFUNRJYVN4YU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7KJKLZDBSHBDJOUFUNRJYVN4YU/action/storage_attestation","attest_author":"https://pith.science/pith/7KJKLZDBSHBDJOUFUNRJYVN4YU/action/author_attestation","sign_citation":"https://pith.science/pith/7KJKLZDBSHBDJOUFUNRJYVN4YU/action/citation_signature","submit_replication":"https://pith.science/pith/7KJKLZDBSHBDJOUFUNRJYVN4YU/action/replication_record"}},"created_at":"2026-07-04T23:51:04.628673+00:00","updated_at":"2026-07-04T23:51:04.628673+00:00"}