{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QBGDF2RU4DXU3MYWZEJ6HLKKYL","short_pith_number":"pith:QBGDF2RU","schema_version":"1.0","canonical_sha256":"804c32ea34e0ef4db316c913e3ad4ac2caaf73f3f2d7342ca3bbe4b81895568e","source":{"kind":"arxiv","id":"1912.03263","version":3},"attestation_state":"computed","paper":{"title":"Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Duvenaud, J\\\"orn-Henrik Jacobsen, Kevin Swersky, Kuan-Chieh Wang, Mohammad Norouzi, Will Grathwohl","submitted_at":"2019-12-06T18:00:36Z","abstract_excerpt":"We propose to reinterpret a standard discriminative classifier of p(y|x) as an energy based model for the joint distribution p(x,y). In this setting, the standard class probabilities can be easily computed as well as unnormalized values of p(x) and p(x|y). Within this framework, standard discriminative architectures may beused and the model can also be trained on unlabeled data. We demonstrate that energy based training of the joint distribution improves calibration, robustness, andout-of-distribution detection while also enabling our models to generate samplesrivaling the quality of recent GA"},"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":"1912.03263","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-06T18:00:36Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"bb306cb7fc8e0a003ba61b85b8b7d6d95be3fb389ebfe4d6535ba200c80909e3","abstract_canon_sha256":"24bbb8ba291c98287b61a455df4623cd80e22d8dc5f3fedf3e7661b0f9aabc1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:35:26.395014Z","signature_b64":"t0bKrt1gCmLD80xFH5UCsPXrvoONlGU2grGsNTUdqADGpgNjMtwaNpydB75zoVcRkqO7XZbkfuP9Fb9oyPDuCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"804c32ea34e0ef4db316c913e3ad4ac2caaf73f3f2d7342ca3bbe4b81895568e","last_reissued_at":"2026-07-05T01:35:26.394557Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:35:26.394557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Duvenaud, J\\\"orn-Henrik Jacobsen, Kevin Swersky, Kuan-Chieh Wang, Mohammad Norouzi, Will Grathwohl","submitted_at":"2019-12-06T18:00:36Z","abstract_excerpt":"We propose to reinterpret a standard discriminative classifier of p(y|x) as an energy based model for the joint distribution p(x,y). In this setting, the standard class probabilities can be easily computed as well as unnormalized values of p(x) and p(x|y). Within this framework, standard discriminative architectures may beused and the model can also be trained on unlabeled data. We demonstrate that energy based training of the joint distribution improves calibration, robustness, andout-of-distribution detection while also enabling our models to generate samplesrivaling the quality of recent GA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.03263","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/1912.03263/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":"1912.03263","created_at":"2026-07-05T01:35:26.394613+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.03263v3","created_at":"2026-07-05T01:35:26.394613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03263","created_at":"2026-07-05T01:35:26.394613+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBGDF2RU4DXU","created_at":"2026-07-05T01:35:26.394613+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBGDF2RU4DXU3MYW","created_at":"2026-07-05T01:35:26.394613+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBGDF2RU","created_at":"2026-07-05T01:35:26.394613+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23819","citing_title":"Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19607","citing_title":"Contrastive Residual Energy Test-time Adaptation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2209.14577","citing_title":"Rectified Flow: A Marginal Preserving Approach to Optimal Transport","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2512.11077","citing_title":"A probabilistic framework for crystal structure denoising, phase classification, and order parameters","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14558","citing_title":"Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2105.05233","citing_title":"Diffusion Models Beat GANs on Image Synthesis","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08618","citing_title":"Beyond Toy Benchmarks: A Systematic Evaluation of OOD Detection Methods For Plant Pathology Classification","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QBGDF2RU4DXU3MYWZEJ6HLKKYL","json":"https://pith.science/pith/QBGDF2RU4DXU3MYWZEJ6HLKKYL.json","graph_json":"https://pith.science/api/pith-number/QBGDF2RU4DXU3MYWZEJ6HLKKYL/graph.json","events_json":"https://pith.science/api/pith-number/QBGDF2RU4DXU3MYWZEJ6HLKKYL/events.json","paper":"https://pith.science/paper/QBGDF2RU"},"agent_actions":{"view_html":"https://pith.science/pith/QBGDF2RU4DXU3MYWZEJ6HLKKYL","download_json":"https://pith.science/pith/QBGDF2RU4DXU3MYWZEJ6HLKKYL.json","view_paper":"https://pith.science/paper/QBGDF2RU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.03263&json=true","fetch_graph":"https://pith.science/api/pith-number/QBGDF2RU4DXU3MYWZEJ6HLKKYL/graph.json","fetch_events":"https://pith.science/api/pith-number/QBGDF2RU4DXU3MYWZEJ6HLKKYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBGDF2RU4DXU3MYWZEJ6HLKKYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBGDF2RU4DXU3MYWZEJ6HLKKYL/action/storage_attestation","attest_author":"https://pith.science/pith/QBGDF2RU4DXU3MYWZEJ6HLKKYL/action/author_attestation","sign_citation":"https://pith.science/pith/QBGDF2RU4DXU3MYWZEJ6HLKKYL/action/citation_signature","submit_replication":"https://pith.science/pith/QBGDF2RU4DXU3MYWZEJ6HLKKYL/action/replication_record"}},"created_at":"2026-07-05T01:35:26.394613+00:00","updated_at":"2026-07-05T01:35:26.394613+00:00"}