{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HPPC4PZDBP6UB6FRTZOAHWKL4B","short_pith_number":"pith:HPPC4PZD","schema_version":"1.0","canonical_sha256":"3bde2e3f230bfd40f8b19e5c03d94be07d569c76d1ba674e3d8919255a90ce6a","source":{"kind":"arxiv","id":"1709.08868","version":3},"attestation_state":"computed","paper":{"title":"Learning Energy-Based Models as Generative ConvNets via Multi-grid Modeling and Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"stat.ML","authors_text":"Junpei Zhou, Ruiqi Gao, Song-Chun Zhu, Yang Lu, Ying Nian Wu","submitted_at":"2017-09-26T07:48:52Z","abstract_excerpt":"This paper proposes a multi-grid method for learning energy-based generative ConvNet models of images. For each grid, we learn an energy-based probabilistic model where the energy function is defined by a bottom-up convolutional neural network (ConvNet or CNN). Learning such a model requires generating synthesized examples from the model. Within each iteration of our learning algorithm, for each observed training image, we generate synthesized images at multiple grids by initializing the finite-step MCMC sampling from a minimal 1 x 1 version of the training image. The synthesized image at each"},"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":"1709.08868","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-09-26T07:48:52Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"43a26b1c90616ff48662882fb868645219749ff7bc13d98e10a7cca60e7336f4","abstract_canon_sha256":"2c2c294a4742ecde9065806d5c2b52601f3614911a882f52d9c9e19e010697e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:04.291675Z","signature_b64":"Kt8RwW49qjDN5zIbtl3H0lFiMyq49qS5KygnlsCM3z3YYaVyydmT/E7eiWTMByOiIerwENqwHpOJEPOsOzHpBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bde2e3f230bfd40f8b19e5c03d94be07d569c76d1ba674e3d8919255a90ce6a","last_reissued_at":"2026-07-05T01:43:04.291297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:04.291297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Energy-Based Models as Generative ConvNets via Multi-grid Modeling and Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"stat.ML","authors_text":"Junpei Zhou, Ruiqi Gao, Song-Chun Zhu, Yang Lu, Ying Nian Wu","submitted_at":"2017-09-26T07:48:52Z","abstract_excerpt":"This paper proposes a multi-grid method for learning energy-based generative ConvNet models of images. For each grid, we learn an energy-based probabilistic model where the energy function is defined by a bottom-up convolutional neural network (ConvNet or CNN). Learning such a model requires generating synthesized examples from the model. Within each iteration of our learning algorithm, for each observed training image, we generate synthesized images at multiple grids by initializing the finite-step MCMC sampling from a minimal 1 x 1 version of the training image. The synthesized image at each"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.08868","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/1709.08868/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":"1709.08868","created_at":"2026-07-05T01:43:04.291372+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.08868v3","created_at":"2026-07-05T01:43:04.291372+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.08868","created_at":"2026-07-05T01:43:04.291372+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPPC4PZDBP6U","created_at":"2026-07-05T01:43:04.291372+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPPC4PZDBP6UB6FR","created_at":"2026-07-05T01:43:04.291372+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPPC4PZD","created_at":"2026-07-05T01:43:04.291372+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/HPPC4PZDBP6UB6FRTZOAHWKL4B","json":"https://pith.science/pith/HPPC4PZDBP6UB6FRTZOAHWKL4B.json","graph_json":"https://pith.science/api/pith-number/HPPC4PZDBP6UB6FRTZOAHWKL4B/graph.json","events_json":"https://pith.science/api/pith-number/HPPC4PZDBP6UB6FRTZOAHWKL4B/events.json","paper":"https://pith.science/paper/HPPC4PZD"},"agent_actions":{"view_html":"https://pith.science/pith/HPPC4PZDBP6UB6FRTZOAHWKL4B","download_json":"https://pith.science/pith/HPPC4PZDBP6UB6FRTZOAHWKL4B.json","view_paper":"https://pith.science/paper/HPPC4PZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.08868&json=true","fetch_graph":"https://pith.science/api/pith-number/HPPC4PZDBP6UB6FRTZOAHWKL4B/graph.json","fetch_events":"https://pith.science/api/pith-number/HPPC4PZDBP6UB6FRTZOAHWKL4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPPC4PZDBP6UB6FRTZOAHWKL4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPPC4PZDBP6UB6FRTZOAHWKL4B/action/storage_attestation","attest_author":"https://pith.science/pith/HPPC4PZDBP6UB6FRTZOAHWKL4B/action/author_attestation","sign_citation":"https://pith.science/pith/HPPC4PZDBP6UB6FRTZOAHWKL4B/action/citation_signature","submit_replication":"https://pith.science/pith/HPPC4PZDBP6UB6FRTZOAHWKL4B/action/replication_record"}},"created_at":"2026-07-05T01:43:04.291372+00:00","updated_at":"2026-07-05T01:43:04.291372+00:00"}