{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:JQDAK6D6GOYDETWHFO3CW2B7OC","short_pith_number":"pith:JQDAK6D6","schema_version":"1.0","canonical_sha256":"4c0605787e33b0324ec72bb62b683f70bd10f43da12fb1fad89437afe7552a95","source":{"kind":"arxiv","id":"1611.02252","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical compositional feature learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dileep George, D. Scott Phoenix, Miguel L\\'azaro-Gredilla, Yi Liu","submitted_at":"2016-11-07T20:25:08Z","abstract_excerpt":"We introduce the hierarchical compositional network (HCN), a directed generative model able to discover and disentangle, without supervision, the building blocks of a set of binary images. The building blocks are binary features defined hierarchically as a composition of some of the features in the layer immediately below, arranged in a particular manner. At a high level, HCN is similar to a sigmoid belief network with pooling. Inference and learning in HCN are very challenging and existing variational approximations do not work satisfactorily. A main contribution of this work is to show that "},"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":"1611.02252","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-07T20:25:08Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4728fa554c8a6ccd7c8a6f24ba94adc0967b18f74760bd1860597fec3b0cda67","abstract_canon_sha256":"c8f87cfaf62ed3c88b580f75cfe0106507279a2132890e756c22e2f9d4cf6e90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:59.646202Z","signature_b64":"Hpy7ka2h13Bs6R5NR9YNfLqzT9MH/ottdAEeloCYWaKu7o7D846YM5FLwHn3kH80XSBT1vea7/89+AFIr1VXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c0605787e33b0324ec72bb62b683f70bd10f43da12fb1fad89437afe7552a95","last_reissued_at":"2026-05-18T00:31:59.645772Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:59.645772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical compositional feature learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dileep George, D. Scott Phoenix, Miguel L\\'azaro-Gredilla, Yi Liu","submitted_at":"2016-11-07T20:25:08Z","abstract_excerpt":"We introduce the hierarchical compositional network (HCN), a directed generative model able to discover and disentangle, without supervision, the building blocks of a set of binary images. The building blocks are binary features defined hierarchically as a composition of some of the features in the layer immediately below, arranged in a particular manner. At a high level, HCN is similar to a sigmoid belief network with pooling. Inference and learning in HCN are very challenging and existing variational approximations do not work satisfactorily. A main contribution of this work is to show that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.02252","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":""},"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":"1611.02252","created_at":"2026-05-18T00:31:59.645835+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.02252v2","created_at":"2026-05-18T00:31:59.645835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.02252","created_at":"2026-05-18T00:31:59.645835+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQDAK6D6GOYD","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQDAK6D6GOYDETWH","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQDAK6D6","created_at":"2026-05-18T12:30:25.849896+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/JQDAK6D6GOYDETWHFO3CW2B7OC","json":"https://pith.science/pith/JQDAK6D6GOYDETWHFO3CW2B7OC.json","graph_json":"https://pith.science/api/pith-number/JQDAK6D6GOYDETWHFO3CW2B7OC/graph.json","events_json":"https://pith.science/api/pith-number/JQDAK6D6GOYDETWHFO3CW2B7OC/events.json","paper":"https://pith.science/paper/JQDAK6D6"},"agent_actions":{"view_html":"https://pith.science/pith/JQDAK6D6GOYDETWHFO3CW2B7OC","download_json":"https://pith.science/pith/JQDAK6D6GOYDETWHFO3CW2B7OC.json","view_paper":"https://pith.science/paper/JQDAK6D6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.02252&json=true","fetch_graph":"https://pith.science/api/pith-number/JQDAK6D6GOYDETWHFO3CW2B7OC/graph.json","fetch_events":"https://pith.science/api/pith-number/JQDAK6D6GOYDETWHFO3CW2B7OC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQDAK6D6GOYDETWHFO3CW2B7OC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQDAK6D6GOYDETWHFO3CW2B7OC/action/storage_attestation","attest_author":"https://pith.science/pith/JQDAK6D6GOYDETWHFO3CW2B7OC/action/author_attestation","sign_citation":"https://pith.science/pith/JQDAK6D6GOYDETWHFO3CW2B7OC/action/citation_signature","submit_replication":"https://pith.science/pith/JQDAK6D6GOYDETWHFO3CW2B7OC/action/replication_record"}},"created_at":"2026-05-18T00:31:59.645835+00:00","updated_at":"2026-05-18T00:31:59.645835+00:00"}