{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:7WD5YASAN2ZBYF2KU22LHZ2WMB","short_pith_number":"pith:7WD5YASA","schema_version":"1.0","canonical_sha256":"fd87dc02406eb21c174aa6b4b3e756607e4f3e517c733a3a33ce83cdc75efda1","source":{"kind":"arxiv","id":"1608.02341","version":1},"attestation_state":"computed","paper":{"title":"Towards Representation Learning with Tractable Probabilistic Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonio Vergari, Floriana Esposito, Nicola Di Mauro","submitted_at":"2016-08-08T07:44:24Z","abstract_excerpt":"Probabilistic models learned as density estimators can be exploited in representation learning beside being toolboxes used to answer inference queries only. However, how to extract useful representations highly depends on the particular model involved. We argue that tractable inference, i.e. inference that can be computed in polynomial time, can enable general schemes to extract features from black box models. We plan to investigate how Tractable Probabilistic Models (TPMs) can be exploited to generate embeddings by random query evaluations. We devise two experimental designs to assess and com"},"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":"1608.02341","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2016-08-08T07:44:24Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e47c7cf422e6d89e1ac9d23cc9824ba3e7ed2f8c964d4b17fb9a32a777bc5830","abstract_canon_sha256":"1b8520071897228ad4b6e3c96fb81ab7511db1933638ccf8e51b12ada289b066"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:09:29.285012Z","signature_b64":"Ohz9p95eAL4oeAP2o6Q9pwAlAm8XOuE4sLtwihYODCa3RDow/kDyfWxChUjxO0+NcTjg9ePhDn5sYC7ZdKAABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd87dc02406eb21c174aa6b4b3e756607e4f3e517c733a3a33ce83cdc75efda1","last_reissued_at":"2026-05-18T01:09:29.284586Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:09:29.284586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Representation Learning with Tractable Probabilistic Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonio Vergari, Floriana Esposito, Nicola Di Mauro","submitted_at":"2016-08-08T07:44:24Z","abstract_excerpt":"Probabilistic models learned as density estimators can be exploited in representation learning beside being toolboxes used to answer inference queries only. However, how to extract useful representations highly depends on the particular model involved. We argue that tractable inference, i.e. inference that can be computed in polynomial time, can enable general schemes to extract features from black box models. We plan to investigate how Tractable Probabilistic Models (TPMs) can be exploited to generate embeddings by random query evaluations. We devise two experimental designs to assess and com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.02341","kind":"arxiv","version":1},"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":"1608.02341","created_at":"2026-05-18T01:09:29.284658+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.02341v1","created_at":"2026-05-18T01:09:29.284658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.02341","created_at":"2026-05-18T01:09:29.284658+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WD5YASAN2ZB","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WD5YASAN2ZBYF2K","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WD5YASA","created_at":"2026-05-18T12:30:04.600751+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/7WD5YASAN2ZBYF2KU22LHZ2WMB","json":"https://pith.science/pith/7WD5YASAN2ZBYF2KU22LHZ2WMB.json","graph_json":"https://pith.science/api/pith-number/7WD5YASAN2ZBYF2KU22LHZ2WMB/graph.json","events_json":"https://pith.science/api/pith-number/7WD5YASAN2ZBYF2KU22LHZ2WMB/events.json","paper":"https://pith.science/paper/7WD5YASA"},"agent_actions":{"view_html":"https://pith.science/pith/7WD5YASAN2ZBYF2KU22LHZ2WMB","download_json":"https://pith.science/pith/7WD5YASAN2ZBYF2KU22LHZ2WMB.json","view_paper":"https://pith.science/paper/7WD5YASA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.02341&json=true","fetch_graph":"https://pith.science/api/pith-number/7WD5YASAN2ZBYF2KU22LHZ2WMB/graph.json","fetch_events":"https://pith.science/api/pith-number/7WD5YASAN2ZBYF2KU22LHZ2WMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WD5YASAN2ZBYF2KU22LHZ2WMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WD5YASAN2ZBYF2KU22LHZ2WMB/action/storage_attestation","attest_author":"https://pith.science/pith/7WD5YASAN2ZBYF2KU22LHZ2WMB/action/author_attestation","sign_citation":"https://pith.science/pith/7WD5YASAN2ZBYF2KU22LHZ2WMB/action/citation_signature","submit_replication":"https://pith.science/pith/7WD5YASAN2ZBYF2KU22LHZ2WMB/action/replication_record"}},"created_at":"2026-05-18T01:09:29.284658+00:00","updated_at":"2026-05-18T01:09:29.284658+00:00"}