{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:POLIBV4TFJAYINNGKT6S7ISKZQ","short_pith_number":"pith:POLIBV4T","schema_version":"1.0","canonical_sha256":"7b9680d7932a418435a654fd2fa24acc02ede0b027e84ca4f3e668d5e99d88a2","source":{"kind":"arxiv","id":"1911.10922","version":3},"attestation_state":"computed","paper":{"title":"Towards Better Understanding of Disentangled Representations via Mutual Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Junchi Yan, Wendong Bi, Xiaojiang Yang, Yitong Sun, Yu Cheng","submitted_at":"2019-11-25T13:56:53Z","abstract_excerpt":"Most existing works on disentangled representation learning are solely built upon an marginal independence assumption: all factors in disentangled representations should be statistically independent. This assumption is necessary but definitely not sufficient for the disentangled representations without additional inductive biases in the modeling process, which is shown theoretically in recent studies. We argue in this work that disentangled representations should be characterized by their relation with observable data. In particular, we formulate such a relation through the concept of mutual i"},"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":"1911.10922","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-25T13:56:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"00031c9c7097e5da08971640052c0f99e3048d1c913815118434dace9ca70f4c","abstract_canon_sha256":"cf3e7ab79861943e7597e8c2f0cfb77cc811ab66297b2fdf4c3e206098196b5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:15:23.495682Z","signature_b64":"zBJPTfAP0ZlFVo9eSf/GpOp8KhnWDVP14O4Ix7qaTawkCLbfhvHoRpBGT5g5n2BuXMUjBTzPMGip9MuzVEbLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b9680d7932a418435a654fd2fa24acc02ede0b027e84ca4f3e668d5e99d88a2","last_reissued_at":"2026-07-05T01:15:23.495174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:15:23.495174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Better Understanding of Disentangled Representations via Mutual Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Junchi Yan, Wendong Bi, Xiaojiang Yang, Yitong Sun, Yu Cheng","submitted_at":"2019-11-25T13:56:53Z","abstract_excerpt":"Most existing works on disentangled representation learning are solely built upon an marginal independence assumption: all factors in disentangled representations should be statistically independent. This assumption is necessary but definitely not sufficient for the disentangled representations without additional inductive biases in the modeling process, which is shown theoretically in recent studies. We argue in this work that disentangled representations should be characterized by their relation with observable data. In particular, we formulate such a relation through the concept of mutual i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.10922","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/1911.10922/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":"1911.10922","created_at":"2026-07-05T01:15:23.495235+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.10922v3","created_at":"2026-07-05T01:15:23.495235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.10922","created_at":"2026-07-05T01:15:23.495235+00:00"},{"alias_kind":"pith_short_12","alias_value":"POLIBV4TFJAY","created_at":"2026-07-05T01:15:23.495235+00:00"},{"alias_kind":"pith_short_16","alias_value":"POLIBV4TFJAYINNG","created_at":"2026-07-05T01:15:23.495235+00:00"},{"alias_kind":"pith_short_8","alias_value":"POLIBV4T","created_at":"2026-07-05T01:15:23.495235+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24684","citing_title":"Disentangling Granularity: An Implicit Inductive Bias in Factorized VAEs","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POLIBV4TFJAYINNGKT6S7ISKZQ","json":"https://pith.science/pith/POLIBV4TFJAYINNGKT6S7ISKZQ.json","graph_json":"https://pith.science/api/pith-number/POLIBV4TFJAYINNGKT6S7ISKZQ/graph.json","events_json":"https://pith.science/api/pith-number/POLIBV4TFJAYINNGKT6S7ISKZQ/events.json","paper":"https://pith.science/paper/POLIBV4T"},"agent_actions":{"view_html":"https://pith.science/pith/POLIBV4TFJAYINNGKT6S7ISKZQ","download_json":"https://pith.science/pith/POLIBV4TFJAYINNGKT6S7ISKZQ.json","view_paper":"https://pith.science/paper/POLIBV4T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.10922&json=true","fetch_graph":"https://pith.science/api/pith-number/POLIBV4TFJAYINNGKT6S7ISKZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/POLIBV4TFJAYINNGKT6S7ISKZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POLIBV4TFJAYINNGKT6S7ISKZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POLIBV4TFJAYINNGKT6S7ISKZQ/action/storage_attestation","attest_author":"https://pith.science/pith/POLIBV4TFJAYINNGKT6S7ISKZQ/action/author_attestation","sign_citation":"https://pith.science/pith/POLIBV4TFJAYINNGKT6S7ISKZQ/action/citation_signature","submit_replication":"https://pith.science/pith/POLIBV4TFJAYINNGKT6S7ISKZQ/action/replication_record"}},"created_at":"2026-07-05T01:15:23.495235+00:00","updated_at":"2026-07-05T01:15:23.495235+00:00"}