{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7SSHINMZWGTMDRFE6YPQTK3QZM","short_pith_number":"pith:7SSHINMZ","schema_version":"1.0","canonical_sha256":"fca4743599b1a6c1c4a4f61f09ab70cb2af78bbda3429b4143e3dd312c9c8a28","source":{"kind":"arxiv","id":"2110.03498","version":1},"attestation_state":"computed","paper":{"title":"On the relationship between disentanglement and multi-task learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aleksandra Nowak, Andrzej Bedychaj, {\\L}ukasz Maziarka, Maciej Wo{\\l}czyk","submitted_at":"2021-10-07T14:35:34Z","abstract_excerpt":"One of the main arguments behind studying disentangled representations is the assumption that they can be easily reused in different tasks. At the same time finding a joint, adaptable representation of data is one of the key challenges in the multi-task learning setting. In this paper, we take a closer look at the relationship between disentanglement and multi-task learning based on hard parameter sharing. We perform a thorough empirical study of the representations obtained by neural networks trained on automatically generated supervised tasks. Using a set of standard metrics we show that dis"},"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":"2110.03498","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-07T14:35:34Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"97c64f214e5ac19ffac43ae876677c048f45cdb23389e55219fcf9a6fa2d09bb","abstract_canon_sha256":"2df81830d797e9409571f53696a9c3df1c27f8b3c498ee8250669b488bf87d7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:43.336361Z","signature_b64":"kTvDW5EqXyk/m09Ol7ybTN2UjNmnVISgOlNSUoYm8n60fulo174PKmi5Gpp7u8WttT6sjjxc4dFaASB4iJAxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fca4743599b1a6c1c4a4f61f09ab70cb2af78bbda3429b4143e3dd312c9c8a28","last_reissued_at":"2026-07-05T03:20:43.335941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:43.335941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the relationship between disentanglement and multi-task learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aleksandra Nowak, Andrzej Bedychaj, {\\L}ukasz Maziarka, Maciej Wo{\\l}czyk","submitted_at":"2021-10-07T14:35:34Z","abstract_excerpt":"One of the main arguments behind studying disentangled representations is the assumption that they can be easily reused in different tasks. At the same time finding a joint, adaptable representation of data is one of the key challenges in the multi-task learning setting. In this paper, we take a closer look at the relationship between disentanglement and multi-task learning based on hard parameter sharing. We perform a thorough empirical study of the representations obtained by neural networks trained on automatically generated supervised tasks. Using a set of standard metrics we show that dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03498","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.03498/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":"2110.03498","created_at":"2026-07-05T03:20:43.336002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03498v1","created_at":"2026-07-05T03:20:43.336002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03498","created_at":"2026-07-05T03:20:43.336002+00:00"},{"alias_kind":"pith_short_12","alias_value":"7SSHINMZWGTM","created_at":"2026-07-05T03:20:43.336002+00:00"},{"alias_kind":"pith_short_16","alias_value":"7SSHINMZWGTMDRFE","created_at":"2026-07-05T03:20:43.336002+00:00"},{"alias_kind":"pith_short_8","alias_value":"7SSHINMZ","created_at":"2026-07-05T03:20:43.336002+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/7SSHINMZWGTMDRFE6YPQTK3QZM","json":"https://pith.science/pith/7SSHINMZWGTMDRFE6YPQTK3QZM.json","graph_json":"https://pith.science/api/pith-number/7SSHINMZWGTMDRFE6YPQTK3QZM/graph.json","events_json":"https://pith.science/api/pith-number/7SSHINMZWGTMDRFE6YPQTK3QZM/events.json","paper":"https://pith.science/paper/7SSHINMZ"},"agent_actions":{"view_html":"https://pith.science/pith/7SSHINMZWGTMDRFE6YPQTK3QZM","download_json":"https://pith.science/pith/7SSHINMZWGTMDRFE6YPQTK3QZM.json","view_paper":"https://pith.science/paper/7SSHINMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03498&json=true","fetch_graph":"https://pith.science/api/pith-number/7SSHINMZWGTMDRFE6YPQTK3QZM/graph.json","fetch_events":"https://pith.science/api/pith-number/7SSHINMZWGTMDRFE6YPQTK3QZM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7SSHINMZWGTMDRFE6YPQTK3QZM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7SSHINMZWGTMDRFE6YPQTK3QZM/action/storage_attestation","attest_author":"https://pith.science/pith/7SSHINMZWGTMDRFE6YPQTK3QZM/action/author_attestation","sign_citation":"https://pith.science/pith/7SSHINMZWGTMDRFE6YPQTK3QZM/action/citation_signature","submit_replication":"https://pith.science/pith/7SSHINMZWGTMDRFE6YPQTK3QZM/action/replication_record"}},"created_at":"2026-07-05T03:20:43.336002+00:00","updated_at":"2026-07-05T03:20:43.336002+00:00"}