{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6AOWMY3CMCWXWHTOSEMP3X7PWH","short_pith_number":"pith:6AOWMY3C","schema_version":"1.0","canonical_sha256":"f01d66636260ad7b1e6e9118fddfefb1c117366a168bd17b658104b7f2c8632d","source":{"kind":"arxiv","id":"2204.11827","version":1},"attestation_state":"computed","paper":{"title":"Task-Induced Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Anisha Gunjal, Joseph J. Lim, Jun Yamada, Karl Pertsch","submitted_at":"2022-04-25T17:57:10Z","abstract_excerpt":"In this work, we evaluate the effectiveness of representation learning approaches for decision making in visually complex environments. Representation learning is essential for effective reinforcement learning (RL) from high-dimensional inputs. Unsupervised representation learning approaches based on reconstruction, prediction or contrastive learning have shown substantial learning efficiency gains. Yet, they have mostly been evaluated in clean laboratory or simulated settings. In contrast, real environments are visually complex and contain substantial amounts of clutter and distractors. Unsup"},"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":"2204.11827","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-25T17:57:10Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"580e021719431b2fe2661bda9505fb12513f0cbd2ca8ed824a946fe88c52b7c3","abstract_canon_sha256":"a8c2e3214dbda8ed12152e571899907d4c2ad4b2cf0de3438b894ee547c70715"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:31.963187Z","signature_b64":"wwCkLsR0F5CikoHAmy463JWyYNktVPTVUS7ezhQjJregdcVmsfa7KM1uhnvUzYaAuQnANYaaOl/a6Ogq2GITAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f01d66636260ad7b1e6e9118fddfefb1c117366a168bd17b658104b7f2c8632d","last_reissued_at":"2026-07-05T04:17:31.962701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:31.962701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task-Induced Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Anisha Gunjal, Joseph J. Lim, Jun Yamada, Karl Pertsch","submitted_at":"2022-04-25T17:57:10Z","abstract_excerpt":"In this work, we evaluate the effectiveness of representation learning approaches for decision making in visually complex environments. Representation learning is essential for effective reinforcement learning (RL) from high-dimensional inputs. Unsupervised representation learning approaches based on reconstruction, prediction or contrastive learning have shown substantial learning efficiency gains. Yet, they have mostly been evaluated in clean laboratory or simulated settings. In contrast, real environments are visually complex and contain substantial amounts of clutter and distractors. Unsup"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.11827","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/2204.11827/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":"2204.11827","created_at":"2026-07-05T04:17:31.962759+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.11827v1","created_at":"2026-07-05T04:17:31.962759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.11827","created_at":"2026-07-05T04:17:31.962759+00:00"},{"alias_kind":"pith_short_12","alias_value":"6AOWMY3CMCWX","created_at":"2026-07-05T04:17:31.962759+00:00"},{"alias_kind":"pith_short_16","alias_value":"6AOWMY3CMCWXWHTO","created_at":"2026-07-05T04:17:31.962759+00:00"},{"alias_kind":"pith_short_8","alias_value":"6AOWMY3C","created_at":"2026-07-05T04:17:31.962759+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00379","citing_title":"Latent Action Learning Requires Supervision in the Presence of Distractors","ref_index":63,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6AOWMY3CMCWXWHTOSEMP3X7PWH","json":"https://pith.science/pith/6AOWMY3CMCWXWHTOSEMP3X7PWH.json","graph_json":"https://pith.science/api/pith-number/6AOWMY3CMCWXWHTOSEMP3X7PWH/graph.json","events_json":"https://pith.science/api/pith-number/6AOWMY3CMCWXWHTOSEMP3X7PWH/events.json","paper":"https://pith.science/paper/6AOWMY3C"},"agent_actions":{"view_html":"https://pith.science/pith/6AOWMY3CMCWXWHTOSEMP3X7PWH","download_json":"https://pith.science/pith/6AOWMY3CMCWXWHTOSEMP3X7PWH.json","view_paper":"https://pith.science/paper/6AOWMY3C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.11827&json=true","fetch_graph":"https://pith.science/api/pith-number/6AOWMY3CMCWXWHTOSEMP3X7PWH/graph.json","fetch_events":"https://pith.science/api/pith-number/6AOWMY3CMCWXWHTOSEMP3X7PWH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6AOWMY3CMCWXWHTOSEMP3X7PWH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6AOWMY3CMCWXWHTOSEMP3X7PWH/action/storage_attestation","attest_author":"https://pith.science/pith/6AOWMY3CMCWXWHTOSEMP3X7PWH/action/author_attestation","sign_citation":"https://pith.science/pith/6AOWMY3CMCWXWHTOSEMP3X7PWH/action/citation_signature","submit_replication":"https://pith.science/pith/6AOWMY3CMCWXWHTOSEMP3X7PWH/action/replication_record"}},"created_at":"2026-07-05T04:17:31.962759+00:00","updated_at":"2026-07-05T04:17:31.962759+00:00"}