{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3VR5ZC3TF5TBE5QOWOIPJNVS5K","short_pith_number":"pith:3VR5ZC3T","schema_version":"1.0","canonical_sha256":"dd63dc8b732f6612760eb390f4b6b2eaa5e4142bf1edd92195e027b569b2f67f","source":{"kind":"arxiv","id":"2102.02153","version":1},"attestation_state":"computed","paper":{"title":"Fast Concept Mapping: The Emergence of Human Abilities in Artificial Neural Networks when Learning Embodied and Self-Supervised","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Gordon Pipa, Kai-Uwe K\\\"uhnberger, Peter K\\\"onig, Viviane Clay","submitted_at":"2021-02-03T17:19:49Z","abstract_excerpt":"Most artificial neural networks used for object detection and recognition are trained in a fully supervised setup. This is not only very resource consuming as it requires large data sets of labeled examples but also very different from how humans learn. We introduce a setup in which an artificial agent first learns in a simulated world through self-supervised exploration. Following this, the representations learned through interaction with the world can be used to associate semantic concepts such as different types of doors. To do this, we use a method we call fast concept mapping which uses c"},"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":"2102.02153","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-03T17:19:49Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"31943ad7532b72a1cd5acba09c9df529528bb899d91e9c5b344eee098e30638c","abstract_canon_sha256":"702c0c1ed4a86fca97c3414aae1b3bec239edd69ed08bc4a55bf1f9831c18aad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:12:37.393656Z","signature_b64":"vyyla0zvwihdyMmF3pWCBCX7rsK8LwdOuk70wBoU316a7rbEEsfUsHNKvLbe0Ld8zSlWBIBg2n3EvHCu33UnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd63dc8b732f6612760eb390f4b6b2eaa5e4142bf1edd92195e027b569b2f67f","last_reissued_at":"2026-07-05T02:12:37.393284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:12:37.393284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Concept Mapping: The Emergence of Human Abilities in Artificial Neural Networks when Learning Embodied and Self-Supervised","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Gordon Pipa, Kai-Uwe K\\\"uhnberger, Peter K\\\"onig, Viviane Clay","submitted_at":"2021-02-03T17:19:49Z","abstract_excerpt":"Most artificial neural networks used for object detection and recognition are trained in a fully supervised setup. This is not only very resource consuming as it requires large data sets of labeled examples but also very different from how humans learn. We introduce a setup in which an artificial agent first learns in a simulated world through self-supervised exploration. Following this, the representations learned through interaction with the world can be used to associate semantic concepts such as different types of doors. To do this, we use a method we call fast concept mapping which uses c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02153","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/2102.02153/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":"2102.02153","created_at":"2026-07-05T02:12:37.393356+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.02153v1","created_at":"2026-07-05T02:12:37.393356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02153","created_at":"2026-07-05T02:12:37.393356+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VR5ZC3TF5TB","created_at":"2026-07-05T02:12:37.393356+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VR5ZC3TF5TBE5QO","created_at":"2026-07-05T02:12:37.393356+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VR5ZC3T","created_at":"2026-07-05T02:12:37.393356+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/3VR5ZC3TF5TBE5QOWOIPJNVS5K","json":"https://pith.science/pith/3VR5ZC3TF5TBE5QOWOIPJNVS5K.json","graph_json":"https://pith.science/api/pith-number/3VR5ZC3TF5TBE5QOWOIPJNVS5K/graph.json","events_json":"https://pith.science/api/pith-number/3VR5ZC3TF5TBE5QOWOIPJNVS5K/events.json","paper":"https://pith.science/paper/3VR5ZC3T"},"agent_actions":{"view_html":"https://pith.science/pith/3VR5ZC3TF5TBE5QOWOIPJNVS5K","download_json":"https://pith.science/pith/3VR5ZC3TF5TBE5QOWOIPJNVS5K.json","view_paper":"https://pith.science/paper/3VR5ZC3T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.02153&json=true","fetch_graph":"https://pith.science/api/pith-number/3VR5ZC3TF5TBE5QOWOIPJNVS5K/graph.json","fetch_events":"https://pith.science/api/pith-number/3VR5ZC3TF5TBE5QOWOIPJNVS5K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VR5ZC3TF5TBE5QOWOIPJNVS5K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VR5ZC3TF5TBE5QOWOIPJNVS5K/action/storage_attestation","attest_author":"https://pith.science/pith/3VR5ZC3TF5TBE5QOWOIPJNVS5K/action/author_attestation","sign_citation":"https://pith.science/pith/3VR5ZC3TF5TBE5QOWOIPJNVS5K/action/citation_signature","submit_replication":"https://pith.science/pith/3VR5ZC3TF5TBE5QOWOIPJNVS5K/action/replication_record"}},"created_at":"2026-07-05T02:12:37.393356+00:00","updated_at":"2026-07-05T02:12:37.393356+00:00"}