{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:I6P5V42EHFGJOOZXZPII7FFKH6","short_pith_number":"pith:I6P5V42E","schema_version":"1.0","canonical_sha256":"479fdaf344394c973b37cbd08f94aa3f8afb12f57d863e2a40d37252e46ea97e","source":{"kind":"arxiv","id":"2007.07356","version":2},"attestation_state":"computed","paper":{"title":"Efficient Empowerment Estimation for Unsupervised Stabilization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kevin Lu, Pieter Abbeel, Ruihan Zhao, Stas Tiomkin","submitted_at":"2020-07-14T21:10:16Z","abstract_excerpt":"Intrinsically motivated artificial agents learn advantageous behavior without externally-provided rewards. Previously, it was shown that maximizing mutual information between agent actuators and future states, known as the empowerment principle, enables unsupervised stabilization of dynamical systems at upright positions, which is a prototypical intrinsically motivated behavior for upright standing and walking. This follows from the coincidence between the objective of stabilization and the objective of empowerment. Unfortunately, sample-based estimation of this kind of mutual information is 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":"2007.07356","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-14T21:10:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c6082e83f9c4b51007550f5f5be4195c3a99f8704b48a92069f58230ac1162c2","abstract_canon_sha256":"cdb5604a585027475b0d6ce67aec0d59cbdc99b33b9d2c5cd565a8732f9eacb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:38:29.515827Z","signature_b64":"fqO2APbwOyM0kOEu3MiG4VF3zvLIKgssKIMtJdUzi8/fx7H7EjPuQoiLWZD+KxWa8Eu3yRxbaKT/E7GS3egGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"479fdaf344394c973b37cbd08f94aa3f8afb12f57d863e2a40d37252e46ea97e","last_reissued_at":"2026-07-05T02:38:29.515397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:38:29.515397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Empowerment Estimation for Unsupervised Stabilization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kevin Lu, Pieter Abbeel, Ruihan Zhao, Stas Tiomkin","submitted_at":"2020-07-14T21:10:16Z","abstract_excerpt":"Intrinsically motivated artificial agents learn advantageous behavior without externally-provided rewards. Previously, it was shown that maximizing mutual information between agent actuators and future states, known as the empowerment principle, enables unsupervised stabilization of dynamical systems at upright positions, which is a prototypical intrinsically motivated behavior for upright standing and walking. This follows from the coincidence between the objective of stabilization and the objective of empowerment. Unfortunately, sample-based estimation of this kind of mutual information is c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.07356","kind":"arxiv","version":2},"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/2007.07356/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":"2007.07356","created_at":"2026-07-05T02:38:29.515455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.07356v2","created_at":"2026-07-05T02:38:29.515455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.07356","created_at":"2026-07-05T02:38:29.515455+00:00"},{"alias_kind":"pith_short_12","alias_value":"I6P5V42EHFGJ","created_at":"2026-07-05T02:38:29.515455+00:00"},{"alias_kind":"pith_short_16","alias_value":"I6P5V42EHFGJOOZX","created_at":"2026-07-05T02:38:29.515455+00:00"},{"alias_kind":"pith_short_8","alias_value":"I6P5V42E","created_at":"2026-07-05T02:38:29.515455+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.11174","citing_title":"VIScore: Diagnosing Planning-Relevant Quality in Latent World Models","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I6P5V42EHFGJOOZXZPII7FFKH6","json":"https://pith.science/pith/I6P5V42EHFGJOOZXZPII7FFKH6.json","graph_json":"https://pith.science/api/pith-number/I6P5V42EHFGJOOZXZPII7FFKH6/graph.json","events_json":"https://pith.science/api/pith-number/I6P5V42EHFGJOOZXZPII7FFKH6/events.json","paper":"https://pith.science/paper/I6P5V42E"},"agent_actions":{"view_html":"https://pith.science/pith/I6P5V42EHFGJOOZXZPII7FFKH6","download_json":"https://pith.science/pith/I6P5V42EHFGJOOZXZPII7FFKH6.json","view_paper":"https://pith.science/paper/I6P5V42E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.07356&json=true","fetch_graph":"https://pith.science/api/pith-number/I6P5V42EHFGJOOZXZPII7FFKH6/graph.json","fetch_events":"https://pith.science/api/pith-number/I6P5V42EHFGJOOZXZPII7FFKH6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I6P5V42EHFGJOOZXZPII7FFKH6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I6P5V42EHFGJOOZXZPII7FFKH6/action/storage_attestation","attest_author":"https://pith.science/pith/I6P5V42EHFGJOOZXZPII7FFKH6/action/author_attestation","sign_citation":"https://pith.science/pith/I6P5V42EHFGJOOZXZPII7FFKH6/action/citation_signature","submit_replication":"https://pith.science/pith/I6P5V42EHFGJOOZXZPII7FFKH6/action/replication_record"}},"created_at":"2026-07-05T02:38:29.515455+00:00","updated_at":"2026-07-05T02:38:29.515455+00:00"}