{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R4SXHZLS5SIAQM2WI24WOBJUOS","short_pith_number":"pith:R4SXHZLS","schema_version":"1.0","canonical_sha256":"8f2573e572ec9008335646b967053474a913122b314587adab6709d980a44020","source":{"kind":"arxiv","id":"2305.01521","version":1},"attestation_state":"computed","paper":{"title":"Unlocking the Power of Representations in Long-term Novelty-based Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alaa Saade, Bilal Piot, Charles Blundell, Daniele Calandriello, Leopoldo Sarra, Michal Valko, Oliver Groth, Pablo Sprechmann, Steven Kapturowski","submitted_at":"2023-05-02T15:29:40Z","abstract_excerpt":"We introduce Robust Exploration via Clustering-based Online Density Estimation (RECODE), a non-parametric method for novelty-based exploration that estimates visitation counts for clusters of states based on their similarity in a chosen embedding space. By adapting classical clustering to the nonstationary setting of Deep RL, RECODE can efficiently track state visitation counts over thousands of episodes. We further propose a novel generalization of the inverse dynamics loss, which leverages masked transformer architectures for multi-step prediction; which in conjunction with RECODE achieves a"},"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":"2305.01521","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-02T15:29:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"91bf4ae934b44cf5caa9c2d1f7b7ba4be40c97c2e3929b8d37efa9e16cba3950","abstract_canon_sha256":"24a04cf5d91d98c5c2885806d53a5aa14e35638524dc08d2cb9af46edf0bb62d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:26.660859Z","signature_b64":"QE8Xn/eab1pBWmQlGJlQviJwYMa5KfeM//MwwSJCFbHpyj3ARVdQfiHnt5X0Yt+zzeNuVgHxU/qmqDM401bFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f2573e572ec9008335646b967053474a913122b314587adab6709d980a44020","last_reissued_at":"2026-07-05T06:06:26.660432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:26.660432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlocking the Power of Representations in Long-term Novelty-based Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alaa Saade, Bilal Piot, Charles Blundell, Daniele Calandriello, Leopoldo Sarra, Michal Valko, Oliver Groth, Pablo Sprechmann, Steven Kapturowski","submitted_at":"2023-05-02T15:29:40Z","abstract_excerpt":"We introduce Robust Exploration via Clustering-based Online Density Estimation (RECODE), a non-parametric method for novelty-based exploration that estimates visitation counts for clusters of states based on their similarity in a chosen embedding space. By adapting classical clustering to the nonstationary setting of Deep RL, RECODE can efficiently track state visitation counts over thousands of episodes. We further propose a novel generalization of the inverse dynamics loss, which leverages masked transformer architectures for multi-step prediction; which in conjunction with RECODE achieves a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01521","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/2305.01521/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":"2305.01521","created_at":"2026-07-05T06:06:26.660505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.01521v1","created_at":"2026-07-05T06:06:26.660505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01521","created_at":"2026-07-05T06:06:26.660505+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4SXHZLS5SIA","created_at":"2026-07-05T06:06:26.660505+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4SXHZLS5SIAQM2W","created_at":"2026-07-05T06:06:26.660505+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4SXHZLS","created_at":"2026-07-05T06:06:26.660505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06272","citing_title":"Your GFlowNet Secretly Learns an Optimal Transport Plan","ref_index":93,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4SXHZLS5SIAQM2WI24WOBJUOS","json":"https://pith.science/pith/R4SXHZLS5SIAQM2WI24WOBJUOS.json","graph_json":"https://pith.science/api/pith-number/R4SXHZLS5SIAQM2WI24WOBJUOS/graph.json","events_json":"https://pith.science/api/pith-number/R4SXHZLS5SIAQM2WI24WOBJUOS/events.json","paper":"https://pith.science/paper/R4SXHZLS"},"agent_actions":{"view_html":"https://pith.science/pith/R4SXHZLS5SIAQM2WI24WOBJUOS","download_json":"https://pith.science/pith/R4SXHZLS5SIAQM2WI24WOBJUOS.json","view_paper":"https://pith.science/paper/R4SXHZLS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.01521&json=true","fetch_graph":"https://pith.science/api/pith-number/R4SXHZLS5SIAQM2WI24WOBJUOS/graph.json","fetch_events":"https://pith.science/api/pith-number/R4SXHZLS5SIAQM2WI24WOBJUOS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4SXHZLS5SIAQM2WI24WOBJUOS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4SXHZLS5SIAQM2WI24WOBJUOS/action/storage_attestation","attest_author":"https://pith.science/pith/R4SXHZLS5SIAQM2WI24WOBJUOS/action/author_attestation","sign_citation":"https://pith.science/pith/R4SXHZLS5SIAQM2WI24WOBJUOS/action/citation_signature","submit_replication":"https://pith.science/pith/R4SXHZLS5SIAQM2WI24WOBJUOS/action/replication_record"}},"created_at":"2026-07-05T06:06:26.660505+00:00","updated_at":"2026-07-05T06:06:26.660505+00:00"}