{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QX5SFY6LGXT5HULKGQESEMPIL5","short_pith_number":"pith:QX5SFY6L","schema_version":"1.0","canonical_sha256":"85fb22e3cb35e7d3d16a34092231e85f6ec4595259a3b418f9112f522af4dc68","source":{"kind":"arxiv","id":"2011.08909","version":2},"attestation_state":"computed","paper":{"title":"C-Learning: Learning to Achieve Goals via Recursive Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine","submitted_at":"2020-11-17T19:58:56Z","abstract_excerpt":"We study the problem of predicting and controlling the future state distribution of an autonomous agent. This problem, which can be viewed as a reframing of goal-conditioned reinforcement learning (RL), is centered around learning a conditional probability density function over future states. Instead of directly estimating this density function, we indirectly estimate this density function by training a classifier to predict whether an observation comes from the future. Via Bayes' rule, predictions from our classifier can be transformed into predictions over future states. Importantly, an off-"},"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":"2011.08909","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-17T19:58:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6c36f73f063ccae7282725492d04d31a3488d4fddb2fb2e9e4a5bf0f98919f96","abstract_canon_sha256":"3f5fb178f870d4a36005eca87b21536b0d97f0170b011cf4b2857034ed37be30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:22.590829Z","signature_b64":"WkPJ/iddthQoPKzzOxWBoekrNJNhiC8uIfc5VLdlyAdTudRQqA3PNt9zqEskF6M3X40d/FvAKnFLLLNzBNihDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85fb22e3cb35e7d3d16a34092231e85f6ec4595259a3b418f9112f522af4dc68","last_reissued_at":"2026-07-05T02:33:22.590359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:22.590359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"C-Learning: Learning to Achieve Goals via Recursive Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine","submitted_at":"2020-11-17T19:58:56Z","abstract_excerpt":"We study the problem of predicting and controlling the future state distribution of an autonomous agent. This problem, which can be viewed as a reframing of goal-conditioned reinforcement learning (RL), is centered around learning a conditional probability density function over future states. Instead of directly estimating this density function, we indirectly estimate this density function by training a classifier to predict whether an observation comes from the future. Via Bayes' rule, predictions from our classifier can be transformed into predictions over future states. Importantly, an off-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.08909","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/2011.08909/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":"2011.08909","created_at":"2026-07-05T02:33:22.590415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.08909v2","created_at":"2026-07-05T02:33:22.590415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.08909","created_at":"2026-07-05T02:33:22.590415+00:00"},{"alias_kind":"pith_short_12","alias_value":"QX5SFY6LGXT5","created_at":"2026-07-05T02:33:22.590415+00:00"},{"alias_kind":"pith_short_16","alias_value":"QX5SFY6LGXT5HULK","created_at":"2026-07-05T02:33:22.590415+00:00"},{"alias_kind":"pith_short_8","alias_value":"QX5SFY6L","created_at":"2026-07-05T02:33:22.590415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23551","citing_title":"Goal-Conditioned Agents that Learn Everything All at Once","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08902","citing_title":"Intention-Conditioned Flow Occupancy Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14350","citing_title":"Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling","ref_index":276,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QX5SFY6LGXT5HULKGQESEMPIL5","json":"https://pith.science/pith/QX5SFY6LGXT5HULKGQESEMPIL5.json","graph_json":"https://pith.science/api/pith-number/QX5SFY6LGXT5HULKGQESEMPIL5/graph.json","events_json":"https://pith.science/api/pith-number/QX5SFY6LGXT5HULKGQESEMPIL5/events.json","paper":"https://pith.science/paper/QX5SFY6L"},"agent_actions":{"view_html":"https://pith.science/pith/QX5SFY6LGXT5HULKGQESEMPIL5","download_json":"https://pith.science/pith/QX5SFY6LGXT5HULKGQESEMPIL5.json","view_paper":"https://pith.science/paper/QX5SFY6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.08909&json=true","fetch_graph":"https://pith.science/api/pith-number/QX5SFY6LGXT5HULKGQESEMPIL5/graph.json","fetch_events":"https://pith.science/api/pith-number/QX5SFY6LGXT5HULKGQESEMPIL5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QX5SFY6LGXT5HULKGQESEMPIL5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QX5SFY6LGXT5HULKGQESEMPIL5/action/storage_attestation","attest_author":"https://pith.science/pith/QX5SFY6LGXT5HULKGQESEMPIL5/action/author_attestation","sign_citation":"https://pith.science/pith/QX5SFY6LGXT5HULKGQESEMPIL5/action/citation_signature","submit_replication":"https://pith.science/pith/QX5SFY6LGXT5HULKGQESEMPIL5/action/replication_record"}},"created_at":"2026-07-05T02:33:22.590415+00:00","updated_at":"2026-07-05T02:33:22.590415+00:00"}