{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TKWQWETMCORB7FEAEZG32DEHPK","short_pith_number":"pith:TKWQWETM","schema_version":"1.0","canonical_sha256":"9aad0b126c13a21f9480264dbd0c877a90c75cdef630d4a25cbf96eaa309f2c0","source":{"kind":"arxiv","id":"1907.02998","version":2},"attestation_state":"computed","paper":{"title":"Self-supervised Learning of Distance Functions for Goal-Conditioned Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Eric Crawford, Srinivas Venkattaramanujam, Thang Doan","submitted_at":"2019-07-05T19:00:14Z","abstract_excerpt":"Goal-conditioned policies are used in order to break down complex reinforcement learning (RL) problems by using subgoals, which can be defined either in state space or in a latent feature space. This can increase the efficiency of learning by using a curriculum, and also enables simultaneous learning and generalization across goals. A crucial requirement of goal-conditioned policies is to be able to determine whether the goal has been achieved. Having a notion of distance to a goal is thus a crucial component of this approach. However, it is not straightforward to come up with an appropriate d"},"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":"1907.02998","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-05T19:00:14Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"2fc50b81343f70c1d67d44783177b6b5446820b88fda7a31bd35c6b10415bd2c","abstract_canon_sha256":"1411f5bfa69a6ee7b8a7ce4e103377097a89c81aa83687657614c09ace1d5455"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:37.398178Z","signature_b64":"RYXb10me68qJBzfApj/qrxYRu0e3sViRGoG7EOjC5BPHMDXikZCasEEpTKXyghl1iT8dzyGa/t7ju+QqOLnnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9aad0b126c13a21f9480264dbd0c877a90c75cdef630d4a25cbf96eaa309f2c0","last_reissued_at":"2026-07-05T01:07:37.397720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:37.397720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Learning of Distance Functions for Goal-Conditioned Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Eric Crawford, Srinivas Venkattaramanujam, Thang Doan","submitted_at":"2019-07-05T19:00:14Z","abstract_excerpt":"Goal-conditioned policies are used in order to break down complex reinforcement learning (RL) problems by using subgoals, which can be defined either in state space or in a latent feature space. This can increase the efficiency of learning by using a curriculum, and also enables simultaneous learning and generalization across goals. A crucial requirement of goal-conditioned policies is to be able to determine whether the goal has been achieved. Having a notion of distance to a goal is thus a crucial component of this approach. However, it is not straightforward to come up with an appropriate d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02998","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/1907.02998/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":"1907.02998","created_at":"2026-07-05T01:07:37.397797+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.02998v2","created_at":"2026-07-05T01:07:37.397797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02998","created_at":"2026-07-05T01:07:37.397797+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKWQWETMCORB","created_at":"2026-07-05T01:07:37.397797+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKWQWETMCORB7FEA","created_at":"2026-07-05T01:07:37.397797+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKWQWETM","created_at":"2026-07-05T01:07:37.397797+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/TKWQWETMCORB7FEAEZG32DEHPK","json":"https://pith.science/pith/TKWQWETMCORB7FEAEZG32DEHPK.json","graph_json":"https://pith.science/api/pith-number/TKWQWETMCORB7FEAEZG32DEHPK/graph.json","events_json":"https://pith.science/api/pith-number/TKWQWETMCORB7FEAEZG32DEHPK/events.json","paper":"https://pith.science/paper/TKWQWETM"},"agent_actions":{"view_html":"https://pith.science/pith/TKWQWETMCORB7FEAEZG32DEHPK","download_json":"https://pith.science/pith/TKWQWETMCORB7FEAEZG32DEHPK.json","view_paper":"https://pith.science/paper/TKWQWETM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.02998&json=true","fetch_graph":"https://pith.science/api/pith-number/TKWQWETMCORB7FEAEZG32DEHPK/graph.json","fetch_events":"https://pith.science/api/pith-number/TKWQWETMCORB7FEAEZG32DEHPK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKWQWETMCORB7FEAEZG32DEHPK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKWQWETMCORB7FEAEZG32DEHPK/action/storage_attestation","attest_author":"https://pith.science/pith/TKWQWETMCORB7FEAEZG32DEHPK/action/author_attestation","sign_citation":"https://pith.science/pith/TKWQWETMCORB7FEAEZG32DEHPK/action/citation_signature","submit_replication":"https://pith.science/pith/TKWQWETMCORB7FEAEZG32DEHPK/action/replication_record"}},"created_at":"2026-07-05T01:07:37.397797+00:00","updated_at":"2026-07-05T01:07:37.397797+00:00"}