{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TKWQWETMCORB7FEAEZG32DEHPK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1411f5bfa69a6ee7b8a7ce4e103377097a89c81aa83687657614c09ace1d5455","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-05T19:00:14Z","title_canon_sha256":"2fc50b81343f70c1d67d44783177b6b5446820b88fda7a31bd35c6b10415bd2c"},"schema_version":"1.0","source":{"id":"1907.02998","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.02998","created_at":"2026-07-05T01:07:37Z"},{"alias_kind":"arxiv_version","alias_value":"1907.02998v2","created_at":"2026-07-05T01:07:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02998","created_at":"2026-07-05T01:07:37Z"},{"alias_kind":"pith_short_12","alias_value":"TKWQWETMCORB","created_at":"2026-07-05T01:07:37Z"},{"alias_kind":"pith_short_16","alias_value":"TKWQWETMCORB7FEA","created_at":"2026-07-05T01:07:37Z"},{"alias_kind":"pith_short_8","alias_value":"TKWQWETM","created_at":"2026-07-05T01:07:37Z"}],"graph_snapshots":[{"event_id":"sha256:f79a37179b347f155098111291a21bd60752a9563cd114ef78434bee498819e9","target":"graph","created_at":"2026-07-05T01:07:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1907.02998/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Doina Precup, Eric Crawford, Srinivas Venkattaramanujam, Thang Doan","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-05T19:00:14Z","title":"Self-supervised Learning of Distance Functions for Goal-Conditioned Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02998","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ff4c44f35a36e7cd817e32d87bebd1d555261b98aaf2d0a7938ed28edcc612b2","target":"record","created_at":"2026-07-05T01:07:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1411f5bfa69a6ee7b8a7ce4e103377097a89c81aa83687657614c09ace1d5455","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-05T19:00:14Z","title_canon_sha256":"2fc50b81343f70c1d67d44783177b6b5446820b88fda7a31bd35c6b10415bd2c"},"schema_version":"1.0","source":{"id":"1907.02998","kind":"arxiv","version":2}},"canonical_sha256":"9aad0b126c13a21f9480264dbd0c877a90c75cdef630d4a25cbf96eaa309f2c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9aad0b126c13a21f9480264dbd0c877a90c75cdef630d4a25cbf96eaa309f2c0","first_computed_at":"2026-07-05T01:07:37.397720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:07:37.397720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RYXb10me68qJBzfApj/qrxYRu0e3sViRGoG7EOjC5BPHMDXikZCasEEpTKXyghl1iT8dzyGa/t7ju+QqOLnnCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:07:37.398178Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.02998","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff4c44f35a36e7cd817e32d87bebd1d555261b98aaf2d0a7938ed28edcc612b2","sha256:f79a37179b347f155098111291a21bd60752a9563cd114ef78434bee498819e9"],"state_sha256":"a24477f4f165899253c13928e4278e8863e325d53251c6cc8b4179685708c973"}