{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OWK247ENSWT3G4UFVJN32RI2HB","short_pith_number":"pith:OWK247EN","canonical_record":{"source":{"id":"2411.01521","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-03T10:47:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"491405aca148e865a3ce3262ec1c41ef036a6db8a944edb97c340b1a5c191959","abstract_canon_sha256":"1380c5197b79c5056f7d8c066afa334a2096f98f6f7879018d85899501317009"},"schema_version":"1.0"},"canonical_sha256":"7595ae7c8d95a7b37285aa5bbd451a384553d1ce1ce584aad44e73b71dd64867","source":{"kind":"arxiv","id":"2411.01521","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01521","created_at":"2026-07-05T09:31:51Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01521v2","created_at":"2026-07-05T09:31:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01521","created_at":"2026-07-05T09:31:51Z"},{"alias_kind":"pith_short_12","alias_value":"OWK247ENSWT3","created_at":"2026-07-05T09:31:51Z"},{"alias_kind":"pith_short_16","alias_value":"OWK247ENSWT3G4UF","created_at":"2026-07-05T09:31:51Z"},{"alias_kind":"pith_short_8","alias_value":"OWK247EN","created_at":"2026-07-05T09:31:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OWK247ENSWT3G4UFVJN32RI2HB","target":"record","payload":{"canonical_record":{"source":{"id":"2411.01521","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-03T10:47:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"491405aca148e865a3ce3262ec1c41ef036a6db8a944edb97c340b1a5c191959","abstract_canon_sha256":"1380c5197b79c5056f7d8c066afa334a2096f98f6f7879018d85899501317009"},"schema_version":"1.0"},"canonical_sha256":"7595ae7c8d95a7b37285aa5bbd451a384553d1ce1ce584aad44e73b71dd64867","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:51.063889Z","signature_b64":"3jaLaMTA5F0rueXGoi69uRNB9BvDAK/12Ptr+4WHGDV7cZn9Kesj8eWvlqHjovBr7ignj1KViv+SnI6oKGRkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7595ae7c8d95a7b37285aa5bbd451a384553d1ce1ce584aad44e73b71dd64867","last_reissued_at":"2026-07-05T09:31:51.063364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:51.063364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.01521","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:31:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MZlQKAIIsxDANCbnYTOcTwEj6WeiUBV29ld2m/x0CEZ+pJ1qCZm593HFjfGk9kpQZ8JcbUIAFvJtgl8VcYyHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:23:07.565208Z"},"content_sha256":"8682f0be178c9d154efd1be58f8a3523bd67c51ad98ed50939fc6925e7644113","schema_version":"1.0","event_id":"sha256:8682f0be178c9d154efd1be58f8a3523bd67c51ad98ed50939fc6925e7644113"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OWK247ENSWT3G4UFVJN32RI2HB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diversity Progress for Goal Selection in Discriminability-Motivated RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Christian Guckelsberger, Erik M. Lintunen, Nadia M. Ady","submitted_at":"2024-11-03T10:47:39Z","abstract_excerpt":"Non-uniform goal selection has the potential to improve the reinforcement learning (RL) of skills over uniform-random selection. In this paper, we introduce a method for learning a goal-selection policy in intrinsically-motivated goal-conditioned RL: \"Diversity Progress\" (DP). The learner forms a curriculum based on observed improvement in discriminability over its set of goals. Our proposed method is applicable to the class of discriminability-motivated agents, where the intrinsic reward is computed as a function of the agent's certainty of following the true goal being pursued. This reward c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01521","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/2411.01521/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:31:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EkrVY3iTfgrldwmk6NdKxWqDO0vVdbL/XGBFsCh01GPtc4HTFyHsmaj3nfMQCNE0WuKCs9TUWYODW1DxSzqmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:23:07.565750Z"},"content_sha256":"65e1499d4565b1eb1f22d6620a987998aec8498365020ca682137687f8be83e4","schema_version":"1.0","event_id":"sha256:65e1499d4565b1eb1f22d6620a987998aec8498365020ca682137687f8be83e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OWK247ENSWT3G4UFVJN32RI2HB/bundle.json","state_url":"https://pith.science/pith/OWK247ENSWT3G4UFVJN32RI2HB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OWK247ENSWT3G4UFVJN32RI2HB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T06:23:07Z","links":{"resolver":"https://pith.science/pith/OWK247ENSWT3G4UFVJN32RI2HB","bundle":"https://pith.science/pith/OWK247ENSWT3G4UFVJN32RI2HB/bundle.json","state":"https://pith.science/pith/OWK247ENSWT3G4UFVJN32RI2HB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OWK247ENSWT3G4UFVJN32RI2HB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OWK247ENSWT3G4UFVJN32RI2HB","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":"1380c5197b79c5056f7d8c066afa334a2096f98f6f7879018d85899501317009","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-03T10:47:39Z","title_canon_sha256":"491405aca148e865a3ce3262ec1c41ef036a6db8a944edb97c340b1a5c191959"},"schema_version":"1.0","source":{"id":"2411.01521","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01521","created_at":"2026-07-05T09:31:51Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01521v2","created_at":"2026-07-05T09:31:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01521","created_at":"2026-07-05T09:31:51Z"},{"alias_kind":"pith_short_12","alias_value":"OWK247ENSWT3","created_at":"2026-07-05T09:31:51Z"},{"alias_kind":"pith_short_16","alias_value":"OWK247ENSWT3G4UF","created_at":"2026-07-05T09:31:51Z"},{"alias_kind":"pith_short_8","alias_value":"OWK247EN","created_at":"2026-07-05T09:31:51Z"}],"graph_snapshots":[{"event_id":"sha256:65e1499d4565b1eb1f22d6620a987998aec8498365020ca682137687f8be83e4","target":"graph","created_at":"2026-07-05T09:31:51Z","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/2411.01521/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Non-uniform goal selection has the potential to improve the reinforcement learning (RL) of skills over uniform-random selection. In this paper, we introduce a method for learning a goal-selection policy in intrinsically-motivated goal-conditioned RL: \"Diversity Progress\" (DP). The learner forms a curriculum based on observed improvement in discriminability over its set of goals. Our proposed method is applicable to the class of discriminability-motivated agents, where the intrinsic reward is computed as a function of the agent's certainty of following the true goal being pursued. This reward c","authors_text":"Christian Guckelsberger, Erik M. Lintunen, Nadia M. Ady","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-03T10:47:39Z","title":"Diversity Progress for Goal Selection in Discriminability-Motivated RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01521","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":"sha256:8682f0be178c9d154efd1be58f8a3523bd67c51ad98ed50939fc6925e7644113","target":"record","created_at":"2026-07-05T09:31:51Z","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":"1380c5197b79c5056f7d8c066afa334a2096f98f6f7879018d85899501317009","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-03T10:47:39Z","title_canon_sha256":"491405aca148e865a3ce3262ec1c41ef036a6db8a944edb97c340b1a5c191959"},"schema_version":"1.0","source":{"id":"2411.01521","kind":"arxiv","version":2}},"canonical_sha256":"7595ae7c8d95a7b37285aa5bbd451a384553d1ce1ce584aad44e73b71dd64867","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7595ae7c8d95a7b37285aa5bbd451a384553d1ce1ce584aad44e73b71dd64867","first_computed_at":"2026-07-05T09:31:51.063364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:51.063364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3jaLaMTA5F0rueXGoi69uRNB9BvDAK/12Ptr+4WHGDV7cZn9Kesj8eWvlqHjovBr7ignj1KViv+SnI6oKGRkCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:51.063889Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.01521","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8682f0be178c9d154efd1be58f8a3523bd67c51ad98ed50939fc6925e7644113","sha256:65e1499d4565b1eb1f22d6620a987998aec8498365020ca682137687f8be83e4"],"state_sha256":"17b84a26783be75629ef1d50f65233f1547ee9e88815975ed5e5bb7a6c702907"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xMk+eojPwkMpAMoVYv3wS8aZrlFGGqjYlWfW/98KWSualWwMxRiDEg/L95sfAV4S+HVgsOyVehC3MLnhJpPIAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:23:07.572684Z","bundle_sha256":"57f0a74856153c98df782e42827cbe200b5a57e121ed7d95d2b4cb801aef2cd1"}}