{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:4FHJ55MQETXOENZFNGCVAKVQPE","short_pith_number":"pith:4FHJ55MQ","canonical_record":{"source":{"id":"2107.14226","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-29T17:58:04Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5e14bfb13cab44b4980eca5602c2d25aa093e73b55c55ae5a8289d667f4e8567","abstract_canon_sha256":"181715ef5bfe096504358bf5a490b4d656563e2d9f276e7fc13f52f693fd17e9"},"schema_version":"1.0"},"canonical_sha256":"e14e9ef59024eee237256985502ab07925104241929fb0434817023d8601098e","source":{"kind":"arxiv","id":"2107.14226","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.14226","created_at":"2026-07-05T04:22:38Z"},{"alias_kind":"arxiv_version","alias_value":"2107.14226v6","created_at":"2026-07-05T04:22:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.14226","created_at":"2026-07-05T04:22:38Z"},{"alias_kind":"pith_short_12","alias_value":"4FHJ55MQETXO","created_at":"2026-07-05T04:22:38Z"},{"alias_kind":"pith_short_16","alias_value":"4FHJ55MQETXOENZF","created_at":"2026-07-05T04:22:38Z"},{"alias_kind":"pith_short_8","alias_value":"4FHJ55MQ","created_at":"2026-07-05T04:22:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:4FHJ55MQETXOENZFNGCVAKVQPE","target":"record","payload":{"canonical_record":{"source":{"id":"2107.14226","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-29T17:58:04Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5e14bfb13cab44b4980eca5602c2d25aa093e73b55c55ae5a8289d667f4e8567","abstract_canon_sha256":"181715ef5bfe096504358bf5a490b4d656563e2d9f276e7fc13f52f693fd17e9"},"schema_version":"1.0"},"canonical_sha256":"e14e9ef59024eee237256985502ab07925104241929fb0434817023d8601098e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:38.374003Z","signature_b64":"n807HgmTdOeJdS2VM1ehZSpvG6FOee7eYIVPkPiGqDtpGNWqkhOCt7dreAmMgizaSEryZKOr56XQmTfHACj7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e14e9ef59024eee237256985502ab07925104241929fb0434817023d8601098e","last_reissued_at":"2026-07-05T04:22:38.373517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:38.373517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.14226","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:22:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pyWdlLu0WXIWwYjYnsWIyJl7EME09iKrQrFHD/qY/QPeX0ajf/RiCElB2rj5HAeSYxhMMMSWcIeKsoJfUbz/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:31:25.758796Z"},"content_sha256":"53ffafb4bc9150684652aec8cf64513bde07f2bda9bc677b556d6c4b96c4eef9","schema_version":"1.0","event_id":"sha256:53ffafb4bc9150684652aec8cf64513bde07f2bda9bc677b556d6c4b96c4eef9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:4FHJ55MQETXOENZFNGCVAKVQPE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning more skills through optimistic exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Warde-Farley, DJ Strouse, Kate Baumli, Steven Hansen, Vlad Mnih","submitted_at":"2021-07-29T17:58:04Z","abstract_excerpt":"Unsupervised skill learning objectives (Gregor et al., 2016, Eysenbach et al., 2018) allow agents to learn rich repertoires of behavior in the absence of extrinsic rewards. They work by simultaneously training a policy to produce distinguishable latent-conditioned trajectories, and a discriminator to evaluate distinguishability by trying to infer latents from trajectories. The hope is for the agent to explore and master the environment by encouraging each skill (latent) to reliably reach different states. However, an inherent exploration problem lingers: when a novel state is actually encounte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.14226","kind":"arxiv","version":6},"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/2107.14226/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":"2026-07-05T04:22:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3jiTJ3b8Po6M6pkU6TagIHbGPbwKNrT3ZquT0qQ4b5iWVksOLhzSTOToqQMVbq2hlmej9v8GqnrfvIH7rfUpBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T09:31:25.760042Z"},"content_sha256":"7afcea604fc0a005290cf1521e7d1e5818bdeee0a1100218c7e1fd93b146ed0a","schema_version":"1.0","event_id":"sha256:7afcea604fc0a005290cf1521e7d1e5818bdeee0a1100218c7e1fd93b146ed0a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4FHJ55MQETXOENZFNGCVAKVQPE/bundle.json","state_url":"https://pith.science/pith/4FHJ55MQETXOENZFNGCVAKVQPE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4FHJ55MQETXOENZFNGCVAKVQPE/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":"2026-08-07T09:31:25Z","links":{"resolver":"https://pith.science/pith/4FHJ55MQETXOENZFNGCVAKVQPE","bundle":"https://pith.science/pith/4FHJ55MQETXOENZFNGCVAKVQPE/bundle.json","state":"https://pith.science/pith/4FHJ55MQETXOENZFNGCVAKVQPE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4FHJ55MQETXOENZFNGCVAKVQPE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4FHJ55MQETXOENZFNGCVAKVQPE","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":"181715ef5bfe096504358bf5a490b4d656563e2d9f276e7fc13f52f693fd17e9","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-29T17:58:04Z","title_canon_sha256":"5e14bfb13cab44b4980eca5602c2d25aa093e73b55c55ae5a8289d667f4e8567"},"schema_version":"1.0","source":{"id":"2107.14226","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.14226","created_at":"2026-07-05T04:22:38Z"},{"alias_kind":"arxiv_version","alias_value":"2107.14226v6","created_at":"2026-07-05T04:22:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.14226","created_at":"2026-07-05T04:22:38Z"},{"alias_kind":"pith_short_12","alias_value":"4FHJ55MQETXO","created_at":"2026-07-05T04:22:38Z"},{"alias_kind":"pith_short_16","alias_value":"4FHJ55MQETXOENZF","created_at":"2026-07-05T04:22:38Z"},{"alias_kind":"pith_short_8","alias_value":"4FHJ55MQ","created_at":"2026-07-05T04:22:38Z"}],"graph_snapshots":[{"event_id":"sha256:7afcea604fc0a005290cf1521e7d1e5818bdeee0a1100218c7e1fd93b146ed0a","target":"graph","created_at":"2026-07-05T04:22:38Z","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/2107.14226/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised skill learning objectives (Gregor et al., 2016, Eysenbach et al., 2018) allow agents to learn rich repertoires of behavior in the absence of extrinsic rewards. They work by simultaneously training a policy to produce distinguishable latent-conditioned trajectories, and a discriminator to evaluate distinguishability by trying to infer latents from trajectories. The hope is for the agent to explore and master the environment by encouraging each skill (latent) to reliably reach different states. However, an inherent exploration problem lingers: when a novel state is actually encounte","authors_text":"David Warde-Farley, DJ Strouse, Kate Baumli, Steven Hansen, Vlad Mnih","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-29T17:58:04Z","title":"Learning more skills through optimistic exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.14226","kind":"arxiv","version":6},"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":"sha256:53ffafb4bc9150684652aec8cf64513bde07f2bda9bc677b556d6c4b96c4eef9","target":"record","created_at":"2026-07-05T04:22:38Z","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":"181715ef5bfe096504358bf5a490b4d656563e2d9f276e7fc13f52f693fd17e9","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-29T17:58:04Z","title_canon_sha256":"5e14bfb13cab44b4980eca5602c2d25aa093e73b55c55ae5a8289d667f4e8567"},"schema_version":"1.0","source":{"id":"2107.14226","kind":"arxiv","version":6}},"canonical_sha256":"e14e9ef59024eee237256985502ab07925104241929fb0434817023d8601098e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e14e9ef59024eee237256985502ab07925104241929fb0434817023d8601098e","first_computed_at":"2026-07-05T04:22:38.373517Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:38.373517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n807HgmTdOeJdS2VM1ehZSpvG6FOee7eYIVPkPiGqDtpGNWqkhOCt7dreAmMgizaSEryZKOr56XQmTfHACj7BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:38.374003Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.14226","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53ffafb4bc9150684652aec8cf64513bde07f2bda9bc677b556d6c4b96c4eef9","sha256:7afcea604fc0a005290cf1521e7d1e5818bdeee0a1100218c7e1fd93b146ed0a"],"state_sha256":"d28442c08cf66554a12a759d34677b8541f1ca0bd47504c1964403f6e3ec7849"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mg3AdkLhV926DeUVZxKc5waxtmHVz0VEP4WqdhtFA10guge/zurHQN3MPS85usenVCnqAOi9wsUCRAvwaUzZCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T09:31:25.764569Z","bundle_sha256":"d966aca37cc85ddfa38ae6dd4ea52314d89d867271d2396ac54e29cc13cc933e"}}