{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TTUKWL2QZX3FQEIMPJADNMBK5T","short_pith_number":"pith:TTUKWL2Q","canonical_record":{"source":{"id":"2110.14457","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T14:22:19Z","cross_cats_sorted":[],"title_canon_sha256":"4b13cba0b3f60be1ad84fa0aa3baab9a243f5997a6779e83d8457f480424abc6","abstract_canon_sha256":"273cc0807ad034ca0c0bedaa09eeb5c0d88c8e648c377a2fb18ae97dc2ba00a3"},"schema_version":"1.0"},"canonical_sha256":"9ce8ab2f50cdf658110c7a4036b02aeccf7ecbca66cf443e59f659d970e14e07","source":{"kind":"arxiv","id":"2110.14457","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.14457","created_at":"2026-07-05T04:19:03Z"},{"alias_kind":"arxiv_version","alias_value":"2110.14457v2","created_at":"2026-07-05T04:19:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14457","created_at":"2026-07-05T04:19:03Z"},{"alias_kind":"pith_short_12","alias_value":"TTUKWL2QZX3F","created_at":"2026-07-05T04:19:03Z"},{"alias_kind":"pith_short_16","alias_value":"TTUKWL2QZX3FQEIM","created_at":"2026-07-05T04:19:03Z"},{"alias_kind":"pith_short_8","alias_value":"TTUKWL2Q","created_at":"2026-07-05T04:19:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TTUKWL2QZX3FQEIMPJADNMBK5T","target":"record","payload":{"canonical_record":{"source":{"id":"2110.14457","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T14:22:19Z","cross_cats_sorted":[],"title_canon_sha256":"4b13cba0b3f60be1ad84fa0aa3baab9a243f5997a6779e83d8457f480424abc6","abstract_canon_sha256":"273cc0807ad034ca0c0bedaa09eeb5c0d88c8e648c377a2fb18ae97dc2ba00a3"},"schema_version":"1.0"},"canonical_sha256":"9ce8ab2f50cdf658110c7a4036b02aeccf7ecbca66cf443e59f659d970e14e07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:03.669519Z","signature_b64":"LOMbEExrBAOEIt02Ca3LYQe5pGAskOCM0fuRiu+gGZh6ynhVx7Em3GcVjDccu/vrg32lF+i7pcWxtlNS1WE7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ce8ab2f50cdf658110c7a4036b02aeccf7ecbca66cf443e59f659d970e14e07","last_reissued_at":"2026-07-05T04:19:03.669017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:03.669017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.14457","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":"2026-07-05T04:19:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YwErLd4cDC6csEdlSgfSIMx6rKTHDWaaGytEDVOstzuNn3ubC0AyHBbuAWZ491crVYzGXgNGtRIUJIVbW2jHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:47:12.855832Z"},"content_sha256":"9e4c95e66b2d8be3f1553fbc467829e914db1e0124fb4c7459974d6eb911af6f","schema_version":"1.0","event_id":"sha256:9e4c95e66b2d8be3f1553fbc467829e914db1e0124fb4c7459974d6eb911af6f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TTUKWL2QZX3FQEIMPJADNMBK5T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, Jean Tarbouriech, Ludovic Denoyer, Pierre-Alexandre Kamienny, Sylvain Lamprier","submitted_at":"2021-10-27T14:22:19Z","abstract_excerpt":"Learning meaningful behaviors in the absence of reward is a difficult problem in reinforcement learning. A desirable and challenging unsupervised objective is to learn a set of diverse skills that provide a thorough coverage of the state space while being directed, i.e., reliably reaching distinct regions of the environment. In this paper, we build on the mutual information framework for skill discovery and introduce UPSIDE, which addresses the coverage-directedness trade-off in the following ways: 1) We design policies with a decoupled structure of a directed skill, trained to reach a specifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14457","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/2110.14457/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":"2026-07-05T04:19:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7WlkMD78PtwVyyOBR+iKY5wSBSZf+g1phlYAannLs1oNJVdpDpIJQR2tTHC5h83aLlf0cg1+W4PY/oXynge2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:47:12.856207Z"},"content_sha256":"8b58e3a302d1fe482e72a01a7b30b94826f4b64f1faa636a37b546de9a61fc66","schema_version":"1.0","event_id":"sha256:8b58e3a302d1fe482e72a01a7b30b94826f4b64f1faa636a37b546de9a61fc66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TTUKWL2QZX3FQEIMPJADNMBK5T/bundle.json","state_url":"https://pith.science/pith/TTUKWL2QZX3FQEIMPJADNMBK5T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TTUKWL2QZX3FQEIMPJADNMBK5T/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":"2026-07-07T08:47:12Z","links":{"resolver":"https://pith.science/pith/TTUKWL2QZX3FQEIMPJADNMBK5T","bundle":"https://pith.science/pith/TTUKWL2QZX3FQEIMPJADNMBK5T/bundle.json","state":"https://pith.science/pith/TTUKWL2QZX3FQEIMPJADNMBK5T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TTUKWL2QZX3FQEIMPJADNMBK5T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TTUKWL2QZX3FQEIMPJADNMBK5T","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":"273cc0807ad034ca0c0bedaa09eeb5c0d88c8e648c377a2fb18ae97dc2ba00a3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T14:22:19Z","title_canon_sha256":"4b13cba0b3f60be1ad84fa0aa3baab9a243f5997a6779e83d8457f480424abc6"},"schema_version":"1.0","source":{"id":"2110.14457","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.14457","created_at":"2026-07-05T04:19:03Z"},{"alias_kind":"arxiv_version","alias_value":"2110.14457v2","created_at":"2026-07-05T04:19:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14457","created_at":"2026-07-05T04:19:03Z"},{"alias_kind":"pith_short_12","alias_value":"TTUKWL2QZX3F","created_at":"2026-07-05T04:19:03Z"},{"alias_kind":"pith_short_16","alias_value":"TTUKWL2QZX3FQEIM","created_at":"2026-07-05T04:19:03Z"},{"alias_kind":"pith_short_8","alias_value":"TTUKWL2Q","created_at":"2026-07-05T04:19:03Z"}],"graph_snapshots":[{"event_id":"sha256:8b58e3a302d1fe482e72a01a7b30b94826f4b64f1faa636a37b546de9a61fc66","target":"graph","created_at":"2026-07-05T04:19:03Z","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/2110.14457/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning meaningful behaviors in the absence of reward is a difficult problem in reinforcement learning. A desirable and challenging unsupervised objective is to learn a set of diverse skills that provide a thorough coverage of the state space while being directed, i.e., reliably reaching distinct regions of the environment. In this paper, we build on the mutual information framework for skill discovery and introduce UPSIDE, which addresses the coverage-directedness trade-off in the following ways: 1) We design policies with a decoupled structure of a directed skill, trained to reach a specifi","authors_text":"Alessandro Lazaric, Jean Tarbouriech, Ludovic Denoyer, Pierre-Alexandre Kamienny, Sylvain Lamprier","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T14:22:19Z","title":"Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14457","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":"sha256:9e4c95e66b2d8be3f1553fbc467829e914db1e0124fb4c7459974d6eb911af6f","target":"record","created_at":"2026-07-05T04:19:03Z","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":"273cc0807ad034ca0c0bedaa09eeb5c0d88c8e648c377a2fb18ae97dc2ba00a3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T14:22:19Z","title_canon_sha256":"4b13cba0b3f60be1ad84fa0aa3baab9a243f5997a6779e83d8457f480424abc6"},"schema_version":"1.0","source":{"id":"2110.14457","kind":"arxiv","version":2}},"canonical_sha256":"9ce8ab2f50cdf658110c7a4036b02aeccf7ecbca66cf443e59f659d970e14e07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ce8ab2f50cdf658110c7a4036b02aeccf7ecbca66cf443e59f659d970e14e07","first_computed_at":"2026-07-05T04:19:03.669017Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:19:03.669017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LOMbEExrBAOEIt02Ca3LYQe5pGAskOCM0fuRiu+gGZh6ynhVx7Em3GcVjDccu/vrg32lF+i7pcWxtlNS1WE7DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:19:03.669519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.14457","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e4c95e66b2d8be3f1553fbc467829e914db1e0124fb4c7459974d6eb911af6f","sha256:8b58e3a302d1fe482e72a01a7b30b94826f4b64f1faa636a37b546de9a61fc66"],"state_sha256":"06182c1c9be5720754456d167b119717202a90824f97fbffbd802890a0d6091d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xxi8eF6X5INnNTxMbN1I63Z3x//BTQgYz1ACC6NL48R7oiq5Vi2T6S26MGxq8ScVBur0Wn8lKQ6oEBkZqhlgDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:47:12.858095Z","bundle_sha256":"ee8482f9bed219f786220ea0ebd89f1c0560598f36e56e9a0bf24c49bceaf463"}}