{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:JP634J3B2JMSLU6HYACA46ZELA","short_pith_number":"pith:JP634J3B","canonical_record":{"source":{"id":"2211.16838","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-30T09:18:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8680aec6c5af34b0a3717a23d83bc2fa8dc2d2366300a735b01112694efc5cae","abstract_canon_sha256":"4b96aadc08b60dc4b80e92a667ff801cb08dcdd4c832f70b25291a94ac1b3038"},"schema_version":"1.0"},"canonical_sha256":"4bfdbe2761d25925d3c7c0040e7b24580af76f63e55e49aeea675caf0125d962","source":{"kind":"arxiv","id":"2211.16838","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.16838","created_at":"2026-07-05T05:21:12Z"},{"alias_kind":"arxiv_version","alias_value":"2211.16838v1","created_at":"2026-07-05T05:21:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.16838","created_at":"2026-07-05T05:21:12Z"},{"alias_kind":"pith_short_12","alias_value":"JP634J3B2JMS","created_at":"2026-07-05T05:21:12Z"},{"alias_kind":"pith_short_16","alias_value":"JP634J3B2JMSLU6H","created_at":"2026-07-05T05:21:12Z"},{"alias_kind":"pith_short_8","alias_value":"JP634J3B","created_at":"2026-07-05T05:21:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:JP634J3B2JMSLU6HYACA46ZELA","target":"record","payload":{"canonical_record":{"source":{"id":"2211.16838","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-30T09:18:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8680aec6c5af34b0a3717a23d83bc2fa8dc2d2366300a735b01112694efc5cae","abstract_canon_sha256":"4b96aadc08b60dc4b80e92a667ff801cb08dcdd4c832f70b25291a94ac1b3038"},"schema_version":"1.0"},"canonical_sha256":"4bfdbe2761d25925d3c7c0040e7b24580af76f63e55e49aeea675caf0125d962","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:12.013251Z","signature_b64":"55mP5fF8pa0Z0u53aXsopEbdwiB8dGvQmvJoPDmOJMXKGSJsyMUorcm8S/dRjL6OVguJaSnsfPUJcWUKjgqVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bfdbe2761d25925d3c7c0040e7b24580af76f63e55e49aeea675caf0125d962","last_reissued_at":"2026-07-05T05:21:12.012800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:12.012800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.16838","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:21:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lMCao66zAEswB9Cccdzt+sQcB/wGf0kI7TJxMkLd+uBZiaWsOPs/XhxisgWfqHfJFHXP+oOIyL1K90Znb//iDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T23:13:12.582369Z"},"content_sha256":"571301a47e32d2f40ee44279fc8f0bfd160e4462097dca6387b7596dee82b6ee","schema_version":"1.0","event_id":"sha256:571301a47e32d2f40ee44279fc8f0bfd160e4462097dca6387b7596dee82b6ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:JP634J3B2JMSLU6HYACA46ZELA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Improving Exploration in Self-Imitation Learning using Intrinsic Motivation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alain Andres, Esther Villar-Rodriguez, Javier Del Ser","submitted_at":"2022-11-30T09:18:59Z","abstract_excerpt":"Reinforcement Learning has emerged as a strong alternative to solve optimization tasks efficiently. The use of these algorithms highly depends on the feedback signals provided by the environment in charge of informing about how good (or bad) the decisions made by the learned agent are. Unfortunately, in a broad range of problems the design of a good reward function is not trivial, so in such cases sparse reward signals are instead adopted. The lack of a dense reward function poses new challenges, mostly related to exploration. Imitation Learning has addressed those problems by leveraging demon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.16838","kind":"arxiv","version":1},"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/2211.16838/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":"2026-07-05T05:21:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sYT5u4/JUAQX5JbhEKS7U6Q/qF0vqnQwfuxbb18Yt7SZkKCcplrZa6cM0hDu8KjqJgWFYMDTJEHDjE3z8a1wDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T23:13:12.582755Z"},"content_sha256":"88f25d248e68c82c5fd8e20413790c89040e49436644df3546980c9dbcdd04c3","schema_version":"1.0","event_id":"sha256:88f25d248e68c82c5fd8e20413790c89040e49436644df3546980c9dbcdd04c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JP634J3B2JMSLU6HYACA46ZELA/bundle.json","state_url":"https://pith.science/pith/JP634J3B2JMSLU6HYACA46ZELA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JP634J3B2JMSLU6HYACA46ZELA/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":"2026-07-21T23:13:12Z","links":{"resolver":"https://pith.science/pith/JP634J3B2JMSLU6HYACA46ZELA","bundle":"https://pith.science/pith/JP634J3B2JMSLU6HYACA46ZELA/bundle.json","state":"https://pith.science/pith/JP634J3B2JMSLU6HYACA46ZELA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JP634J3B2JMSLU6HYACA46ZELA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JP634J3B2JMSLU6HYACA46ZELA","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":"4b96aadc08b60dc4b80e92a667ff801cb08dcdd4c832f70b25291a94ac1b3038","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-30T09:18:59Z","title_canon_sha256":"8680aec6c5af34b0a3717a23d83bc2fa8dc2d2366300a735b01112694efc5cae"},"schema_version":"1.0","source":{"id":"2211.16838","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.16838","created_at":"2026-07-05T05:21:12Z"},{"alias_kind":"arxiv_version","alias_value":"2211.16838v1","created_at":"2026-07-05T05:21:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.16838","created_at":"2026-07-05T05:21:12Z"},{"alias_kind":"pith_short_12","alias_value":"JP634J3B2JMS","created_at":"2026-07-05T05:21:12Z"},{"alias_kind":"pith_short_16","alias_value":"JP634J3B2JMSLU6H","created_at":"2026-07-05T05:21:12Z"},{"alias_kind":"pith_short_8","alias_value":"JP634J3B","created_at":"2026-07-05T05:21:12Z"}],"graph_snapshots":[{"event_id":"sha256:88f25d248e68c82c5fd8e20413790c89040e49436644df3546980c9dbcdd04c3","target":"graph","created_at":"2026-07-05T05:21:12Z","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/2211.16838/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning has emerged as a strong alternative to solve optimization tasks efficiently. The use of these algorithms highly depends on the feedback signals provided by the environment in charge of informing about how good (or bad) the decisions made by the learned agent are. Unfortunately, in a broad range of problems the design of a good reward function is not trivial, so in such cases sparse reward signals are instead adopted. The lack of a dense reward function poses new challenges, mostly related to exploration. Imitation Learning has addressed those problems by leveraging demon","authors_text":"Alain Andres, Esther Villar-Rodriguez, Javier Del Ser","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-30T09:18:59Z","title":"Towards Improving Exploration in Self-Imitation Learning using Intrinsic Motivation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.16838","kind":"arxiv","version":1},"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":"sha256:571301a47e32d2f40ee44279fc8f0bfd160e4462097dca6387b7596dee82b6ee","target":"record","created_at":"2026-07-05T05:21:12Z","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":"4b96aadc08b60dc4b80e92a667ff801cb08dcdd4c832f70b25291a94ac1b3038","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-30T09:18:59Z","title_canon_sha256":"8680aec6c5af34b0a3717a23d83bc2fa8dc2d2366300a735b01112694efc5cae"},"schema_version":"1.0","source":{"id":"2211.16838","kind":"arxiv","version":1}},"canonical_sha256":"4bfdbe2761d25925d3c7c0040e7b24580af76f63e55e49aeea675caf0125d962","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bfdbe2761d25925d3c7c0040e7b24580af76f63e55e49aeea675caf0125d962","first_computed_at":"2026-07-05T05:21:12.012800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:21:12.012800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"55mP5fF8pa0Z0u53aXsopEbdwiB8dGvQmvJoPDmOJMXKGSJsyMUorcm8S/dRjL6OVguJaSnsfPUJcWUKjgqVBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:21:12.013251Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.16838","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:571301a47e32d2f40ee44279fc8f0bfd160e4462097dca6387b7596dee82b6ee","sha256:88f25d248e68c82c5fd8e20413790c89040e49436644df3546980c9dbcdd04c3"],"state_sha256":"c902baa048d1f86e16db8ec480c6db0b56ac97994df39d3552ceafb698f54c2e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gunZ/383S64Uf8O49WDl+5M+jzklyxCLdKHvn5/FGr+4CPvdG5qucAhl39QuJNCEUhdivY0YarLBk5Te/t5MBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T23:13:12.584969Z","bundle_sha256":"c75e51b5c15645308308d0266e71168282a9a562d78261dc500dee3dcf69f7c7"}}