{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OCGGTUUTGO3PEO3QLJ575HGZYK","short_pith_number":"pith:OCGGTUUT","canonical_record":{"source":{"id":"2407.20806","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-30T13:11:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ea39f4ac9ab221daf47e2883a3bf5286165068fd31be47d0ac50f9990015d280","abstract_canon_sha256":"e51763e1324c81ae009ffc4f4cd2e10a4519a5e3eb78e9981668e4a855712d35"},"schema_version":"1.0"},"canonical_sha256":"708c69d29333b6f23b705a7bfe9cd9c28ef8d7e65b0173207b778cf063246c5c","source":{"kind":"arxiv","id":"2407.20806","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.20806","created_at":"2026-07-05T08:50:18Z"},{"alias_kind":"arxiv_version","alias_value":"2407.20806v1","created_at":"2026-07-05T08:50:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20806","created_at":"2026-07-05T08:50:18Z"},{"alias_kind":"pith_short_12","alias_value":"OCGGTUUTGO3P","created_at":"2026-07-05T08:50:18Z"},{"alias_kind":"pith_short_16","alias_value":"OCGGTUUTGO3PEO3Q","created_at":"2026-07-05T08:50:18Z"},{"alias_kind":"pith_short_8","alias_value":"OCGGTUUT","created_at":"2026-07-05T08:50:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OCGGTUUTGO3PEO3QLJ575HGZYK","target":"record","payload":{"canonical_record":{"source":{"id":"2407.20806","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-30T13:11:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ea39f4ac9ab221daf47e2883a3bf5286165068fd31be47d0ac50f9990015d280","abstract_canon_sha256":"e51763e1324c81ae009ffc4f4cd2e10a4519a5e3eb78e9981668e4a855712d35"},"schema_version":"1.0"},"canonical_sha256":"708c69d29333b6f23b705a7bfe9cd9c28ef8d7e65b0173207b778cf063246c5c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:18.803918Z","signature_b64":"RLoWHxta3CYjQkxtsaop0z9cnWX51X2hr5NftAmkc+N/XU47sU+lTk1sWUwR+RE/bmk1ulKnesFOgUad+v7GBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"708c69d29333b6f23b705a7bfe9cd9c28ef8d7e65b0173207b778cf063246c5c","last_reissued_at":"2026-07-05T08:50:18.803478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:18.803478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.20806","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":"2026-07-05T08:50:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sl/aiEWfna91kn2aBbxMasATh2WXXxJvzeATHGl4j2j5KZM4wcCsEcxpajVi7ucTYFkzbgG9ZUHVbYwNohjYBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:03:10.662867Z"},"content_sha256":"993eb3a5ba67996f2e13f4da9d18b728766884ce8736a5ffe17dba4b7c2d35be","schema_version":"1.0","event_id":"sha256:993eb3a5ba67996f2e13f4da9d18b728766884ce8736a5ffe17dba4b7c2d35be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OCGGTUUTGO3PEO3QLJ575HGZYK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Byung-Jun Lee, Hosung Lee, Jihwan Lee, Sanha Hwang, Sejin Kim, Seungpil Lee, Sundong Kim","submitted_at":"2024-07-30T13:11:45Z","abstract_excerpt":"This paper introduces ARCLE, an environment designed to facilitate reinforcement learning research on the Abstraction and Reasoning Corpus (ARC). Addressing this inductive reasoning benchmark with reinforcement learning presents these challenges: a vast action space, a hard-to-reach goal, and a variety of tasks. We demonstrate that an agent with proximal policy optimization can learn individual tasks through ARCLE. The adoption of non-factorial policies and auxiliary losses led to performance enhancements, effectively mitigating issues associated with action spaces and goal attainment. Based o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20806","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/2407.20806/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":"2026-07-05T08:50:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GAawpH6taHf1ma09Xeo1l71v1Kzyj/Y4Hz+okhHdXQpEb3C/omcnHnv2VMGc4o0fFnm3/FAXvqzQAMjc3/tyDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:03:10.663638Z"},"content_sha256":"f246ff2181564a70fbd4883e29608298061d50b3b3d94c59f996f13daf803eff","schema_version":"1.0","event_id":"sha256:f246ff2181564a70fbd4883e29608298061d50b3b3d94c59f996f13daf803eff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OCGGTUUTGO3PEO3QLJ575HGZYK/bundle.json","state_url":"https://pith.science/pith/OCGGTUUTGO3PEO3QLJ575HGZYK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OCGGTUUTGO3PEO3QLJ575HGZYK/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":"2026-07-09T06:03:10Z","links":{"resolver":"https://pith.science/pith/OCGGTUUTGO3PEO3QLJ575HGZYK","bundle":"https://pith.science/pith/OCGGTUUTGO3PEO3QLJ575HGZYK/bundle.json","state":"https://pith.science/pith/OCGGTUUTGO3PEO3QLJ575HGZYK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OCGGTUUTGO3PEO3QLJ575HGZYK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OCGGTUUTGO3PEO3QLJ575HGZYK","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":"e51763e1324c81ae009ffc4f4cd2e10a4519a5e3eb78e9981668e4a855712d35","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-30T13:11:45Z","title_canon_sha256":"ea39f4ac9ab221daf47e2883a3bf5286165068fd31be47d0ac50f9990015d280"},"schema_version":"1.0","source":{"id":"2407.20806","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.20806","created_at":"2026-07-05T08:50:18Z"},{"alias_kind":"arxiv_version","alias_value":"2407.20806v1","created_at":"2026-07-05T08:50:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20806","created_at":"2026-07-05T08:50:18Z"},{"alias_kind":"pith_short_12","alias_value":"OCGGTUUTGO3P","created_at":"2026-07-05T08:50:18Z"},{"alias_kind":"pith_short_16","alias_value":"OCGGTUUTGO3PEO3Q","created_at":"2026-07-05T08:50:18Z"},{"alias_kind":"pith_short_8","alias_value":"OCGGTUUT","created_at":"2026-07-05T08:50:18Z"}],"graph_snapshots":[{"event_id":"sha256:f246ff2181564a70fbd4883e29608298061d50b3b3d94c59f996f13daf803eff","target":"graph","created_at":"2026-07-05T08:50:18Z","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/2407.20806/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces ARCLE, an environment designed to facilitate reinforcement learning research on the Abstraction and Reasoning Corpus (ARC). Addressing this inductive reasoning benchmark with reinforcement learning presents these challenges: a vast action space, a hard-to-reach goal, and a variety of tasks. We demonstrate that an agent with proximal policy optimization can learn individual tasks through ARCLE. The adoption of non-factorial policies and auxiliary losses led to performance enhancements, effectively mitigating issues associated with action spaces and goal attainment. Based o","authors_text":"Byung-Jun Lee, Hosung Lee, Jihwan Lee, Sanha Hwang, Sejin Kim, Seungpil Lee, Sundong Kim","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-30T13:11:45Z","title":"ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20806","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":"sha256:993eb3a5ba67996f2e13f4da9d18b728766884ce8736a5ffe17dba4b7c2d35be","target":"record","created_at":"2026-07-05T08:50:18Z","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":"e51763e1324c81ae009ffc4f4cd2e10a4519a5e3eb78e9981668e4a855712d35","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-30T13:11:45Z","title_canon_sha256":"ea39f4ac9ab221daf47e2883a3bf5286165068fd31be47d0ac50f9990015d280"},"schema_version":"1.0","source":{"id":"2407.20806","kind":"arxiv","version":1}},"canonical_sha256":"708c69d29333b6f23b705a7bfe9cd9c28ef8d7e65b0173207b778cf063246c5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"708c69d29333b6f23b705a7bfe9cd9c28ef8d7e65b0173207b778cf063246c5c","first_computed_at":"2026-07-05T08:50:18.803478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:18.803478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RLoWHxta3CYjQkxtsaop0z9cnWX51X2hr5NftAmkc+N/XU47sU+lTk1sWUwR+RE/bmk1ulKnesFOgUad+v7GBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:18.803918Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.20806","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:993eb3a5ba67996f2e13f4da9d18b728766884ce8736a5ffe17dba4b7c2d35be","sha256:f246ff2181564a70fbd4883e29608298061d50b3b3d94c59f996f13daf803eff"],"state_sha256":"9bbcf3d6bd2997c1fa6e1831cec8a3699f740d4c56c0d23a4b0c148266ec0ede"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wDRGf0cst0p+d27bT49ZaPj+dgrVEA9Jm8wiUrJbU9wG6nIap/Yfn0UfYCCEN3hSl1qXV1CNBndLmhg68lZUDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:03:10.667127Z","bundle_sha256":"9a090492eae14dbb35abcd72b65d2ae9ff6ce455970e8dfeb0ddf2cb05950ba2"}}