{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VM2ZOXYR4UZVHAL564XX2BXGUN","short_pith_number":"pith:VM2ZOXYR","canonical_record":{"source":{"id":"2411.19583","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T09:56:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3f8ca4157b8d9eeaadc4d384b558bb6adc15a0121d0f0abad6b1366417983d3f","abstract_canon_sha256":"d82a6657924bd39b4b7b4f367b19ed17654e0fd2a0c7e600618f163e7f1a0a7d"},"schema_version":"1.0"},"canonical_sha256":"ab35975f11e53353817df72f7d06e6a34a8b830dc89a2e92d66ef3714ede47c6","source":{"kind":"arxiv","id":"2411.19583","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19583","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19583v1","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19583","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"pith_short_12","alias_value":"VM2ZOXYR4UZV","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"pith_short_16","alias_value":"VM2ZOXYR4UZVHAL5","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"pith_short_8","alias_value":"VM2ZOXYR","created_at":"2026-07-05T09:42:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VM2ZOXYR4UZVHAL564XX2BXGUN","target":"record","payload":{"canonical_record":{"source":{"id":"2411.19583","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T09:56:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3f8ca4157b8d9eeaadc4d384b558bb6adc15a0121d0f0abad6b1366417983d3f","abstract_canon_sha256":"d82a6657924bd39b4b7b4f367b19ed17654e0fd2a0c7e600618f163e7f1a0a7d"},"schema_version":"1.0"},"canonical_sha256":"ab35975f11e53353817df72f7d06e6a34a8b830dc89a2e92d66ef3714ede47c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:04.794403Z","signature_b64":"DRMg/PifGrIsPN2Zx/n+hpIj9aacFyGUGh3ZeAqTXThxDLNTVczDdAKEIxym9TEWvk3QuKgw+8bjmVCeZ0NIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab35975f11e53353817df72f7d06e6a34a8b830dc89a2e92d66ef3714ede47c6","last_reissued_at":"2026-07-05T09:42:04.793929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:04.793929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.19583","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":"2026-07-05T09:42:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WIOeFacyvJ328L9g7KwP/MrmJcsXm3yq4sKOU2n0OO3Q+16svEp+zkp8pioH3m45urx1ZG0g4VBOkGbJXrkCDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:49:22.774731Z"},"content_sha256":"16d03d9fd6c2a82d3d7f32fbf316c923ca048acde0e245398f707a3a11bdd0e0","schema_version":"1.0","event_id":"sha256:16d03d9fd6c2a82d3d7f32fbf316c923ca048acde0e245398f707a3a11bdd0e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VM2ZOXYR4UZVHAL564XX2BXGUN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Solving Rubik's Cube Without Tricky Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Siyu Liang, Yicheng Lin","submitted_at":"2024-11-29T09:56:40Z","abstract_excerpt":"The Rubiks Cube, with its vast state space and sparse reward structure, presents a significant challenge for reinforcement learning (RL) due to the difficulty of reaching rewarded states. Previous research addressed this by propagating cost-to-go estimates from the solved state and incorporating search techniques. These approaches differ from human strategies that start from fully scrambled cubes, which can be tricky for solving a general sparse-reward problem. In this paper, we introduce a novel RL algorithm using policy gradient methods to solve the Rubiks Cube without relying on near solved"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19583","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/2411.19583/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":"2026-07-05T09:42:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3eYMazy4V7wCd6Ea8WX7hxxaF4E/tQZjsz5orsgxCOTPrkijOP0JUhMDvoqPTkkfMi0bzc+49xbyW0pqJLmCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:49:22.775506Z"},"content_sha256":"caf4273953a88c1f9c34b6df687ce6f356be4ca9d89c4cab7386e1494cb88aa1","schema_version":"1.0","event_id":"sha256:caf4273953a88c1f9c34b6df687ce6f356be4ca9d89c4cab7386e1494cb88aa1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VM2ZOXYR4UZVHAL564XX2BXGUN/bundle.json","state_url":"https://pith.science/pith/VM2ZOXYR4UZVHAL564XX2BXGUN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VM2ZOXYR4UZVHAL564XX2BXGUN/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":"2026-08-15T10:49:22Z","links":{"resolver":"https://pith.science/pith/VM2ZOXYR4UZVHAL564XX2BXGUN","bundle":"https://pith.science/pith/VM2ZOXYR4UZVHAL564XX2BXGUN/bundle.json","state":"https://pith.science/pith/VM2ZOXYR4UZVHAL564XX2BXGUN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VM2ZOXYR4UZVHAL564XX2BXGUN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VM2ZOXYR4UZVHAL564XX2BXGUN","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":"d82a6657924bd39b4b7b4f367b19ed17654e0fd2a0c7e600618f163e7f1a0a7d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T09:56:40Z","title_canon_sha256":"3f8ca4157b8d9eeaadc4d384b558bb6adc15a0121d0f0abad6b1366417983d3f"},"schema_version":"1.0","source":{"id":"2411.19583","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19583","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19583v1","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19583","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"pith_short_12","alias_value":"VM2ZOXYR4UZV","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"pith_short_16","alias_value":"VM2ZOXYR4UZVHAL5","created_at":"2026-07-05T09:42:04Z"},{"alias_kind":"pith_short_8","alias_value":"VM2ZOXYR","created_at":"2026-07-05T09:42:04Z"}],"graph_snapshots":[{"event_id":"sha256:caf4273953a88c1f9c34b6df687ce6f356be4ca9d89c4cab7386e1494cb88aa1","target":"graph","created_at":"2026-07-05T09:42:04Z","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/2411.19583/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Rubiks Cube, with its vast state space and sparse reward structure, presents a significant challenge for reinforcement learning (RL) due to the difficulty of reaching rewarded states. Previous research addressed this by propagating cost-to-go estimates from the solved state and incorporating search techniques. These approaches differ from human strategies that start from fully scrambled cubes, which can be tricky for solving a general sparse-reward problem. In this paper, we introduce a novel RL algorithm using policy gradient methods to solve the Rubiks Cube without relying on near solved","authors_text":"Siyu Liang, Yicheng Lin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T09:56:40Z","title":"Solving Rubik's Cube Without Tricky Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19583","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":"sha256:16d03d9fd6c2a82d3d7f32fbf316c923ca048acde0e245398f707a3a11bdd0e0","target":"record","created_at":"2026-07-05T09:42:04Z","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":"d82a6657924bd39b4b7b4f367b19ed17654e0fd2a0c7e600618f163e7f1a0a7d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-29T09:56:40Z","title_canon_sha256":"3f8ca4157b8d9eeaadc4d384b558bb6adc15a0121d0f0abad6b1366417983d3f"},"schema_version":"1.0","source":{"id":"2411.19583","kind":"arxiv","version":1}},"canonical_sha256":"ab35975f11e53353817df72f7d06e6a34a8b830dc89a2e92d66ef3714ede47c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab35975f11e53353817df72f7d06e6a34a8b830dc89a2e92d66ef3714ede47c6","first_computed_at":"2026-07-05T09:42:04.793929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:04.793929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DRMg/PifGrIsPN2Zx/n+hpIj9aacFyGUGh3ZeAqTXThxDLNTVczDdAKEIxym9TEWvk3QuKgw+8bjmVCeZ0NIAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:04.794403Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.19583","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16d03d9fd6c2a82d3d7f32fbf316c923ca048acde0e245398f707a3a11bdd0e0","sha256:caf4273953a88c1f9c34b6df687ce6f356be4ca9d89c4cab7386e1494cb88aa1"],"state_sha256":"1c2bf73121e2fa521b7cd8cb61b17cad4e4e9c7ed11e3041c709e9526dea019b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8K9y1uwrQAjLZp5YF4Y89Jfo3sQSI+kNki2Xl0X5IplTqCGQsTqrrIgVvZpnLA9S/qEeLOwHwGhzrVkgNFJnAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T10:49:22.779053Z","bundle_sha256":"81c50a72f3702f9d2d6bfcff4344a9fbe137a5f5e93d30dc2d364121db8eae4d"}}