{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:CKHJTZ3XHOTHFYBYAAV3YC4A5X","short_pith_number":"pith:CKHJTZ3X","canonical_record":{"source":{"id":"1606.07374","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-06-23T16:58:33Z","cross_cats_sorted":[],"title_canon_sha256":"7747ce6c768286cad056f0ecae19639e64a49e77adca117b39f5133feca1200d","abstract_canon_sha256":"16451f184f26c65ada39674d47b8b1a46977d12518d8a83cadae2ecea14bc045"},"schema_version":"1.0"},"canonical_sha256":"128e99e7773ba672e038002bbc0b80edf1a3302fe6514624f4a5ffac66f47628","source":{"kind":"arxiv","id":"1606.07374","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.07374","created_at":"2026-05-18T01:10:47Z"},{"alias_kind":"arxiv_version","alias_value":"1606.07374v2","created_at":"2026-05-18T01:10:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.07374","created_at":"2026-05-18T01:10:47Z"},{"alias_kind":"pith_short_12","alias_value":"CKHJTZ3XHOTH","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"CKHJTZ3XHOTHFYBY","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"CKHJTZ3X","created_at":"2026-05-18T12:30:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:CKHJTZ3XHOTHFYBYAAV3YC4A5X","target":"record","payload":{"canonical_record":{"source":{"id":"1606.07374","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-06-23T16:58:33Z","cross_cats_sorted":[],"title_canon_sha256":"7747ce6c768286cad056f0ecae19639e64a49e77adca117b39f5133feca1200d","abstract_canon_sha256":"16451f184f26c65ada39674d47b8b1a46977d12518d8a83cadae2ecea14bc045"},"schema_version":"1.0"},"canonical_sha256":"128e99e7773ba672e038002bbc0b80edf1a3302fe6514624f4a5ffac66f47628","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:47.135512Z","signature_b64":"X/ZNZGr+qX3jP2GrYwCtmazhtp/YlNwb5DxMFxQ2NmwM8eut135vIJh/Yylbit1oy3lnSem2dfE629sRAvh+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"128e99e7773ba672e038002bbc0b80edf1a3302fe6514624f4a5ffac66f47628","last_reissued_at":"2026-05-18T01:10:47.134900Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:47.134900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.07374","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":"2026-05-18T01:10:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R5yz0evcZlzlE5a4e6HBgBfjdaARXpkalHazpIZXdSjTzlv3oX0AiCWrZ2T378a2x/hEr0sCFmaafFeccavmDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T01:31:03.498851Z"},"content_sha256":"4748eb7425644bc925487dacbffde61d88473ce8a38de3af83a585e9c0a74504","schema_version":"1.0","event_id":"sha256:4748eb7425644bc925487dacbffde61d88473ce8a38de3af83a585e9c0a74504"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:CKHJTZ3XHOTHFYBYAAV3YC4A5X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Stage Temporal Difference Learning for 2048-like Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao-Chin Liang, Chia-Chuan Chang, Chu-Hsuan Hsueh, Han Chiang, I-Chen Wu, Kun-Hao Yeh","submitted_at":"2016-06-23T16:58:33Z","abstract_excerpt":"Szubert and Jaskowski successfully used temporal difference (TD) learning together with n-tuple networks for playing the game 2048. However, we observed a phenomenon that the programs based on TD learning still hardly reach large tiles. In this paper, we propose multi-stage TD (MS-TD) learning, a kind of hierarchical reinforcement learning method, to effectively improve the performance for the rates of reaching large tiles, which are good metrics to analyze the strength of 2048 programs. Our experiments showed significant improvements over the one without using MS-TD learning. Namely, using 3-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.07374","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":""},"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":"2026-05-18T01:10:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C+K7vcAP/6wdtsd5mLs/rbxqsRTDnmsXwG18NanazhHm/DKI1S8U+KgkYkUhqRyvtmSWiVYQNgWK5mGc7qOtDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T01:31:03.499554Z"},"content_sha256":"130115885901658052164f028fc6e796dd39c59c4b1ce806436452033f4ea72b","schema_version":"1.0","event_id":"sha256:130115885901658052164f028fc6e796dd39c59c4b1ce806436452033f4ea72b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CKHJTZ3XHOTHFYBYAAV3YC4A5X/bundle.json","state_url":"https://pith.science/pith/CKHJTZ3XHOTHFYBYAAV3YC4A5X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CKHJTZ3XHOTHFYBYAAV3YC4A5X/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":"2026-06-09T01:31:03Z","links":{"resolver":"https://pith.science/pith/CKHJTZ3XHOTHFYBYAAV3YC4A5X","bundle":"https://pith.science/pith/CKHJTZ3XHOTHFYBYAAV3YC4A5X/bundle.json","state":"https://pith.science/pith/CKHJTZ3XHOTHFYBYAAV3YC4A5X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CKHJTZ3XHOTHFYBYAAV3YC4A5X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:CKHJTZ3XHOTHFYBYAAV3YC4A5X","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":"16451f184f26c65ada39674d47b8b1a46977d12518d8a83cadae2ecea14bc045","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-06-23T16:58:33Z","title_canon_sha256":"7747ce6c768286cad056f0ecae19639e64a49e77adca117b39f5133feca1200d"},"schema_version":"1.0","source":{"id":"1606.07374","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.07374","created_at":"2026-05-18T01:10:47Z"},{"alias_kind":"arxiv_version","alias_value":"1606.07374v2","created_at":"2026-05-18T01:10:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.07374","created_at":"2026-05-18T01:10:47Z"},{"alias_kind":"pith_short_12","alias_value":"CKHJTZ3XHOTH","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"CKHJTZ3XHOTHFYBY","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"CKHJTZ3X","created_at":"2026-05-18T12:30:09Z"}],"graph_snapshots":[{"event_id":"sha256:130115885901658052164f028fc6e796dd39c59c4b1ce806436452033f4ea72b","target":"graph","created_at":"2026-05-18T01:10:47Z","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"},"paper":{"abstract_excerpt":"Szubert and Jaskowski successfully used temporal difference (TD) learning together with n-tuple networks for playing the game 2048. However, we observed a phenomenon that the programs based on TD learning still hardly reach large tiles. In this paper, we propose multi-stage TD (MS-TD) learning, a kind of hierarchical reinforcement learning method, to effectively improve the performance for the rates of reaching large tiles, which are good metrics to analyze the strength of 2048 programs. Our experiments showed significant improvements over the one without using MS-TD learning. Namely, using 3-","authors_text":"Chao-Chin Liang, Chia-Chuan Chang, Chu-Hsuan Hsueh, Han Chiang, I-Chen Wu, Kun-Hao Yeh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-06-23T16:58:33Z","title":"Multi-Stage Temporal Difference Learning for 2048-like Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.07374","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":"sha256:4748eb7425644bc925487dacbffde61d88473ce8a38de3af83a585e9c0a74504","target":"record","created_at":"2026-05-18T01:10:47Z","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":"16451f184f26c65ada39674d47b8b1a46977d12518d8a83cadae2ecea14bc045","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-06-23T16:58:33Z","title_canon_sha256":"7747ce6c768286cad056f0ecae19639e64a49e77adca117b39f5133feca1200d"},"schema_version":"1.0","source":{"id":"1606.07374","kind":"arxiv","version":2}},"canonical_sha256":"128e99e7773ba672e038002bbc0b80edf1a3302fe6514624f4a5ffac66f47628","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"128e99e7773ba672e038002bbc0b80edf1a3302fe6514624f4a5ffac66f47628","first_computed_at":"2026-05-18T01:10:47.134900Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:10:47.134900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X/ZNZGr+qX3jP2GrYwCtmazhtp/YlNwb5DxMFxQ2NmwM8eut135vIJh/Yylbit1oy3lnSem2dfE629sRAvh+BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:10:47.135512Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.07374","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4748eb7425644bc925487dacbffde61d88473ce8a38de3af83a585e9c0a74504","sha256:130115885901658052164f028fc6e796dd39c59c4b1ce806436452033f4ea72b"],"state_sha256":"da4cc2008a672fe0032988778248a1b79c5987471dce0745a581ad29349943d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KXYMZTlgtfk4QdBXEw006HiRp2DrZCSXcl9PPWmlekC7dHnIJ5de4KMB15vL4kq3ZX7SEXUjaKUt/mrsRPyPBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T01:31:03.504501Z","bundle_sha256":"da99cf3b51e97d1eefb48a7e2d653d3f3d23985f140b2330fcd204ed177ca17a"}}