{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:6EQMFI7X6E2EDNS23UTNNNN44F","short_pith_number":"pith:6EQMFI7X","canonical_record":{"source":{"id":"1812.00091","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-30T23:18:08Z","cross_cats_sorted":[],"title_canon_sha256":"060fbdf0dec70582bbf2d656c5c51ac9c075cfc7fe25e8959cfe9e51372ff3c4","abstract_canon_sha256":"15f334bb24ab4f86fb8140fd69898aacfd04b912aa8506b2ac92b26e51ce7411"},"schema_version":"1.0"},"canonical_sha256":"f120c2a3f7f13441b65add26d6b5bce15b2d594f476cfea11c141736205e8802","source":{"kind":"arxiv","id":"1812.00091","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.00091","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"arxiv_version","alias_value":"1812.00091v1","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00091","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"pith_short_12","alias_value":"6EQMFI7X6E2E","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6EQMFI7X6E2EDNS2","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6EQMFI7X","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:6EQMFI7X6E2EDNS23UTNNNN44F","target":"record","payload":{"canonical_record":{"source":{"id":"1812.00091","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-30T23:18:08Z","cross_cats_sorted":[],"title_canon_sha256":"060fbdf0dec70582bbf2d656c5c51ac9c075cfc7fe25e8959cfe9e51372ff3c4","abstract_canon_sha256":"15f334bb24ab4f86fb8140fd69898aacfd04b912aa8506b2ac92b26e51ce7411"},"schema_version":"1.0"},"canonical_sha256":"f120c2a3f7f13441b65add26d6b5bce15b2d594f476cfea11c141736205e8802","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:27.327260Z","signature_b64":"w71Oz+m1tHMrhTJKtKIKwmCKyP7f3MC34j6WrMx+EX+S8O3R3Jc8vHEbojZmxT35SEUjFCYuHZ9iroIxeiFiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f120c2a3f7f13441b65add26d6b5bce15b2d594f476cfea11c141736205e8802","last_reissued_at":"2026-05-17T23:59:27.326598Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:27.326598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.00091","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":"2026-05-17T23:59:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vMVtexB7xL80edyIYUo4LoLWe56fEr7LXL9fp1ht0gdUY1QQ6Q4unQlJo2/+i+Ded+cZvTHLbFUVB2ooHYEACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T18:13:45.418783Z"},"content_sha256":"883e9207ebb4d15728b5481da30f8ea97e677a734d8950c84a0f87a7fda464a6","schema_version":"1.0","event_id":"sha256:883e9207ebb4d15728b5481da30f8ea97e677a734d8950c84a0f87a7fda464a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:6EQMFI7X6E2EDNS23UTNNNN44F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BlockPuzzle - A Challenge in Physical Reasoning and Generalization for Robot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Yixiu Zhao, Ziyin Liu","submitted_at":"2018-11-30T23:18:08Z","abstract_excerpt":"In this work we propose a novel task framework under which a variety of physical reasoning puzzles can be constructed using very simple rules. Under sparse reward settings, most of these tasks can be very challenging for a reinforcement learning agent to learn. We build several simple environments with this task framework in Mujoco and OpenAI gym and attempt to solve them. We are able to solve the environments by designing curricula to guide the agent in learning and using imitation learning methods to transfer knowledge from a simpler environment. This is only a first step for the task framew"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00091","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":""},"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":"2026-05-17T23:59:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WKgMtsTZHYUo+pkWMtwf3GiuM3ZwhPNZK9ZZygTuO3i5u1KZ0B0UnsdVgFvRA0NPL1yjYQZxJcOXMx0M5KpeBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T18:13:45.419275Z"},"content_sha256":"7eaef593ad550b2b96e4b9b89e519d1a87f28f5f0dfc1ee00fe7bb463e6205df","schema_version":"1.0","event_id":"sha256:7eaef593ad550b2b96e4b9b89e519d1a87f28f5f0dfc1ee00fe7bb463e6205df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6EQMFI7X6E2EDNS23UTNNNN44F/bundle.json","state_url":"https://pith.science/pith/6EQMFI7X6E2EDNS23UTNNNN44F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6EQMFI7X6E2EDNS23UTNNNN44F/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":"2026-05-26T18:13:45Z","links":{"resolver":"https://pith.science/pith/6EQMFI7X6E2EDNS23UTNNNN44F","bundle":"https://pith.science/pith/6EQMFI7X6E2EDNS23UTNNNN44F/bundle.json","state":"https://pith.science/pith/6EQMFI7X6E2EDNS23UTNNNN44F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6EQMFI7X6E2EDNS23UTNNNN44F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:6EQMFI7X6E2EDNS23UTNNNN44F","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":"15f334bb24ab4f86fb8140fd69898aacfd04b912aa8506b2ac92b26e51ce7411","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-30T23:18:08Z","title_canon_sha256":"060fbdf0dec70582bbf2d656c5c51ac9c075cfc7fe25e8959cfe9e51372ff3c4"},"schema_version":"1.0","source":{"id":"1812.00091","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.00091","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"arxiv_version","alias_value":"1812.00091v1","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00091","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"pith_short_12","alias_value":"6EQMFI7X6E2E","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6EQMFI7X6E2EDNS2","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6EQMFI7X","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:7eaef593ad550b2b96e4b9b89e519d1a87f28f5f0dfc1ee00fe7bb463e6205df","target":"graph","created_at":"2026-05-17T23:59:27Z","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":"In this work we propose a novel task framework under which a variety of physical reasoning puzzles can be constructed using very simple rules. Under sparse reward settings, most of these tasks can be very challenging for a reinforcement learning agent to learn. We build several simple environments with this task framework in Mujoco and OpenAI gym and attempt to solve them. We are able to solve the environments by designing curricula to guide the agent in learning and using imitation learning methods to transfer knowledge from a simpler environment. This is only a first step for the task framew","authors_text":"Yixiu Zhao, Ziyin Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-30T23:18:08Z","title":"BlockPuzzle - A Challenge in Physical Reasoning and Generalization for Robot Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00091","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":"sha256:883e9207ebb4d15728b5481da30f8ea97e677a734d8950c84a0f87a7fda464a6","target":"record","created_at":"2026-05-17T23:59:27Z","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":"15f334bb24ab4f86fb8140fd69898aacfd04b912aa8506b2ac92b26e51ce7411","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-11-30T23:18:08Z","title_canon_sha256":"060fbdf0dec70582bbf2d656c5c51ac9c075cfc7fe25e8959cfe9e51372ff3c4"},"schema_version":"1.0","source":{"id":"1812.00091","kind":"arxiv","version":1}},"canonical_sha256":"f120c2a3f7f13441b65add26d6b5bce15b2d594f476cfea11c141736205e8802","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f120c2a3f7f13441b65add26d6b5bce15b2d594f476cfea11c141736205e8802","first_computed_at":"2026-05-17T23:59:27.326598Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:27.326598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w71Oz+m1tHMrhTJKtKIKwmCKyP7f3MC34j6WrMx+EX+S8O3R3Jc8vHEbojZmxT35SEUjFCYuHZ9iroIxeiFiAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:27.327260Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.00091","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:883e9207ebb4d15728b5481da30f8ea97e677a734d8950c84a0f87a7fda464a6","sha256:7eaef593ad550b2b96e4b9b89e519d1a87f28f5f0dfc1ee00fe7bb463e6205df"],"state_sha256":"a0d1d77956d577b5d4ecb1cd20c6170a50fa9f94fc32986a2fa0d83808e76e34"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6FshHm2KHCLz32czllCO3RR0x8NcZi64JMAwX0Did9KfM9qumbSdhrLCeohK7i6ydzUgyFLPr+KKPRu88SuqDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T18:13:45.422405Z","bundle_sha256":"0bf38e01b77ace3de9cec66222fc8001b255f217cd8ac5fae3ae4e4f9c87f5ba"}}