{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:S3BUVWRPOUC5CIEPQFBYJATVOX","short_pith_number":"pith:S3BUVWRP","canonical_record":{"source":{"id":"2112.05218","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2021-12-09T21:23:26Z","cross_cats_sorted":[],"title_canon_sha256":"a879e3b206fbb5030b785de8f5a918c458ed9b7e1a21507381dc3e98bc521b75","abstract_canon_sha256":"80022ecae749a2edaaff2316880ddb1edd8f26eff245e3db02dd8d8dc8d5f3b8"},"schema_version":"1.0"},"canonical_sha256":"96c34ada2f7505d1208f814384827575e16120fc35dff1ca4a9e73048ca12a1b","source":{"kind":"arxiv","id":"2112.05218","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.05218","created_at":"2026-07-05T03:39:38Z"},{"alias_kind":"arxiv_version","alias_value":"2112.05218v1","created_at":"2026-07-05T03:39:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05218","created_at":"2026-07-05T03:39:38Z"},{"alias_kind":"pith_short_12","alias_value":"S3BUVWRPOUC5","created_at":"2026-07-05T03:39:38Z"},{"alias_kind":"pith_short_16","alias_value":"S3BUVWRPOUC5CIEP","created_at":"2026-07-05T03:39:38Z"},{"alias_kind":"pith_short_8","alias_value":"S3BUVWRP","created_at":"2026-07-05T03:39:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:S3BUVWRPOUC5CIEPQFBYJATVOX","target":"record","payload":{"canonical_record":{"source":{"id":"2112.05218","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2021-12-09T21:23:26Z","cross_cats_sorted":[],"title_canon_sha256":"a879e3b206fbb5030b785de8f5a918c458ed9b7e1a21507381dc3e98bc521b75","abstract_canon_sha256":"80022ecae749a2edaaff2316880ddb1edd8f26eff245e3db02dd8d8dc8d5f3b8"},"schema_version":"1.0"},"canonical_sha256":"96c34ada2f7505d1208f814384827575e16120fc35dff1ca4a9e73048ca12a1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:38.061616Z","signature_b64":"mN5Hx+WII+nFJzzq9SccAxvE6w57EVV+E+97Xr0CUAm24+ZIVuDJ1rgLZr/Mxhtf/3RG4kG2xP/p9HbGAlMcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96c34ada2f7505d1208f814384827575e16120fc35dff1ca4a9e73048ca12a1b","last_reissued_at":"2026-07-05T03:39:38.061239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:38.061239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.05218","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":"2026-07-05T03:39:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OOMpi+c4LWy+tzN2Lm6Rsyr5EOnRHDrSdIx8sqXALh7FUgH6FsZTnCA4RNDZP0PzS0jGkJyTOMXUUSLjyEj1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T09:45:31.775944Z"},"content_sha256":"c4f014c6f5410a97f724b7e6956b058f90f05304459dda77f8a53d8bd56e09c5","schema_version":"1.0","event_id":"sha256:c4f014c6f5410a97f724b7e6956b058f90f05304459dda77f8a53d8bd56e09c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:S3BUVWRPOUC5CIEPQFBYJATVOX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Generalizable Behavior via Visual Rewrite Rules","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Michael Littman, Mingxuan Li, Shangqun Yu, Yiheng Xie","submitted_at":"2021-12-09T21:23:26Z","abstract_excerpt":"Though deep reinforcement learning agents have achieved unprecedented success in recent years, their learned policies can be brittle, failing to generalize to even slight modifications of their environments or unfamiliar situations. The black-box nature of the neural network learning dynamics makes it impossible to audit trained deep agents and recover from such failures. In this paper, we propose a novel representation and learning approach to capture environment dynamics without using neural networks. It originates from the observation that, in games designed for people, the effect of an act"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05218","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/2112.05218/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":"2026-07-05T03:39:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0zTTG9fRvEmLMyODeUrqIJK9i7+s69I33DIxd9UhpeghaduvLC1NwU6jY+GFi3Sw4FL/DWjdXybis6Jjq8UJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T09:45:31.776309Z"},"content_sha256":"e21d71f04c90e267f7fb80b5f53b22bb7558610d4ec1f144c74d06f1fac27a86","schema_version":"1.0","event_id":"sha256:e21d71f04c90e267f7fb80b5f53b22bb7558610d4ec1f144c74d06f1fac27a86"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S3BUVWRPOUC5CIEPQFBYJATVOX/bundle.json","state_url":"https://pith.science/pith/S3BUVWRPOUC5CIEPQFBYJATVOX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S3BUVWRPOUC5CIEPQFBYJATVOX/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":"2026-07-10T09:45:31Z","links":{"resolver":"https://pith.science/pith/S3BUVWRPOUC5CIEPQFBYJATVOX","bundle":"https://pith.science/pith/S3BUVWRPOUC5CIEPQFBYJATVOX/bundle.json","state":"https://pith.science/pith/S3BUVWRPOUC5CIEPQFBYJATVOX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S3BUVWRPOUC5CIEPQFBYJATVOX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:S3BUVWRPOUC5CIEPQFBYJATVOX","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":"80022ecae749a2edaaff2316880ddb1edd8f26eff245e3db02dd8d8dc8d5f3b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2021-12-09T21:23:26Z","title_canon_sha256":"a879e3b206fbb5030b785de8f5a918c458ed9b7e1a21507381dc3e98bc521b75"},"schema_version":"1.0","source":{"id":"2112.05218","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.05218","created_at":"2026-07-05T03:39:38Z"},{"alias_kind":"arxiv_version","alias_value":"2112.05218v1","created_at":"2026-07-05T03:39:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05218","created_at":"2026-07-05T03:39:38Z"},{"alias_kind":"pith_short_12","alias_value":"S3BUVWRPOUC5","created_at":"2026-07-05T03:39:38Z"},{"alias_kind":"pith_short_16","alias_value":"S3BUVWRPOUC5CIEP","created_at":"2026-07-05T03:39:38Z"},{"alias_kind":"pith_short_8","alias_value":"S3BUVWRP","created_at":"2026-07-05T03:39:38Z"}],"graph_snapshots":[{"event_id":"sha256:e21d71f04c90e267f7fb80b5f53b22bb7558610d4ec1f144c74d06f1fac27a86","target":"graph","created_at":"2026-07-05T03:39:38Z","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/2112.05218/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Though deep reinforcement learning agents have achieved unprecedented success in recent years, their learned policies can be brittle, failing to generalize to even slight modifications of their environments or unfamiliar situations. The black-box nature of the neural network learning dynamics makes it impossible to audit trained deep agents and recover from such failures. In this paper, we propose a novel representation and learning approach to capture environment dynamics without using neural networks. It originates from the observation that, in games designed for people, the effect of an act","authors_text":"Michael Littman, Mingxuan Li, Shangqun Yu, Yiheng Xie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2021-12-09T21:23:26Z","title":"Learning Generalizable Behavior via Visual Rewrite Rules"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05218","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:c4f014c6f5410a97f724b7e6956b058f90f05304459dda77f8a53d8bd56e09c5","target":"record","created_at":"2026-07-05T03:39:38Z","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":"80022ecae749a2edaaff2316880ddb1edd8f26eff245e3db02dd8d8dc8d5f3b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2021-12-09T21:23:26Z","title_canon_sha256":"a879e3b206fbb5030b785de8f5a918c458ed9b7e1a21507381dc3e98bc521b75"},"schema_version":"1.0","source":{"id":"2112.05218","kind":"arxiv","version":1}},"canonical_sha256":"96c34ada2f7505d1208f814384827575e16120fc35dff1ca4a9e73048ca12a1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96c34ada2f7505d1208f814384827575e16120fc35dff1ca4a9e73048ca12a1b","first_computed_at":"2026-07-05T03:39:38.061239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:39:38.061239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mN5Hx+WII+nFJzzq9SccAxvE6w57EVV+E+97Xr0CUAm24+ZIVuDJ1rgLZr/Mxhtf/3RG4kG2xP/p9HbGAlMcAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:39:38.061616Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.05218","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4f014c6f5410a97f724b7e6956b058f90f05304459dda77f8a53d8bd56e09c5","sha256:e21d71f04c90e267f7fb80b5f53b22bb7558610d4ec1f144c74d06f1fac27a86"],"state_sha256":"52a0382edbf0faf10fa62febfdac4ab6eafd903565bdfde36fd024b67bef489f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+un5Bm4frMfLfaLwV9Kt3a/p6QwphyjdskVHHtSPhk17r0118/sT4jz1iDrgbXcuq1BVV1IhvNBNuVs9HvWIAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T09:45:31.778174Z","bundle_sha256":"69bc981139e38c0918c7fbb508a776cfed3db31b0c07c1fe98e9049a8660abf4"}}