{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:ZGEYL3EKFFA4LMRNPJ3HCQNAJI","short_pith_number":"pith:ZGEYL3EK","canonical_record":{"source":{"id":"1301.0567","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-12-12T15:56:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"85a62bd2bcad0e070f3721bbbed8d122f261ed01a95428a83f0129160a4c4a31","abstract_canon_sha256":"3fabf71c89ff21d66159baf932c94517b31a08e4ff1edd482ed2e26a3ec3821e"},"schema_version":"1.0"},"canonical_sha256":"c98985ec8a2941c5b22d7a767141a04a080eb0c3025b64932deeefe60bfc24e2","source":{"kind":"arxiv","id":"1301.0567","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.0567","created_at":"2026-05-18T03:37:18Z"},{"alias_kind":"arxiv_version","alias_value":"1301.0567v1","created_at":"2026-05-18T03:37:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.0567","created_at":"2026-05-18T03:37:18Z"},{"alias_kind":"pith_short_12","alias_value":"ZGEYL3EKFFA4","created_at":"2026-05-18T12:27:30Z"},{"alias_kind":"pith_short_16","alias_value":"ZGEYL3EKFFA4LMRN","created_at":"2026-05-18T12:27:30Z"},{"alias_kind":"pith_short_8","alias_value":"ZGEYL3EK","created_at":"2026-05-18T12:27:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:ZGEYL3EKFFA4LMRNPJ3HCQNAJI","target":"record","payload":{"canonical_record":{"source":{"id":"1301.0567","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-12-12T15:56:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"85a62bd2bcad0e070f3721bbbed8d122f261ed01a95428a83f0129160a4c4a31","abstract_canon_sha256":"3fabf71c89ff21d66159baf932c94517b31a08e4ff1edd482ed2e26a3ec3821e"},"schema_version":"1.0"},"canonical_sha256":"c98985ec8a2941c5b22d7a767141a04a080eb0c3025b64932deeefe60bfc24e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:37:18.492659Z","signature_b64":"WrsP56tEFEM7t7F7nvBQycxM5omDM8Vsn/auPYIpX2ubw8y4II195w8LSTGh4PU7BAXuEPuFlLYANR/AMb2aBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c98985ec8a2941c5b22d7a767141a04a080eb0c3025b64932deeefe60bfc24e2","last_reissued_at":"2026-05-18T03:37:18.492001Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:37:18.492001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1301.0567","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":"2026-05-18T03:37:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r8tvHCOp8korH+PQJP7gKFHOw1XMqpNFm9gLD3k14IIRkbs8IoQHfBnY73Tx3ddPDnDaDXtJtD12EYkwzR4hAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T16:58:15.992403Z"},"content_sha256":"3d336f641e3aff38191b77088cc07dd151702191ea48d8588ff03f1ac5fa5480","schema_version":"1.0","event_id":"sha256:3d336f641e3aff38191b77088cc07dd151702191ea48d8588ff03f1ac5fa5480"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:ZGEYL3EKFFA4LMRNPJ3HCQNAJI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Thing That We Tried Didn't Work Very Well : Deictic Representation in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Leslie Pack Kaelbling, Natalia Gardiol, Sarah Finney, Tim Oates","submitted_at":"2012-12-12T15:56:10Z","abstract_excerpt":"Most reinforcement learning methods operate on propositional representations of the world state.  Such representations are often intractably large and generalize poorly.  Using a deictic representation is believed to be a viable alternative: they promise generalization while allowing the use of existing reinforcement-learning methods.  Yet, there are few experiments on learning with deictic representations reported in the literature.  In this paper we explore the effectiveness of two forms of deictic representation and a na\\\"{i}ve propositional representation in a simple blocks-world domain.  "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.0567","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":"2026-05-18T03:37:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JBOeZ3hUVnk0psX06/ONPNFOlBquQR+ozVC7QR5nzus5i2N1AsFX5wEaeNXvl9f0wdFSSEqyK4/15synoXa+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T16:58:15.993061Z"},"content_sha256":"4f1e91fe11cca2b0205e44134f951402c0efc418c213f0524cb67494a180a6ad","schema_version":"1.0","event_id":"sha256:4f1e91fe11cca2b0205e44134f951402c0efc418c213f0524cb67494a180a6ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZGEYL3EKFFA4LMRNPJ3HCQNAJI/bundle.json","state_url":"https://pith.science/pith/ZGEYL3EKFFA4LMRNPJ3HCQNAJI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZGEYL3EKFFA4LMRNPJ3HCQNAJI/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":"2026-06-07T16:58:15Z","links":{"resolver":"https://pith.science/pith/ZGEYL3EKFFA4LMRNPJ3HCQNAJI","bundle":"https://pith.science/pith/ZGEYL3EKFFA4LMRNPJ3HCQNAJI/bundle.json","state":"https://pith.science/pith/ZGEYL3EKFFA4LMRNPJ3HCQNAJI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZGEYL3EKFFA4LMRNPJ3HCQNAJI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:ZGEYL3EKFFA4LMRNPJ3HCQNAJI","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":"3fabf71c89ff21d66159baf932c94517b31a08e4ff1edd482ed2e26a3ec3821e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-12-12T15:56:10Z","title_canon_sha256":"85a62bd2bcad0e070f3721bbbed8d122f261ed01a95428a83f0129160a4c4a31"},"schema_version":"1.0","source":{"id":"1301.0567","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.0567","created_at":"2026-05-18T03:37:18Z"},{"alias_kind":"arxiv_version","alias_value":"1301.0567v1","created_at":"2026-05-18T03:37:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.0567","created_at":"2026-05-18T03:37:18Z"},{"alias_kind":"pith_short_12","alias_value":"ZGEYL3EKFFA4","created_at":"2026-05-18T12:27:30Z"},{"alias_kind":"pith_short_16","alias_value":"ZGEYL3EKFFA4LMRN","created_at":"2026-05-18T12:27:30Z"},{"alias_kind":"pith_short_8","alias_value":"ZGEYL3EK","created_at":"2026-05-18T12:27:30Z"}],"graph_snapshots":[{"event_id":"sha256:4f1e91fe11cca2b0205e44134f951402c0efc418c213f0524cb67494a180a6ad","target":"graph","created_at":"2026-05-18T03:37:18Z","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"},"paper":{"abstract_excerpt":"Most reinforcement learning methods operate on propositional representations of the world state.  Such representations are often intractably large and generalize poorly.  Using a deictic representation is believed to be a viable alternative: they promise generalization while allowing the use of existing reinforcement-learning methods.  Yet, there are few experiments on learning with deictic representations reported in the literature.  In this paper we explore the effectiveness of two forms of deictic representation and a na\\\"{i}ve propositional representation in a simple blocks-world domain.  ","authors_text":"Leslie Pack Kaelbling, Natalia Gardiol, Sarah Finney, Tim Oates","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-12-12T15:56:10Z","title":"The Thing That We Tried Didn't Work Very Well : Deictic Representation in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.0567","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":"sha256:3d336f641e3aff38191b77088cc07dd151702191ea48d8588ff03f1ac5fa5480","target":"record","created_at":"2026-05-18T03:37:18Z","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":"3fabf71c89ff21d66159baf932c94517b31a08e4ff1edd482ed2e26a3ec3821e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-12-12T15:56:10Z","title_canon_sha256":"85a62bd2bcad0e070f3721bbbed8d122f261ed01a95428a83f0129160a4c4a31"},"schema_version":"1.0","source":{"id":"1301.0567","kind":"arxiv","version":1}},"canonical_sha256":"c98985ec8a2941c5b22d7a767141a04a080eb0c3025b64932deeefe60bfc24e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c98985ec8a2941c5b22d7a767141a04a080eb0c3025b64932deeefe60bfc24e2","first_computed_at":"2026-05-18T03:37:18.492001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:37:18.492001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WrsP56tEFEM7t7F7nvBQycxM5omDM8Vsn/auPYIpX2ubw8y4II195w8LSTGh4PU7BAXuEPuFlLYANR/AMb2aBA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:37:18.492659Z","signed_message":"canonical_sha256_bytes"},"source_id":"1301.0567","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d336f641e3aff38191b77088cc07dd151702191ea48d8588ff03f1ac5fa5480","sha256:4f1e91fe11cca2b0205e44134f951402c0efc418c213f0524cb67494a180a6ad"],"state_sha256":"8263632e68005f4b55c0572fd98f3cd315f1474ae8211b886a791c1bfd8b60da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wsKVkUASqrBAuY5z4PCWI2eH/6chSd2TiPyQrb9yQ486YwEkaafL87PV6UDKaKA4tUist0xmGS+SC+f117XKBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T16:58:15.996888Z","bundle_sha256":"04343126be6153fddc63bdd0c4d854b5c9ed3a25a8d9b0fbb54b6fe468f46c55"}}