{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:3BS3URIWTSHW3GWQKX2SGXXG3D","short_pith_number":"pith:3BS3URIW","canonical_record":{"source":{"id":"1601.01297","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-01-06T20:22:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cd5809ab09f71f6495bb5c8a3b4692ba82f5d2eb151733a24468c8335c77d294","abstract_canon_sha256":"e02971d5f83a2f1c087d12aac0ad3d66f0bed3aeff340f8a9811c785c6363f98"},"schema_version":"1.0"},"canonical_sha256":"d865ba45169c8f6d9ad055f5235ee6d8fca5a307addf4f94652177ae4f144666","source":{"kind":"arxiv","id":"1601.01297","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1601.01297","created_at":"2026-05-18T01:23:15Z"},{"alias_kind":"arxiv_version","alias_value":"1601.01297v2","created_at":"2026-05-18T01:23:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.01297","created_at":"2026-05-18T01:23:15Z"},{"alias_kind":"pith_short_12","alias_value":"3BS3URIWTSHW","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"3BS3URIWTSHW3GWQ","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"3BS3URIW","created_at":"2026-05-18T12:29:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:3BS3URIWTSHW3GWQKX2SGXXG3D","target":"record","payload":{"canonical_record":{"source":{"id":"1601.01297","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-01-06T20:22:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cd5809ab09f71f6495bb5c8a3b4692ba82f5d2eb151733a24468c8335c77d294","abstract_canon_sha256":"e02971d5f83a2f1c087d12aac0ad3d66f0bed3aeff340f8a9811c785c6363f98"},"schema_version":"1.0"},"canonical_sha256":"d865ba45169c8f6d9ad055f5235ee6d8fca5a307addf4f94652177ae4f144666","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:23:15.735703Z","signature_b64":"PqPkAYCWR34jHi6DomLeI1BGKIx2ARqBM3DoEzXF+mzBSbGDBWPTionm5/iXQWZgAXe47b9fZXZcxuI4DN2hAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d865ba45169c8f6d9ad055f5235ee6d8fca5a307addf4f94652177ae4f144666","last_reissued_at":"2026-05-18T01:23:15.735083Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:23:15.735083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1601.01297","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":"2026-05-18T01:23:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+Tvcla/4Pgm9kZN43IKvDZBbxMtcwQ1AdFW3+O4LQE+YnRDPVx+ZgqSVHsleX57Sg0dY4IHH5XuxW/lHTDE6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T08:49:08.408960Z"},"content_sha256":"95674ea13359a78a094902be1af186a1ab4168c89e6349207c6eeeb44061570e","schema_version":"1.0","event_id":"sha256:95674ea13359a78a094902be1af186a1ab4168c89e6349207c6eeeb44061570e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:3BS3URIWTSHW3GWQKX2SGXXG3D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Angrier Birds: Bayesian reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bernardo Ramos, Imanol Arrieta Ibarra, Lars Roemheld","submitted_at":"2016-01-06T20:22:22Z","abstract_excerpt":"We train a reinforcement learner to play a simplified version of the game Angry Birds. The learner is provided with a game state in a manner similar to the output that could be produced by computer vision algorithms. We improve on the efficiency of regular {\\epsilon}-greedy Q-Learning with linear function approximation through more systematic exploration in Randomized Least Squares Value Iteration (RLSVI), an algorithm that samples its policy from a posterior distribution on optimal policies. With larger state-action spaces, efficient exploration becomes increasingly important, as evidenced by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.01297","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":"2026-05-18T01:23:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4AIiMrqa66Y67EPnO4prPpeuMK17Ig6UoVWWoG153ADGyzaTVO1CF3GvVyN14FrgTZyodF7hQbdC7896J6giDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T08:49:08.409335Z"},"content_sha256":"8cf08ac80a2c713324f875574966e037228bcffcbb2b2940fabdf8a474ce2157","schema_version":"1.0","event_id":"sha256:8cf08ac80a2c713324f875574966e037228bcffcbb2b2940fabdf8a474ce2157"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3BS3URIWTSHW3GWQKX2SGXXG3D/bundle.json","state_url":"https://pith.science/pith/3BS3URIWTSHW3GWQKX2SGXXG3D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3BS3URIWTSHW3GWQKX2SGXXG3D/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":"2026-06-05T08:49:08Z","links":{"resolver":"https://pith.science/pith/3BS3URIWTSHW3GWQKX2SGXXG3D","bundle":"https://pith.science/pith/3BS3URIWTSHW3GWQKX2SGXXG3D/bundle.json","state":"https://pith.science/pith/3BS3URIWTSHW3GWQKX2SGXXG3D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3BS3URIWTSHW3GWQKX2SGXXG3D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:3BS3URIWTSHW3GWQKX2SGXXG3D","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":"e02971d5f83a2f1c087d12aac0ad3d66f0bed3aeff340f8a9811c785c6363f98","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-01-06T20:22:22Z","title_canon_sha256":"cd5809ab09f71f6495bb5c8a3b4692ba82f5d2eb151733a24468c8335c77d294"},"schema_version":"1.0","source":{"id":"1601.01297","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1601.01297","created_at":"2026-05-18T01:23:15Z"},{"alias_kind":"arxiv_version","alias_value":"1601.01297v2","created_at":"2026-05-18T01:23:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.01297","created_at":"2026-05-18T01:23:15Z"},{"alias_kind":"pith_short_12","alias_value":"3BS3URIWTSHW","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"3BS3URIWTSHW3GWQ","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"3BS3URIW","created_at":"2026-05-18T12:29:55Z"}],"graph_snapshots":[{"event_id":"sha256:8cf08ac80a2c713324f875574966e037228bcffcbb2b2940fabdf8a474ce2157","target":"graph","created_at":"2026-05-18T01:23:15Z","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":"We train a reinforcement learner to play a simplified version of the game Angry Birds. The learner is provided with a game state in a manner similar to the output that could be produced by computer vision algorithms. We improve on the efficiency of regular {\\epsilon}-greedy Q-Learning with linear function approximation through more systematic exploration in Randomized Least Squares Value Iteration (RLSVI), an algorithm that samples its policy from a posterior distribution on optimal policies. With larger state-action spaces, efficient exploration becomes increasingly important, as evidenced by","authors_text":"Bernardo Ramos, Imanol Arrieta Ibarra, Lars Roemheld","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-01-06T20:22:22Z","title":"Angrier Birds: Bayesian reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.01297","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":"sha256:95674ea13359a78a094902be1af186a1ab4168c89e6349207c6eeeb44061570e","target":"record","created_at":"2026-05-18T01:23:15Z","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":"e02971d5f83a2f1c087d12aac0ad3d66f0bed3aeff340f8a9811c785c6363f98","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-01-06T20:22:22Z","title_canon_sha256":"cd5809ab09f71f6495bb5c8a3b4692ba82f5d2eb151733a24468c8335c77d294"},"schema_version":"1.0","source":{"id":"1601.01297","kind":"arxiv","version":2}},"canonical_sha256":"d865ba45169c8f6d9ad055f5235ee6d8fca5a307addf4f94652177ae4f144666","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d865ba45169c8f6d9ad055f5235ee6d8fca5a307addf4f94652177ae4f144666","first_computed_at":"2026-05-18T01:23:15.735083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:23:15.735083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PqPkAYCWR34jHi6DomLeI1BGKIx2ARqBM3DoEzXF+mzBSbGDBWPTionm5/iXQWZgAXe47b9fZXZcxuI4DN2hAA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:23:15.735703Z","signed_message":"canonical_sha256_bytes"},"source_id":"1601.01297","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95674ea13359a78a094902be1af186a1ab4168c89e6349207c6eeeb44061570e","sha256:8cf08ac80a2c713324f875574966e037228bcffcbb2b2940fabdf8a474ce2157"],"state_sha256":"9a9bc89f4f6c76366c1fce22d671a4b73f4b975906aab2df4202a865b0190a79"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/mcUH/lkJ7r6WD5kqfNTI2P2J3udReMsHUT2GMPDTztHu+ABoIxDWeR0DQLsA/Ts6v2s0+qEVg+FdftGDI8XDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T08:49:08.411294Z","bundle_sha256":"a7b41481cf60700ca3a4a7b14815ca29ea87335a3d76f786165a81a8642b3466"}}