{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:KOMOFQA6VL2PKSOF2JV6M5E4JO","short_pith_number":"pith:KOMOFQA6","canonical_record":{"source":{"id":"1407.0449","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-07-02T03:19:43Z","cross_cats_sorted":["cs.SY","math.OC","stat.ML"],"title_canon_sha256":"e135126c2be09723f98ad354d780e380f80f4047cbe9b871fd22aca34ad66433","abstract_canon_sha256":"956869701f86fbade2adec9a7b0c2e9c236040f647bf2c59a7865f1d3df38b09"},"schema_version":"1.0"},"canonical_sha256":"5398e2c01eaaf4f549c5d26be6749c4b825b4cf6a461e0b440987d7568b6db87","source":{"kind":"arxiv","id":"1407.0449","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1407.0449","created_at":"2026-05-18T02:48:33Z"},{"alias_kind":"arxiv_version","alias_value":"1407.0449v1","created_at":"2026-05-18T02:48:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.0449","created_at":"2026-05-18T02:48:33Z"},{"alias_kind":"pith_short_12","alias_value":"KOMOFQA6VL2P","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"KOMOFQA6VL2PKSOF","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"KOMOFQA6","created_at":"2026-05-18T12:28:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:KOMOFQA6VL2PKSOF2JV6M5E4JO","target":"record","payload":{"canonical_record":{"source":{"id":"1407.0449","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-07-02T03:19:43Z","cross_cats_sorted":["cs.SY","math.OC","stat.ML"],"title_canon_sha256":"e135126c2be09723f98ad354d780e380f80f4047cbe9b871fd22aca34ad66433","abstract_canon_sha256":"956869701f86fbade2adec9a7b0c2e9c236040f647bf2c59a7865f1d3df38b09"},"schema_version":"1.0"},"canonical_sha256":"5398e2c01eaaf4f549c5d26be6749c4b825b4cf6a461e0b440987d7568b6db87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:48:33.755590Z","signature_b64":"RwT9gqIu6CMxxSsAAoSAY0DROy7FP86GhAuJ2VxGSg2MVsV8INNiT90cSqeVsCti8lB89Q4bkfXc4ZxhWZo7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5398e2c01eaaf4f549c5d26be6749c4b825b4cf6a461e0b440987d7568b6db87","last_reissued_at":"2026-05-18T02:48:33.754946Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:48:33.754946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1407.0449","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":"2026-05-18T02:48:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XZsHBUT7MD00Z90k7dIQ7sumrfN/UCJENIUeRbrrW/cSsQgfIbzjGua38JwdBaqXO8qJzcJOdc5W2E9d6V/mBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T18:12:36.424911Z"},"content_sha256":"4bd48c90c83ac4ebba018a113d3aa97946664ded8fd62b54590ece5647ea3f80","schema_version":"1.0","event_id":"sha256:4bd48c90c83ac4ebba018a113d3aa97946664ded8fd62b54590ece5647ea3f80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:KOMOFQA6VL2PKSOF2JV6M5E4JO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Classification-based Approximate Policy Iteration: Experiments and Extended Discussions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir-massoud Farahmand, Andr\\'e M.S. Barreto, Doina Precup, Mohammad Ghavamzadeh","submitted_at":"2014-07-02T03:19:43Z","abstract_excerpt":"Tackling large approximate dynamic programming or reinforcement learning problems requires methods that can exploit regularities, or intrinsic structure, of the problem in hand. Most current methods are geared towards exploiting the regularities of either the value function or the policy. We introduce a general classification-based approximate policy iteration (CAPI) framework, which encompasses a large class of algorithms that can exploit regularities of both the value function and the policy space, depending on what is advantageous. This framework has two main components: a generic value fun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.0449","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":"2026-05-18T02:48:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VCv942QLxd1lmaEN4yerDNBMfdwm9WFgA6+tcPB6eNj2ET08HDdJt6+Vl1JFWIUBGBHbhlgpA6e+fHlzM1B8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T18:12:36.425257Z"},"content_sha256":"47b36d5a286b25e16d7596e80a6a83653bde68d5899c60682eaf5b431df3f3de","schema_version":"1.0","event_id":"sha256:47b36d5a286b25e16d7596e80a6a83653bde68d5899c60682eaf5b431df3f3de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KOMOFQA6VL2PKSOF2JV6M5E4JO/bundle.json","state_url":"https://pith.science/pith/KOMOFQA6VL2PKSOF2JV6M5E4JO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KOMOFQA6VL2PKSOF2JV6M5E4JO/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":"2026-05-21T18:12:36Z","links":{"resolver":"https://pith.science/pith/KOMOFQA6VL2PKSOF2JV6M5E4JO","bundle":"https://pith.science/pith/KOMOFQA6VL2PKSOF2JV6M5E4JO/bundle.json","state":"https://pith.science/pith/KOMOFQA6VL2PKSOF2JV6M5E4JO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KOMOFQA6VL2PKSOF2JV6M5E4JO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:KOMOFQA6VL2PKSOF2JV6M5E4JO","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":"956869701f86fbade2adec9a7b0c2e9c236040f647bf2c59a7865f1d3df38b09","cross_cats_sorted":["cs.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-07-02T03:19:43Z","title_canon_sha256":"e135126c2be09723f98ad354d780e380f80f4047cbe9b871fd22aca34ad66433"},"schema_version":"1.0","source":{"id":"1407.0449","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1407.0449","created_at":"2026-05-18T02:48:33Z"},{"alias_kind":"arxiv_version","alias_value":"1407.0449v1","created_at":"2026-05-18T02:48:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.0449","created_at":"2026-05-18T02:48:33Z"},{"alias_kind":"pith_short_12","alias_value":"KOMOFQA6VL2P","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"KOMOFQA6VL2PKSOF","created_at":"2026-05-18T12:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"KOMOFQA6","created_at":"2026-05-18T12:28:35Z"}],"graph_snapshots":[{"event_id":"sha256:47b36d5a286b25e16d7596e80a6a83653bde68d5899c60682eaf5b431df3f3de","target":"graph","created_at":"2026-05-18T02:48:33Z","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":"Tackling large approximate dynamic programming or reinforcement learning problems requires methods that can exploit regularities, or intrinsic structure, of the problem in hand. Most current methods are geared towards exploiting the regularities of either the value function or the policy. We introduce a general classification-based approximate policy iteration (CAPI) framework, which encompasses a large class of algorithms that can exploit regularities of both the value function and the policy space, depending on what is advantageous. This framework has two main components: a generic value fun","authors_text":"Amir-massoud Farahmand, Andr\\'e M.S. Barreto, Doina Precup, Mohammad Ghavamzadeh","cross_cats":["cs.SY","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-07-02T03:19:43Z","title":"Classification-based Approximate Policy Iteration: Experiments and Extended Discussions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.0449","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":"sha256:4bd48c90c83ac4ebba018a113d3aa97946664ded8fd62b54590ece5647ea3f80","target":"record","created_at":"2026-05-18T02:48:33Z","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":"956869701f86fbade2adec9a7b0c2e9c236040f647bf2c59a7865f1d3df38b09","cross_cats_sorted":["cs.SY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-07-02T03:19:43Z","title_canon_sha256":"e135126c2be09723f98ad354d780e380f80f4047cbe9b871fd22aca34ad66433"},"schema_version":"1.0","source":{"id":"1407.0449","kind":"arxiv","version":1}},"canonical_sha256":"5398e2c01eaaf4f549c5d26be6749c4b825b4cf6a461e0b440987d7568b6db87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5398e2c01eaaf4f549c5d26be6749c4b825b4cf6a461e0b440987d7568b6db87","first_computed_at":"2026-05-18T02:48:33.754946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:48:33.754946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RwT9gqIu6CMxxSsAAoSAY0DROy7FP86GhAuJ2VxGSg2MVsV8INNiT90cSqeVsCti8lB89Q4bkfXc4ZxhWZo7Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:48:33.755590Z","signed_message":"canonical_sha256_bytes"},"source_id":"1407.0449","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bd48c90c83ac4ebba018a113d3aa97946664ded8fd62b54590ece5647ea3f80","sha256:47b36d5a286b25e16d7596e80a6a83653bde68d5899c60682eaf5b431df3f3de"],"state_sha256":"5b2fa3fd7d2d0bb5348cd6ce6a38d6e28a6892192c71eea033a988f61b7884a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+o7dCTymZXpPRe/nAsxdE983i/JfLJ9HRWraj45Q2aC2bmHtfCcXhGWp6acZyMG4Axiawyu5AyGYc9xDQ0VmDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T18:12:36.427441Z","bundle_sha256":"2fe35a9883a904234c57bba6af235db11e2abb03aa3913c30f373acc72ebdb3b"}}