{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:KQ2C2RUR6ZFSP2WY5DECDF346S","short_pith_number":"pith:KQ2C2RUR","canonical_record":{"source":{"id":"1605.06076","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-19T18:32:50Z","cross_cats_sorted":[],"title_canon_sha256":"9f636c1a44e3268e2c8789d7c4081088afe4af4bdeb9bc1f4c62be4ee8687a91","abstract_canon_sha256":"200f631b8a604a3db523ec435b408f9979353a9d183e9b48507b4ff983faf1a2"},"schema_version":"1.0"},"canonical_sha256":"54342d4691f64b27ead8e8c821977cf484de480a147c929675629a298c2ffe58","source":{"kind":"arxiv","id":"1605.06076","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.06076","created_at":"2026-05-18T01:14:26Z"},{"alias_kind":"arxiv_version","alias_value":"1605.06076v1","created_at":"2026-05-18T01:14:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.06076","created_at":"2026-05-18T01:14:26Z"},{"alias_kind":"pith_short_12","alias_value":"KQ2C2RUR6ZFS","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"KQ2C2RUR6ZFSP2WY","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"KQ2C2RUR","created_at":"2026-05-18T12:30:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:KQ2C2RUR6ZFSP2WY5DECDF346S","target":"record","payload":{"canonical_record":{"source":{"id":"1605.06076","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-19T18:32:50Z","cross_cats_sorted":[],"title_canon_sha256":"9f636c1a44e3268e2c8789d7c4081088afe4af4bdeb9bc1f4c62be4ee8687a91","abstract_canon_sha256":"200f631b8a604a3db523ec435b408f9979353a9d183e9b48507b4ff983faf1a2"},"schema_version":"1.0"},"canonical_sha256":"54342d4691f64b27ead8e8c821977cf484de480a147c929675629a298c2ffe58","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:14:26.583837Z","signature_b64":"W3iXFu1p3IbD4qIsv5tg+iKot967IRMWK8uMhteQhXlfqMujtq3la5JzTeAjj44baEDLQz9jFX4GEOKnghevCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54342d4691f64b27ead8e8c821977cf484de480a147c929675629a298c2ffe58","last_reissued_at":"2026-05-18T01:14:26.583137Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:14:26.583137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.06076","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":"2026-05-18T01:14:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hEJ6sKOF1DZTB12hPSCmJ76EEJHzdCClcBRF9F8poUKPsOtlkl7EHf1JNhkM5oGXonkq6HXpoFH4e6FJgyZZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T10:57:41.653608Z"},"content_sha256":"9c5ca63e9a856900c8b97d97125589f84aaf05454bac180941a20a7696a7f061","schema_version":"1.0","event_id":"sha256:9c5ca63e9a856900c8b97d97125589f84aaf05454bac180941a20a7696a7f061"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:KQ2C2RUR6ZFSP2WY5DECDF346S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On a convergent off -policy temporal difference learning algorithm in on-line learning environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Prasenjit Karmakar, Rajkumar Maity, Shalabh Bhatnagar","submitted_at":"2016-05-19T18:32:50Z","abstract_excerpt":"In this paper we provide a rigorous convergence analysis of a \"off\"-policy temporal difference learning algorithm with linear function approximation and per time-step linear computational complexity in \"online\" learning environment. The algorithm considered here is TDC with importance weighting introduced by Maei et al. We support our theoretical results by providing suitable empirical results for standard off-policy counterexamples."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.06076","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":"2026-05-18T01:14:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vBO2iyaW1V3sSPi48gC2j2MnUWeyCWEdE4POENO7DcpirIjNTAswxjXwWZn/PL87Hcx/+vLELGpAbBkpO+DxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T10:57:41.654307Z"},"content_sha256":"eeec1b9cab5aad686d5ae4c7f61cdfdd32d0fea1258fa9e0719b5e8119c3b092","schema_version":"1.0","event_id":"sha256:eeec1b9cab5aad686d5ae4c7f61cdfdd32d0fea1258fa9e0719b5e8119c3b092"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KQ2C2RUR6ZFSP2WY5DECDF346S/bundle.json","state_url":"https://pith.science/pith/KQ2C2RUR6ZFSP2WY5DECDF346S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KQ2C2RUR6ZFSP2WY5DECDF346S/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":"2026-05-31T10:57:41Z","links":{"resolver":"https://pith.science/pith/KQ2C2RUR6ZFSP2WY5DECDF346S","bundle":"https://pith.science/pith/KQ2C2RUR6ZFSP2WY5DECDF346S/bundle.json","state":"https://pith.science/pith/KQ2C2RUR6ZFSP2WY5DECDF346S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KQ2C2RUR6ZFSP2WY5DECDF346S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:KQ2C2RUR6ZFSP2WY5DECDF346S","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":"200f631b8a604a3db523ec435b408f9979353a9d183e9b48507b4ff983faf1a2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-19T18:32:50Z","title_canon_sha256":"9f636c1a44e3268e2c8789d7c4081088afe4af4bdeb9bc1f4c62be4ee8687a91"},"schema_version":"1.0","source":{"id":"1605.06076","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.06076","created_at":"2026-05-18T01:14:26Z"},{"alias_kind":"arxiv_version","alias_value":"1605.06076v1","created_at":"2026-05-18T01:14:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.06076","created_at":"2026-05-18T01:14:26Z"},{"alias_kind":"pith_short_12","alias_value":"KQ2C2RUR6ZFS","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"KQ2C2RUR6ZFSP2WY","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"KQ2C2RUR","created_at":"2026-05-18T12:30:25Z"}],"graph_snapshots":[{"event_id":"sha256:eeec1b9cab5aad686d5ae4c7f61cdfdd32d0fea1258fa9e0719b5e8119c3b092","target":"graph","created_at":"2026-05-18T01:14:26Z","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 paper we provide a rigorous convergence analysis of a \"off\"-policy temporal difference learning algorithm with linear function approximation and per time-step linear computational complexity in \"online\" learning environment. The algorithm considered here is TDC with importance weighting introduced by Maei et al. We support our theoretical results by providing suitable empirical results for standard off-policy counterexamples.","authors_text":"Prasenjit Karmakar, Rajkumar Maity, Shalabh Bhatnagar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-19T18:32:50Z","title":"On a convergent off -policy temporal difference learning algorithm in on-line learning environment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.06076","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":"sha256:9c5ca63e9a856900c8b97d97125589f84aaf05454bac180941a20a7696a7f061","target":"record","created_at":"2026-05-18T01:14:26Z","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":"200f631b8a604a3db523ec435b408f9979353a9d183e9b48507b4ff983faf1a2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-19T18:32:50Z","title_canon_sha256":"9f636c1a44e3268e2c8789d7c4081088afe4af4bdeb9bc1f4c62be4ee8687a91"},"schema_version":"1.0","source":{"id":"1605.06076","kind":"arxiv","version":1}},"canonical_sha256":"54342d4691f64b27ead8e8c821977cf484de480a147c929675629a298c2ffe58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54342d4691f64b27ead8e8c821977cf484de480a147c929675629a298c2ffe58","first_computed_at":"2026-05-18T01:14:26.583137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:14:26.583137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W3iXFu1p3IbD4qIsv5tg+iKot967IRMWK8uMhteQhXlfqMujtq3la5JzTeAjj44baEDLQz9jFX4GEOKnghevCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:14:26.583837Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.06076","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c5ca63e9a856900c8b97d97125589f84aaf05454bac180941a20a7696a7f061","sha256:eeec1b9cab5aad686d5ae4c7f61cdfdd32d0fea1258fa9e0719b5e8119c3b092"],"state_sha256":"7bde56ef157ad206ddb4c0060e9d4ea1b2fc223e2938138f1ec819564d64c617"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C0M4WX38ubXOep69Rox3yXrVCgBqJYAusDX6UCXmc++RJV3PKEf87Gqk6YneIvvzm22VkDlZyn++2JCjXMO6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T10:57:41.657862Z","bundle_sha256":"43af45b6c48aef5db7ecb7458264bc96f0cc654914472a596bcd7668d08c2425"}}