{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:CD4L53JSZAOX7MN5KMIRTX2B5Z","short_pith_number":"pith:CD4L53JS","canonical_record":{"source":{"id":"1106.5258","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-06-26T21:03:18Z","cross_cats_sorted":[],"title_canon_sha256":"fcfc61e77c2884c8844760c2f512b5b0fd1e95d66ecb57189568d2b6dfee4a6a","abstract_canon_sha256":"4f70f550dea42b47efc0a0e8417c0ffb77f5f52fc764995b2f2d852c032b0700"},"schema_version":"1.0"},"canonical_sha256":"10f8beed32c81d7fb1bd531119df41ee4646a47d6d165ff393bfd4fb47aa7a26","source":{"kind":"arxiv","id":"1106.5258","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1106.5258","created_at":"2026-05-18T04:19:13Z"},{"alias_kind":"arxiv_version","alias_value":"1106.5258v1","created_at":"2026-05-18T04:19:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1106.5258","created_at":"2026-05-18T04:19:13Z"},{"alias_kind":"pith_short_12","alias_value":"CD4L53JSZAOX","created_at":"2026-05-18T12:26:26Z"},{"alias_kind":"pith_short_16","alias_value":"CD4L53JSZAOX7MN5","created_at":"2026-05-18T12:26:26Z"},{"alias_kind":"pith_short_8","alias_value":"CD4L53JS","created_at":"2026-05-18T12:26:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:CD4L53JSZAOX7MN5KMIRTX2B5Z","target":"record","payload":{"canonical_record":{"source":{"id":"1106.5258","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-06-26T21:03:18Z","cross_cats_sorted":[],"title_canon_sha256":"fcfc61e77c2884c8844760c2f512b5b0fd1e95d66ecb57189568d2b6dfee4a6a","abstract_canon_sha256":"4f70f550dea42b47efc0a0e8417c0ffb77f5f52fc764995b2f2d852c032b0700"},"schema_version":"1.0"},"canonical_sha256":"10f8beed32c81d7fb1bd531119df41ee4646a47d6d165ff393bfd4fb47aa7a26","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:19:13.995708Z","signature_b64":"/OSMCcJuOzZuGxyxtCoYX6+otlGg2ob1oQbptznVOVZJasUOm3pkgjU9h74EEw72Xg05e/LH/5fmZk4/9HmWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10f8beed32c81d7fb1bd531119df41ee4646a47d6d165ff393bfd4fb47aa7a26","last_reissued_at":"2026-05-18T04:19:13.995110Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:19:13.995110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1106.5258","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":"2026-05-18T04:19:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Go4GdhBfeiz09jY5jyVuHE62ELVjxRJivikDGtqyvydyvxz7qnx5GbItwJanItS/5VdGCbGdpi2RsaZzvZALBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T02:03:41.567244Z"},"content_sha256":"98c6e59f180faba7b58144d8c4d30887e2fd15e997eace055cb0730cdf478872","schema_version":"1.0","event_id":"sha256:98c6e59f180faba7b58144d8c4d30887e2fd15e997eace055cb0730cdf478872"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:CD4L53JSZAOX7MN5KMIRTX2B5Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Coordinate Efficiently: A Model-based Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"M. Tennenholtz, R. I. Brafman","submitted_at":"2011-06-26T21:03:18Z","abstract_excerpt":"In common-interest stochastic games all players receive an identical payoff. Players participating in such games must learn to coordinate with each other in order to receive the highest-possible value. A number of reinforcement learning algorithms have been proposed for this problem, and some have been shown to converge to good solutions in the limit. In this paper we show that using very simple model-based algorithms, much better (i.e., polynomial) convergence rates can be attained. Moreover, our model-based algorithms are guaranteed to converge to the optimal value, unlike many of the existi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1106.5258","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":"2026-05-18T04:19:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+iBfvdHvtmI/na+4WcW9znrWoq8rqk2gkMadzlZADuRGCvuPs2Ix0X8P855E5nGCqCHnUmD3qEhpGYVZuAK0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T02:03:41.567608Z"},"content_sha256":"10fd33811f5a3e2d7bd14f6057ea23ea3982b99435364a1b34a265edb7ebf4b7","schema_version":"1.0","event_id":"sha256:10fd33811f5a3e2d7bd14f6057ea23ea3982b99435364a1b34a265edb7ebf4b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CD4L53JSZAOX7MN5KMIRTX2B5Z/bundle.json","state_url":"https://pith.science/pith/CD4L53JSZAOX7MN5KMIRTX2B5Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CD4L53JSZAOX7MN5KMIRTX2B5Z/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":"2026-06-02T02:03:41Z","links":{"resolver":"https://pith.science/pith/CD4L53JSZAOX7MN5KMIRTX2B5Z","bundle":"https://pith.science/pith/CD4L53JSZAOX7MN5KMIRTX2B5Z/bundle.json","state":"https://pith.science/pith/CD4L53JSZAOX7MN5KMIRTX2B5Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CD4L53JSZAOX7MN5KMIRTX2B5Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:CD4L53JSZAOX7MN5KMIRTX2B5Z","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":"4f70f550dea42b47efc0a0e8417c0ffb77f5f52fc764995b2f2d852c032b0700","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-06-26T21:03:18Z","title_canon_sha256":"fcfc61e77c2884c8844760c2f512b5b0fd1e95d66ecb57189568d2b6dfee4a6a"},"schema_version":"1.0","source":{"id":"1106.5258","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1106.5258","created_at":"2026-05-18T04:19:13Z"},{"alias_kind":"arxiv_version","alias_value":"1106.5258v1","created_at":"2026-05-18T04:19:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1106.5258","created_at":"2026-05-18T04:19:13Z"},{"alias_kind":"pith_short_12","alias_value":"CD4L53JSZAOX","created_at":"2026-05-18T12:26:26Z"},{"alias_kind":"pith_short_16","alias_value":"CD4L53JSZAOX7MN5","created_at":"2026-05-18T12:26:26Z"},{"alias_kind":"pith_short_8","alias_value":"CD4L53JS","created_at":"2026-05-18T12:26:26Z"}],"graph_snapshots":[{"event_id":"sha256:10fd33811f5a3e2d7bd14f6057ea23ea3982b99435364a1b34a265edb7ebf4b7","target":"graph","created_at":"2026-05-18T04:19:13Z","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 common-interest stochastic games all players receive an identical payoff. Players participating in such games must learn to coordinate with each other in order to receive the highest-possible value. A number of reinforcement learning algorithms have been proposed for this problem, and some have been shown to converge to good solutions in the limit. In this paper we show that using very simple model-based algorithms, much better (i.e., polynomial) convergence rates can be attained. Moreover, our model-based algorithms are guaranteed to converge to the optimal value, unlike many of the existi","authors_text":"M. Tennenholtz, R. I. Brafman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-06-26T21:03:18Z","title":"Learning to Coordinate Efficiently: A Model-based Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1106.5258","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":"sha256:98c6e59f180faba7b58144d8c4d30887e2fd15e997eace055cb0730cdf478872","target":"record","created_at":"2026-05-18T04:19:13Z","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":"4f70f550dea42b47efc0a0e8417c0ffb77f5f52fc764995b2f2d852c032b0700","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-06-26T21:03:18Z","title_canon_sha256":"fcfc61e77c2884c8844760c2f512b5b0fd1e95d66ecb57189568d2b6dfee4a6a"},"schema_version":"1.0","source":{"id":"1106.5258","kind":"arxiv","version":1}},"canonical_sha256":"10f8beed32c81d7fb1bd531119df41ee4646a47d6d165ff393bfd4fb47aa7a26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10f8beed32c81d7fb1bd531119df41ee4646a47d6d165ff393bfd4fb47aa7a26","first_computed_at":"2026-05-18T04:19:13.995110Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:19:13.995110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/OSMCcJuOzZuGxyxtCoYX6+otlGg2ob1oQbptznVOVZJasUOm3pkgjU9h74EEw72Xg05e/LH/5fmZk4/9HmWAw==","signature_status":"signed_v1","signed_at":"2026-05-18T04:19:13.995708Z","signed_message":"canonical_sha256_bytes"},"source_id":"1106.5258","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98c6e59f180faba7b58144d8c4d30887e2fd15e997eace055cb0730cdf478872","sha256:10fd33811f5a3e2d7bd14f6057ea23ea3982b99435364a1b34a265edb7ebf4b7"],"state_sha256":"f6f759b8244c6113599e8a999ebb3d331642d7b04563c896e874e52e49c5b44f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"698U2E+g4kZQJUl9EiQD057lXnrak+d/Bkt5Y3YiNH/EC7zCDj2LjXvkesq7ZGYrgcOuqGT56xPMUDS3O5KgBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T02:03:41.569606Z","bundle_sha256":"dde8cbfbee0c6377e6ce5becaed5cb41f247598edfa9267839eda29dcddfb444"}}