{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:5Y46OVVBJORA3GO26QSCNLDG3E","short_pith_number":"pith:5Y46OVVB","canonical_record":{"source":{"id":"1505.00274","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-05-01T20:29:27Z","cross_cats_sorted":["cs.SY","stat.ML"],"title_canon_sha256":"212700f00dd98c9bc5f8f3efdca25fabf4b641655ccd7af2c01a556c963bfa0a","abstract_canon_sha256":"dcbf82ea8f3b5407e24ad84bb59fe4211f1b4284a0533215009eb6be20341938"},"schema_version":"1.0"},"canonical_sha256":"ee39e756a14ba20d99daf42426ac66d906f24296a05e5e8e31c3484509a39d43","source":{"kind":"arxiv","id":"1505.00274","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.00274","created_at":"2026-05-18T01:26:18Z"},{"alias_kind":"arxiv_version","alias_value":"1505.00274v2","created_at":"2026-05-18T01:26:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.00274","created_at":"2026-05-18T01:26:18Z"},{"alias_kind":"pith_short_12","alias_value":"5Y46OVVBJORA","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"5Y46OVVBJORA3GO2","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"5Y46OVVB","created_at":"2026-05-18T12:29:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:5Y46OVVBJORA3GO26QSCNLDG3E","target":"record","payload":{"canonical_record":{"source":{"id":"1505.00274","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-05-01T20:29:27Z","cross_cats_sorted":["cs.SY","stat.ML"],"title_canon_sha256":"212700f00dd98c9bc5f8f3efdca25fabf4b641655ccd7af2c01a556c963bfa0a","abstract_canon_sha256":"dcbf82ea8f3b5407e24ad84bb59fe4211f1b4284a0533215009eb6be20341938"},"schema_version":"1.0"},"canonical_sha256":"ee39e756a14ba20d99daf42426ac66d906f24296a05e5e8e31c3484509a39d43","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:18.409604Z","signature_b64":"vS3z8uq0NlIQaUmkWK1mqhi51j5va8P6BY7xgYJ0mY4u2tgDKa38zN9jKXR4rTejMZQ8cAIUXSSyBRHtECGODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee39e756a14ba20d99daf42426ac66d906f24296a05e5e8e31c3484509a39d43","last_reissued_at":"2026-05-18T01:26:18.409025Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:18.409025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1505.00274","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":"2026-05-18T01:26:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I0sv+aQxIWoO6gjWmtrzGhDIQHNRl7tDDuTkmARwLd9VvsbCfmCyuiMTff/TG/XU2FJIgxqOJF/BsO5xIMeuCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T20:30:49.073166Z"},"content_sha256":"cf12d6b6b98ee138fcc890bd3661d0571fbaea15a825381a2cb8760d373e2f84","schema_version":"1.0","event_id":"sha256:cf12d6b6b98ee138fcc890bd3661d0571fbaea15a825381a2cb8760d373e2f84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:5Y46OVVBJORA3GO26QSCNLDG3E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stick-Breaking Policy Learning in Dec-POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","stat.ML"],"primary_cat":"cs.AI","authors_text":"Christopher Amato, Jonathan P. How, Lawrence Carin, Miao Liu, Xuejun Liao","submitted_at":"2015-05-01T20:29:27Z","abstract_excerpt":"Expectation maximization (EM) has recently been shown to be an efficient algorithm for learning finite-state controllers (FSCs) in large decentralized POMDPs (Dec-POMDPs). However, current methods use fixed-size FSCs and often converge to maxima that are far from optimal. This paper considers a variable-size FSC to represent the local policy of each agent. These variable-size FSCs are constructed using a stick-breaking prior, leading to a new framework called \\emph{decentralized stick-breaking policy representation} (Dec-SBPR). This approach learns the controller parameters with a variational "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.00274","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":"2026-05-18T01:26:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c4ZQwW+EONctSFuuaHN/qyonPOH+1i9Te4k2d9qbXep64o4nXF0QYLrndI9NlZwF7wlDHtc5/1QqMc9aoouEBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T20:30:49.073743Z"},"content_sha256":"6c70d3d3a6dac83772022d8f271921ffb2eb40c0ccab65def8fe2f3644a550b3","schema_version":"1.0","event_id":"sha256:6c70d3d3a6dac83772022d8f271921ffb2eb40c0ccab65def8fe2f3644a550b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5Y46OVVBJORA3GO26QSCNLDG3E/bundle.json","state_url":"https://pith.science/pith/5Y46OVVBJORA3GO26QSCNLDG3E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5Y46OVVBJORA3GO26QSCNLDG3E/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":"2026-05-29T20:30:49Z","links":{"resolver":"https://pith.science/pith/5Y46OVVBJORA3GO26QSCNLDG3E","bundle":"https://pith.science/pith/5Y46OVVBJORA3GO26QSCNLDG3E/bundle.json","state":"https://pith.science/pith/5Y46OVVBJORA3GO26QSCNLDG3E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5Y46OVVBJORA3GO26QSCNLDG3E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:5Y46OVVBJORA3GO26QSCNLDG3E","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":"dcbf82ea8f3b5407e24ad84bb59fe4211f1b4284a0533215009eb6be20341938","cross_cats_sorted":["cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-05-01T20:29:27Z","title_canon_sha256":"212700f00dd98c9bc5f8f3efdca25fabf4b641655ccd7af2c01a556c963bfa0a"},"schema_version":"1.0","source":{"id":"1505.00274","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.00274","created_at":"2026-05-18T01:26:18Z"},{"alias_kind":"arxiv_version","alias_value":"1505.00274v2","created_at":"2026-05-18T01:26:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.00274","created_at":"2026-05-18T01:26:18Z"},{"alias_kind":"pith_short_12","alias_value":"5Y46OVVBJORA","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"5Y46OVVBJORA3GO2","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"5Y46OVVB","created_at":"2026-05-18T12:29:07Z"}],"graph_snapshots":[{"event_id":"sha256:6c70d3d3a6dac83772022d8f271921ffb2eb40c0ccab65def8fe2f3644a550b3","target":"graph","created_at":"2026-05-18T01:26:18Z","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":"Expectation maximization (EM) has recently been shown to be an efficient algorithm for learning finite-state controllers (FSCs) in large decentralized POMDPs (Dec-POMDPs). However, current methods use fixed-size FSCs and often converge to maxima that are far from optimal. This paper considers a variable-size FSC to represent the local policy of each agent. These variable-size FSCs are constructed using a stick-breaking prior, leading to a new framework called \\emph{decentralized stick-breaking policy representation} (Dec-SBPR). This approach learns the controller parameters with a variational ","authors_text":"Christopher Amato, Jonathan P. How, Lawrence Carin, Miao Liu, Xuejun Liao","cross_cats":["cs.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-05-01T20:29:27Z","title":"Stick-Breaking Policy Learning in Dec-POMDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.00274","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:cf12d6b6b98ee138fcc890bd3661d0571fbaea15a825381a2cb8760d373e2f84","target":"record","created_at":"2026-05-18T01:26:18Z","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":"dcbf82ea8f3b5407e24ad84bb59fe4211f1b4284a0533215009eb6be20341938","cross_cats_sorted":["cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-05-01T20:29:27Z","title_canon_sha256":"212700f00dd98c9bc5f8f3efdca25fabf4b641655ccd7af2c01a556c963bfa0a"},"schema_version":"1.0","source":{"id":"1505.00274","kind":"arxiv","version":2}},"canonical_sha256":"ee39e756a14ba20d99daf42426ac66d906f24296a05e5e8e31c3484509a39d43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee39e756a14ba20d99daf42426ac66d906f24296a05e5e8e31c3484509a39d43","first_computed_at":"2026-05-18T01:26:18.409025Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:26:18.409025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vS3z8uq0NlIQaUmkWK1mqhi51j5va8P6BY7xgYJ0mY4u2tgDKa38zN9jKXR4rTejMZQ8cAIUXSSyBRHtECGODg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:26:18.409604Z","signed_message":"canonical_sha256_bytes"},"source_id":"1505.00274","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf12d6b6b98ee138fcc890bd3661d0571fbaea15a825381a2cb8760d373e2f84","sha256:6c70d3d3a6dac83772022d8f271921ffb2eb40c0ccab65def8fe2f3644a550b3"],"state_sha256":"f51847a0ee63fe00432a215d9babb51ad097024ceef3fa3ad3b79a7264963f3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uwBeDnt0dUY9bZk/xSnnH7QJiWMozqVjjYsUwwvf2JKVJeUSddzDUooSV3Df8vxqDao7GJOmY0e9PFMijkvTAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T20:30:49.076162Z","bundle_sha256":"8f538c18c7fac0b6b649a3914be2764a7a2f7b47646fbc4b6bc292934f458671"}}