{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:47KLRIIMQU7ARRLGDWKI6WNDAT","short_pith_number":"pith:47KLRIIM","canonical_record":{"source":{"id":"1907.04484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T02:54:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3bfe9cb98854467b9fb25ef57341930c9a18acbf7348aa2c6779c36f5d75c6e1","abstract_canon_sha256":"88a0a12a77f723ace2e191907a5b6f2215fc88d75cb488a60c09d931f520bfe0"},"schema_version":"1.0"},"canonical_sha256":"e7d4b8a10c853e08c5661d948f59a304e850fec76c6c4188908de7c44e5745ac","source":{"kind":"arxiv","id":"1907.04484","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.04484","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"arxiv_version","alias_value":"1907.04484v1","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04484","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"pith_short_12","alias_value":"47KLRIIMQU7A","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"47KLRIIMQU7ARRLG","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"47KLRIIM","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:47KLRIIMQU7ARRLGDWKI6WNDAT","target":"record","payload":{"canonical_record":{"source":{"id":"1907.04484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T02:54:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3bfe9cb98854467b9fb25ef57341930c9a18acbf7348aa2c6779c36f5d75c6e1","abstract_canon_sha256":"88a0a12a77f723ace2e191907a5b6f2215fc88d75cb488a60c09d931f520bfe0"},"schema_version":"1.0"},"canonical_sha256":"e7d4b8a10c853e08c5661d948f59a304e850fec76c6c4188908de7c44e5745ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:00.145290Z","signature_b64":"wqadMML/CBkktopcQ+2S1yNrIHjoP9cIvBwQqck/Yy8HBsTQDsnAS0dTqlqeO6/TFDn+l+K1mDZqHqUFF2J1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7d4b8a10c853e08c5661d948f59a304e850fec76c6c4188908de7c44e5745ac","last_reissued_at":"2026-05-17T23:41:00.144715Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:00.144715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.04484","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":"2026-05-17T23:41:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wuqG7eFE3/S3JcG0E/WZN/jM3fSsAcyz9Zu/tDDePF51X2TF0U5MJTdPoo0qz+0sDcbmWZtfwtfBdYwqUJhgDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:48:32.049277Z"},"content_sha256":"96935b988d638aa72656d6d11affd0466e5792e89d81e35116d769adcdcb30c9","schema_version":"1.0","event_id":"sha256:96935b988d638aa72656d6d11affd0466e5792e89d81e35116d769adcdcb30c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:47KLRIIMQU7ARRLGDWKI6WNDAT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Co-training for Policy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jialin Song, Masahiro Ono, Ravi Lanka, Yisong Yue","submitted_at":"2019-07-03T02:54:13Z","abstract_excerpt":"We study the problem of learning sequential decision-making policies in settings with multiple state-action representations. Such settings naturally arise in many domains, such as planning (e.g., multiple integer programming formulations) and various combinatorial optimization problems (e.g., those with both integer programming and graph-based formulations). Inspired by the classical co-training framework for classification, we study the problem of co-training for policy learning. We present sufficient conditions under which learning from two views can improve upon learning from a single view "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04484","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":"2026-05-17T23:41:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1U9bgxMycrwqDEj1gW3eNsHWqSbJDzuWBKG20spyNb+eSM8vZRTpfMZ7SD+N0HxYM9/nw2JQmw4YAM1o/sqXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:48:32.049696Z"},"content_sha256":"4fbaedbcb68b0efea483d2a7000ff56380429f93adcdaca9251d0f170c2a6800","schema_version":"1.0","event_id":"sha256:4fbaedbcb68b0efea483d2a7000ff56380429f93adcdaca9251d0f170c2a6800"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/47KLRIIMQU7ARRLGDWKI6WNDAT/bundle.json","state_url":"https://pith.science/pith/47KLRIIMQU7ARRLGDWKI6WNDAT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/47KLRIIMQU7ARRLGDWKI6WNDAT/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":"2026-05-27T13:48:32Z","links":{"resolver":"https://pith.science/pith/47KLRIIMQU7ARRLGDWKI6WNDAT","bundle":"https://pith.science/pith/47KLRIIMQU7ARRLGDWKI6WNDAT/bundle.json","state":"https://pith.science/pith/47KLRIIMQU7ARRLGDWKI6WNDAT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/47KLRIIMQU7ARRLGDWKI6WNDAT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:47KLRIIMQU7ARRLGDWKI6WNDAT","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":"88a0a12a77f723ace2e191907a5b6f2215fc88d75cb488a60c09d931f520bfe0","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T02:54:13Z","title_canon_sha256":"3bfe9cb98854467b9fb25ef57341930c9a18acbf7348aa2c6779c36f5d75c6e1"},"schema_version":"1.0","source":{"id":"1907.04484","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.04484","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"arxiv_version","alias_value":"1907.04484v1","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04484","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"pith_short_12","alias_value":"47KLRIIMQU7A","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"47KLRIIMQU7ARRLG","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"47KLRIIM","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:4fbaedbcb68b0efea483d2a7000ff56380429f93adcdaca9251d0f170c2a6800","target":"graph","created_at":"2026-05-17T23:41:00Z","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 study the problem of learning sequential decision-making policies in settings with multiple state-action representations. Such settings naturally arise in many domains, such as planning (e.g., multiple integer programming formulations) and various combinatorial optimization problems (e.g., those with both integer programming and graph-based formulations). Inspired by the classical co-training framework for classification, we study the problem of co-training for policy learning. We present sufficient conditions under which learning from two views can improve upon learning from a single view ","authors_text":"Jialin Song, Masahiro Ono, Ravi Lanka, Yisong Yue","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T02:54:13Z","title":"Co-training for Policy Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04484","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":"sha256:96935b988d638aa72656d6d11affd0466e5792e89d81e35116d769adcdcb30c9","target":"record","created_at":"2026-05-17T23:41:00Z","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":"88a0a12a77f723ace2e191907a5b6f2215fc88d75cb488a60c09d931f520bfe0","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-03T02:54:13Z","title_canon_sha256":"3bfe9cb98854467b9fb25ef57341930c9a18acbf7348aa2c6779c36f5d75c6e1"},"schema_version":"1.0","source":{"id":"1907.04484","kind":"arxiv","version":1}},"canonical_sha256":"e7d4b8a10c853e08c5661d948f59a304e850fec76c6c4188908de7c44e5745ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7d4b8a10c853e08c5661d948f59a304e850fec76c6c4188908de7c44e5745ac","first_computed_at":"2026-05-17T23:41:00.144715Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:00.144715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wqadMML/CBkktopcQ+2S1yNrIHjoP9cIvBwQqck/Yy8HBsTQDsnAS0dTqlqeO6/TFDn+l+K1mDZqHqUFF2J1BQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:00.145290Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.04484","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96935b988d638aa72656d6d11affd0466e5792e89d81e35116d769adcdcb30c9","sha256:4fbaedbcb68b0efea483d2a7000ff56380429f93adcdaca9251d0f170c2a6800"],"state_sha256":"7372e30cd02e461427838a4acd945d3ea9b8557a68bc407c85d69d2abe770535"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ufK3ldwb6dRCQI64CpGORHNX6aFQHMUw3v453HRKP6BfqRitrozrsNczkSX56IQtc0eM7mzROSZrzagf4iz5Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T13:48:32.053153Z","bundle_sha256":"da4abe7a6ca9afa83d664f0754ac46f82ffda883c2e7fad3929c1b2a663c39e2"}}