{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:K4CRQCASFUONDISOPWHMWYZGKR","short_pith_number":"pith:K4CRQCAS","canonical_record":{"source":{"id":"1706.10031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-30T06:09:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"11f0f8d6e19a6b887e0720e4facffb93dd74504d77eebc0bbde5bab024509a25","abstract_canon_sha256":"13a22d503c5e9a23da277ab80ac190803bdbcb0233767ce67caa319e8383d041"},"schema_version":"1.0"},"canonical_sha256":"57051808122d1cd1a24e7d8ecb6326544b67b3ba5b1c583379fccce22c2a8f82","source":{"kind":"arxiv","id":"1706.10031","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.10031","created_at":"2026-05-18T00:41:11Z"},{"alias_kind":"arxiv_version","alias_value":"1706.10031v1","created_at":"2026-05-18T00:41:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.10031","created_at":"2026-05-18T00:41:11Z"},{"alias_kind":"pith_short_12","alias_value":"K4CRQCASFUON","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"K4CRQCASFUONDISO","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"K4CRQCAS","created_at":"2026-05-18T12:31:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:K4CRQCASFUONDISOPWHMWYZGKR","target":"record","payload":{"canonical_record":{"source":{"id":"1706.10031","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-30T06:09:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"11f0f8d6e19a6b887e0720e4facffb93dd74504d77eebc0bbde5bab024509a25","abstract_canon_sha256":"13a22d503c5e9a23da277ab80ac190803bdbcb0233767ce67caa319e8383d041"},"schema_version":"1.0"},"canonical_sha256":"57051808122d1cd1a24e7d8ecb6326544b67b3ba5b1c583379fccce22c2a8f82","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:11.659540Z","signature_b64":"pY0leK0aoK9Th7+1gICEL0j+rPmEPR73tXHaTx33hJXw58+9LzBz2QnGnoyrqKI4ffrsWa8rD+6nITKKHC3ZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57051808122d1cd1a24e7d8ecb6326544b67b3ba5b1c583379fccce22c2a8f82","last_reissued_at":"2026-05-18T00:41:11.658826Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:11.658826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.10031","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":"2026-05-18T00:41:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cUG6S9Cd9LFIXZnBNjn0hZOBqVbN5ql9nXEngjNYKrex6/hFdyYYjN0C6YR+JfGXmhXT0nNFo71ZMy2R4n4bDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:05:32.780939Z"},"content_sha256":"d5391ac5ed311cd1492d630f8182da7f8de1515e86328ad4e9d91a9a708dddea","schema_version":"1.0","event_id":"sha256:d5391ac5ed311cd1492d630f8182da7f8de1515e86328ad4e9d91a9a708dddea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:K4CRQCASFUONDISOPWHMWYZGKR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Sequence Model Training via $\\alpha$-divergence Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Atsunori Kanemura, Shin-ichi Maeda, Shin Ishii, Sotetsu Koyamada, Yuta Kikuchi","submitted_at":"2017-06-30T06:09:47Z","abstract_excerpt":"We propose a new neural sequence model training method in which the objective function is defined by $\\alpha$-divergence. We demonstrate that the objective function generalizes the maximum-likelihood (ML)-based and reinforcement learning (RL)-based objective functions as special cases (i.e., ML corresponds to $\\alpha \\to 0$ and RL to $\\alpha \\to1$). We also show that the gradient of the objective function can be considered a mixture of ML- and RL-based objective gradients. The experimental results of a machine translation task show that minimizing the objective function with $\\alpha > 0$ outpe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.10031","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":"2026-05-18T00:41:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7DZd4iJa4tvIkr48LN1dqhW0bG97B0/WhvjyGfwbuep7f1bbxnimDoo7ck1CvmbtwFyIHDrJWl6KH4NxmJjiCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:05:32.781598Z"},"content_sha256":"d8b8f409f9b856c8991db1361c17e8b46f6b022d59cd2ce91511c378bc66bb26","schema_version":"1.0","event_id":"sha256:d8b8f409f9b856c8991db1361c17e8b46f6b022d59cd2ce91511c378bc66bb26"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K4CRQCASFUONDISOPWHMWYZGKR/bundle.json","state_url":"https://pith.science/pith/K4CRQCASFUONDISOPWHMWYZGKR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K4CRQCASFUONDISOPWHMWYZGKR/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":"2026-05-25T15:05:32Z","links":{"resolver":"https://pith.science/pith/K4CRQCASFUONDISOPWHMWYZGKR","bundle":"https://pith.science/pith/K4CRQCASFUONDISOPWHMWYZGKR/bundle.json","state":"https://pith.science/pith/K4CRQCASFUONDISOPWHMWYZGKR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K4CRQCASFUONDISOPWHMWYZGKR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:K4CRQCASFUONDISOPWHMWYZGKR","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":"13a22d503c5e9a23da277ab80ac190803bdbcb0233767ce67caa319e8383d041","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-30T06:09:47Z","title_canon_sha256":"11f0f8d6e19a6b887e0720e4facffb93dd74504d77eebc0bbde5bab024509a25"},"schema_version":"1.0","source":{"id":"1706.10031","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.10031","created_at":"2026-05-18T00:41:11Z"},{"alias_kind":"arxiv_version","alias_value":"1706.10031v1","created_at":"2026-05-18T00:41:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.10031","created_at":"2026-05-18T00:41:11Z"},{"alias_kind":"pith_short_12","alias_value":"K4CRQCASFUON","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"K4CRQCASFUONDISO","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"K4CRQCAS","created_at":"2026-05-18T12:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:d8b8f409f9b856c8991db1361c17e8b46f6b022d59cd2ce91511c378bc66bb26","target":"graph","created_at":"2026-05-18T00:41:11Z","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 propose a new neural sequence model training method in which the objective function is defined by $\\alpha$-divergence. We demonstrate that the objective function generalizes the maximum-likelihood (ML)-based and reinforcement learning (RL)-based objective functions as special cases (i.e., ML corresponds to $\\alpha \\to 0$ and RL to $\\alpha \\to1$). We also show that the gradient of the objective function can be considered a mixture of ML- and RL-based objective gradients. The experimental results of a machine translation task show that minimizing the objective function with $\\alpha > 0$ outpe","authors_text":"Atsunori Kanemura, Shin-ichi Maeda, Shin Ishii, Sotetsu Koyamada, Yuta Kikuchi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-30T06:09:47Z","title":"Neural Sequence Model Training via $\\alpha$-divergence Minimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.10031","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:d5391ac5ed311cd1492d630f8182da7f8de1515e86328ad4e9d91a9a708dddea","target":"record","created_at":"2026-05-18T00:41:11Z","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":"13a22d503c5e9a23da277ab80ac190803bdbcb0233767ce67caa319e8383d041","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-30T06:09:47Z","title_canon_sha256":"11f0f8d6e19a6b887e0720e4facffb93dd74504d77eebc0bbde5bab024509a25"},"schema_version":"1.0","source":{"id":"1706.10031","kind":"arxiv","version":1}},"canonical_sha256":"57051808122d1cd1a24e7d8ecb6326544b67b3ba5b1c583379fccce22c2a8f82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57051808122d1cd1a24e7d8ecb6326544b67b3ba5b1c583379fccce22c2a8f82","first_computed_at":"2026-05-18T00:41:11.658826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:41:11.658826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pY0leK0aoK9Th7+1gICEL0j+rPmEPR73tXHaTx33hJXw58+9LzBz2QnGnoyrqKI4ffrsWa8rD+6nITKKHC3ZBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:41:11.659540Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.10031","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5391ac5ed311cd1492d630f8182da7f8de1515e86328ad4e9d91a9a708dddea","sha256:d8b8f409f9b856c8991db1361c17e8b46f6b022d59cd2ce91511c378bc66bb26"],"state_sha256":"ae3c04a65abf3e56a6daa75eb32c79d754370ba0a70f157e7b63d82989d3b91d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jKy+SU06gYGhDfJvcE8vNtQtI5RSCwB9BN5l9ZkK2fHpAUDuaLgr2X3X5r8IC7JdK90hX3p54Tcso9QNEEUGDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T15:05:32.785295Z","bundle_sha256":"f867822c1756ab1c6858c9d5ee5ba03c0b9931026dcd008bffc6dc1155a62812"}}