{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KRUUYVDUPC442JJRZOTENJMTQB","short_pith_number":"pith:KRUUYVDU","canonical_record":{"source":{"id":"2210.03053","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-06T16:58:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e67fb1f97e4422e1d80de7dad57ff1e1b41d2094cc0c63aebb99e6f4fdaf93e6","abstract_canon_sha256":"ca4bd454d9a0ab9757c983f915d8eb4f60ecadc37817bc71e0aeb6b4b3d2d379"},"schema_version":"1.0"},"canonical_sha256":"54694c547478b9cd2531cba646a593805ae6988f560cc822e895a7188b6c07f4","source":{"kind":"arxiv","id":"2210.03053","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03053","created_at":"2026-07-05T05:04:06Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03053v1","created_at":"2026-07-05T05:04:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03053","created_at":"2026-07-05T05:04:06Z"},{"alias_kind":"pith_short_12","alias_value":"KRUUYVDUPC44","created_at":"2026-07-05T05:04:06Z"},{"alias_kind":"pith_short_16","alias_value":"KRUUYVDUPC442JJR","created_at":"2026-07-05T05:04:06Z"},{"alias_kind":"pith_short_8","alias_value":"KRUUYVDU","created_at":"2026-07-05T05:04:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KRUUYVDUPC442JJRZOTENJMTQB","target":"record","payload":{"canonical_record":{"source":{"id":"2210.03053","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-06T16:58:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e67fb1f97e4422e1d80de7dad57ff1e1b41d2094cc0c63aebb99e6f4fdaf93e6","abstract_canon_sha256":"ca4bd454d9a0ab9757c983f915d8eb4f60ecadc37817bc71e0aeb6b4b3d2d379"},"schema_version":"1.0"},"canonical_sha256":"54694c547478b9cd2531cba646a593805ae6988f560cc822e895a7188b6c07f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:06.777068Z","signature_b64":"6ygj066/xXxac66xxgRSwfdBg9zhZ5REmaocBRYoi4WdAhEZumCSIrmDuTw/83FmIS4huHeAWoNUfjWNTiOwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54694c547478b9cd2531cba646a593805ae6988f560cc822e895a7188b6c07f4","last_reissued_at":"2026-07-05T05:04:06.776652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:06.776652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.03053","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":"2026-07-05T05:04:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iFWFgvMxPoB/staKQ0hTSdwZCkzsak5hhuxgVqw3AX7EYJzhsHeq/n+6BoJNYJoQ6/Jarj2piFcYpDl5RllWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:00:19.850831Z"},"content_sha256":"32056cde23121b142b5ea6883eac5df91a76272734491f8d654b845eb184274d","schema_version":"1.0","event_id":"sha256:32056cde23121b142b5ea6883eac5df91a76272734491f8d654b845eb184274d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KRUUYVDUPC442JJRZOTENJMTQB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Large Action Spaces for Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Asaf Yehudai, Leshem Choshen, Lior Fox, Omri Abend","submitted_at":"2022-10-06T16:58:27Z","abstract_excerpt":"Applying Reinforcement learning (RL) following maximum likelihood estimation (MLE) pre-training is a versatile method for enhancing neural machine translation (NMT) performance. However, recent work has argued that the gains produced by RL for NMT are mostly due to promoting tokens that have already received a fairly high probability in pre-training. We hypothesize that the large action space is a main obstacle to RL's effectiveness in MT, and conduct two sets of experiments that lend support to our hypothesis. First, we find that reducing the size of the vocabulary improves RL's effectiveness"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03053","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.03053/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T05:04:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ilnBghZb33XSvXoRJHaqLDCpI+5Yul+bwr/yMBBFBCDI59NYNfp+IRyyKy8VqldiQWQ9TmzAdkOytxS5pAfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:00:19.851676Z"},"content_sha256":"b8626429fcd659a14ad29d815c66c99eac205061c81736b9277916f0e463d07d","schema_version":"1.0","event_id":"sha256:b8626429fcd659a14ad29d815c66c99eac205061c81736b9277916f0e463d07d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KRUUYVDUPC442JJRZOTENJMTQB/bundle.json","state_url":"https://pith.science/pith/KRUUYVDUPC442JJRZOTENJMTQB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KRUUYVDUPC442JJRZOTENJMTQB/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":"2026-08-05T13:00:19Z","links":{"resolver":"https://pith.science/pith/KRUUYVDUPC442JJRZOTENJMTQB","bundle":"https://pith.science/pith/KRUUYVDUPC442JJRZOTENJMTQB/bundle.json","state":"https://pith.science/pith/KRUUYVDUPC442JJRZOTENJMTQB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KRUUYVDUPC442JJRZOTENJMTQB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KRUUYVDUPC442JJRZOTENJMTQB","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":"ca4bd454d9a0ab9757c983f915d8eb4f60ecadc37817bc71e0aeb6b4b3d2d379","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-06T16:58:27Z","title_canon_sha256":"e67fb1f97e4422e1d80de7dad57ff1e1b41d2094cc0c63aebb99e6f4fdaf93e6"},"schema_version":"1.0","source":{"id":"2210.03053","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03053","created_at":"2026-07-05T05:04:06Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03053v1","created_at":"2026-07-05T05:04:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03053","created_at":"2026-07-05T05:04:06Z"},{"alias_kind":"pith_short_12","alias_value":"KRUUYVDUPC44","created_at":"2026-07-05T05:04:06Z"},{"alias_kind":"pith_short_16","alias_value":"KRUUYVDUPC442JJR","created_at":"2026-07-05T05:04:06Z"},{"alias_kind":"pith_short_8","alias_value":"KRUUYVDU","created_at":"2026-07-05T05:04:06Z"}],"graph_snapshots":[{"event_id":"sha256:b8626429fcd659a14ad29d815c66c99eac205061c81736b9277916f0e463d07d","target":"graph","created_at":"2026-07-05T05:04:06Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2210.03053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Applying Reinforcement learning (RL) following maximum likelihood estimation (MLE) pre-training is a versatile method for enhancing neural machine translation (NMT) performance. However, recent work has argued that the gains produced by RL for NMT are mostly due to promoting tokens that have already received a fairly high probability in pre-training. We hypothesize that the large action space is a main obstacle to RL's effectiveness in MT, and conduct two sets of experiments that lend support to our hypothesis. First, we find that reducing the size of the vocabulary improves RL's effectiveness","authors_text":"Asaf Yehudai, Leshem Choshen, Lior Fox, Omri Abend","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-06T16:58:27Z","title":"Reinforcement Learning with Large Action Spaces for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03053","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":"sha256:32056cde23121b142b5ea6883eac5df91a76272734491f8d654b845eb184274d","target":"record","created_at":"2026-07-05T05:04:06Z","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":"ca4bd454d9a0ab9757c983f915d8eb4f60ecadc37817bc71e0aeb6b4b3d2d379","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-06T16:58:27Z","title_canon_sha256":"e67fb1f97e4422e1d80de7dad57ff1e1b41d2094cc0c63aebb99e6f4fdaf93e6"},"schema_version":"1.0","source":{"id":"2210.03053","kind":"arxiv","version":1}},"canonical_sha256":"54694c547478b9cd2531cba646a593805ae6988f560cc822e895a7188b6c07f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54694c547478b9cd2531cba646a593805ae6988f560cc822e895a7188b6c07f4","first_computed_at":"2026-07-05T05:04:06.776652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:06.776652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6ygj066/xXxac66xxgRSwfdBg9zhZ5REmaocBRYoi4WdAhEZumCSIrmDuTw/83FmIS4huHeAWoNUfjWNTiOwDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:06.777068Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.03053","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32056cde23121b142b5ea6883eac5df91a76272734491f8d654b845eb184274d","sha256:b8626429fcd659a14ad29d815c66c99eac205061c81736b9277916f0e463d07d"],"state_sha256":"e88318fee3e172eadd8243722a1cabfc637a765fc67adcafd817a32b3ca44d92"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"76tWEEnGCRn2FbJE7a8JjzX1QZW1nzPtxG309FLFZNWi5SO3ov+omIKi2KKdkKaiGhUVOw9J6XgfDRtiUhjwAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:00:19.858163Z","bundle_sha256":"a5aa0faf25647ede688ee9a7b8db013b822131fa2dbc6119d3b7cd04f728d3fb"}}