{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:7QVCOMFX2BXXRHXVECRLFXTFWD","short_pith_number":"pith:7QVCOMFX","canonical_record":{"source":{"id":"1707.09118","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-28T06:32:47Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"1091136b30bea2a63d47b63823c7a7205d2b0923b7bd6ec2f9bfa6d22836b6fa","abstract_canon_sha256":"4a128f04212d86cf1d62c51931ead39130c1f3c4764e506c4148d7c32499e2a0"},"schema_version":"1.0"},"canonical_sha256":"fc2a2730b7d06f789ef520a2b2de65b0dd89cd468175c51437cd8f3cb0acf54d","source":{"kind":"arxiv","id":"1707.09118","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.09118","created_at":"2026-05-18T00:28:02Z"},{"alias_kind":"arxiv_version","alias_value":"1707.09118v3","created_at":"2026-05-18T00:28:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09118","created_at":"2026-05-18T00:28:02Z"},{"alias_kind":"pith_short_12","alias_value":"7QVCOMFX2BXX","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7QVCOMFX2BXXRHXV","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7QVCOMFX","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:7QVCOMFX2BXXRHXVECRLFXTFWD","target":"record","payload":{"canonical_record":{"source":{"id":"1707.09118","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-28T06:32:47Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"1091136b30bea2a63d47b63823c7a7205d2b0923b7bd6ec2f9bfa6d22836b6fa","abstract_canon_sha256":"4a128f04212d86cf1d62c51931ead39130c1f3c4764e506c4148d7c32499e2a0"},"schema_version":"1.0"},"canonical_sha256":"fc2a2730b7d06f789ef520a2b2de65b0dd89cd468175c51437cd8f3cb0acf54d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:02.086643Z","signature_b64":"Ve2RzTYUop9lvwMns+uqYcMW6m0BilpqE5iIeKeba9ypgZwPZ7TCHGPKlPsT9uQVA10g/AVI3O503SYFYzlLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc2a2730b7d06f789ef520a2b2de65b0dd89cd468175c51437cd8f3cb0acf54d","last_reissued_at":"2026-05-18T00:28:02.085985Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:02.085985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.09118","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:28:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QiSjBIMie7m6+UqorADfoPviJlMes3/FNayIT+I+Fs8c0nkx7mYfkBuDN9e8o8oRuA/cpKpQ9DLW6A5A5L65Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T16:39:42.308649Z"},"content_sha256":"af24cdb0aef2bb8bf56773761b3da1287f762b3388458dd07e21eed50b0dd044","schema_version":"1.0","event_id":"sha256:af24cdb0aef2bb8bf56773761b3da1287f762b3388458dd07e21eed50b0dd044"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:7QVCOMFX2BXXRHXVECRLFXTFWD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Counterfactual Learning from Bandit Feedback under Deterministic Logging: A Case Study in Statistical Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Artem Sokolov, Carolin Lawrence, Stefan Riezler","submitted_at":"2017-07-28T06:32:47Z","abstract_excerpt":"The goal of counterfactual learning for statistical machine translation (SMT) is to optimize a target SMT system from logged data that consist of user feedback to translations that were predicted by another, historic SMT system. A challenge arises by the fact that risk-averse commercial SMT systems deterministically log the most probable translation. The lack of sufficient exploration of the SMT output space seemingly contradicts the theoretical requirements for counterfactual learning. We show that counterfactual learning from deterministic bandit logs is possible nevertheless by smoothing ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09118","kind":"arxiv","version":3},"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":"2026-05-18T00:28:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ef8t73PF9McGsPrSgKbLQk/r/5A/twCfrJxyACplnkCsgSeGhnB05HfxLEWP32rY4OBDD3ETv3BlZyv4CQDUCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T16:39:42.309289Z"},"content_sha256":"a01c35b41dd047aac6bcba5aa6a014f80c797901b056a273eec1f257beeb9a66","schema_version":"1.0","event_id":"sha256:a01c35b41dd047aac6bcba5aa6a014f80c797901b056a273eec1f257beeb9a66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7QVCOMFX2BXXRHXVECRLFXTFWD/bundle.json","state_url":"https://pith.science/pith/7QVCOMFX2BXXRHXVECRLFXTFWD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7QVCOMFX2BXXRHXVECRLFXTFWD/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":"2026-06-08T16:39:42Z","links":{"resolver":"https://pith.science/pith/7QVCOMFX2BXXRHXVECRLFXTFWD","bundle":"https://pith.science/pith/7QVCOMFX2BXXRHXVECRLFXTFWD/bundle.json","state":"https://pith.science/pith/7QVCOMFX2BXXRHXVECRLFXTFWD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7QVCOMFX2BXXRHXVECRLFXTFWD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7QVCOMFX2BXXRHXVECRLFXTFWD","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":"4a128f04212d86cf1d62c51931ead39130c1f3c4764e506c4148d7c32499e2a0","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-28T06:32:47Z","title_canon_sha256":"1091136b30bea2a63d47b63823c7a7205d2b0923b7bd6ec2f9bfa6d22836b6fa"},"schema_version":"1.0","source":{"id":"1707.09118","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.09118","created_at":"2026-05-18T00:28:02Z"},{"alias_kind":"arxiv_version","alias_value":"1707.09118v3","created_at":"2026-05-18T00:28:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.09118","created_at":"2026-05-18T00:28:02Z"},{"alias_kind":"pith_short_12","alias_value":"7QVCOMFX2BXX","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7QVCOMFX2BXXRHXV","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7QVCOMFX","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:a01c35b41dd047aac6bcba5aa6a014f80c797901b056a273eec1f257beeb9a66","target":"graph","created_at":"2026-05-18T00:28:02Z","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":"The goal of counterfactual learning for statistical machine translation (SMT) is to optimize a target SMT system from logged data that consist of user feedback to translations that were predicted by another, historic SMT system. A challenge arises by the fact that risk-averse commercial SMT systems deterministically log the most probable translation. The lack of sufficient exploration of the SMT output space seemingly contradicts the theoretical requirements for counterfactual learning. We show that counterfactual learning from deterministic bandit logs is possible nevertheless by smoothing ou","authors_text":"Artem Sokolov, Carolin Lawrence, Stefan Riezler","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-28T06:32:47Z","title":"Counterfactual Learning from Bandit Feedback under Deterministic Logging: A Case Study in Statistical Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.09118","kind":"arxiv","version":3},"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:af24cdb0aef2bb8bf56773761b3da1287f762b3388458dd07e21eed50b0dd044","target":"record","created_at":"2026-05-18T00:28:02Z","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":"4a128f04212d86cf1d62c51931ead39130c1f3c4764e506c4148d7c32499e2a0","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-28T06:32:47Z","title_canon_sha256":"1091136b30bea2a63d47b63823c7a7205d2b0923b7bd6ec2f9bfa6d22836b6fa"},"schema_version":"1.0","source":{"id":"1707.09118","kind":"arxiv","version":3}},"canonical_sha256":"fc2a2730b7d06f789ef520a2b2de65b0dd89cd468175c51437cd8f3cb0acf54d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc2a2730b7d06f789ef520a2b2de65b0dd89cd468175c51437cd8f3cb0acf54d","first_computed_at":"2026-05-18T00:28:02.085985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:02.085985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ve2RzTYUop9lvwMns+uqYcMW6m0BilpqE5iIeKeba9ypgZwPZ7TCHGPKlPsT9uQVA10g/AVI3O503SYFYzlLBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:02.086643Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.09118","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af24cdb0aef2bb8bf56773761b3da1287f762b3388458dd07e21eed50b0dd044","sha256:a01c35b41dd047aac6bcba5aa6a014f80c797901b056a273eec1f257beeb9a66"],"state_sha256":"5a66cd515dc63a8d57799166977199b7c2aba3c2f6304d641986f64646850f03"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hLmohwltQxqVK1bDrwPrEBgFsRCTltiKr5kE2LueXa7I7nuZdAggfQS842ADvI7m4Bt46J+pgxM+QVq3K1n2Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T16:39:42.313152Z","bundle_sha256":"98a6360d08cc1c4f02449eca96032ec412c7c5f736e379e7a516b257b2a7dee3"}}