{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:64CJM7CGGG4IRC4HWP4RDUJTPW","short_pith_number":"pith:64CJM7CG","canonical_record":{"source":{"id":"1910.10410","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-10-23T08:32:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d47b937ed518acf30aa4559fba2f4189ed37daaf6b7a0bbcb5ade61eda2536dd","abstract_canon_sha256":"5d3b63a0d2431031dcd40ef46577026a5ee963dec9842fd2e268875720359f61"},"schema_version":"1.0"},"canonical_sha256":"f704967c4631b8888b87b3f911d1337db141269c1c1d25174e9142585a388a51","source":{"kind":"arxiv","id":"1910.10410","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.10410","created_at":"2026-07-05T00:14:24Z"},{"alias_kind":"arxiv_version","alias_value":"1910.10410v1","created_at":"2026-07-05T00:14:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.10410","created_at":"2026-07-05T00:14:24Z"},{"alias_kind":"pith_short_12","alias_value":"64CJM7CGGG4I","created_at":"2026-07-05T00:14:24Z"},{"alias_kind":"pith_short_16","alias_value":"64CJM7CGGG4IRC4H","created_at":"2026-07-05T00:14:24Z"},{"alias_kind":"pith_short_8","alias_value":"64CJM7CG","created_at":"2026-07-05T00:14:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:64CJM7CGGG4IRC4HWP4RDUJTPW","target":"record","payload":{"canonical_record":{"source":{"id":"1910.10410","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-10-23T08:32:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d47b937ed518acf30aa4559fba2f4189ed37daaf6b7a0bbcb5ade61eda2536dd","abstract_canon_sha256":"5d3b63a0d2431031dcd40ef46577026a5ee963dec9842fd2e268875720359f61"},"schema_version":"1.0"},"canonical_sha256":"f704967c4631b8888b87b3f911d1337db141269c1c1d25174e9142585a388a51","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:14:24.652372Z","signature_b64":"vfceemUZyc9bHEP/I6WeytvZ8HtgmhGO7EcbO9H1t/2ivzNrNp/tnlN295HT5ubAZKEBANpGucDL0dW/kGUsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f704967c4631b8888b87b3f911d1337db141269c1c1d25174e9142585a388a51","last_reissued_at":"2026-07-05T00:14:24.651966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:14:24.651966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.10410","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":"2026-07-05T00:14:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3xuK7IW4G/CqEdd4gHTn0WzyK+25JAJx9FDYdBJ0MN6QJX8lFiiOfRTQv4euEKW0RyPkjVb2L91AxvEZBLf3Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:36:42.946407Z"},"content_sha256":"56d32fefe4e0986a180d3f694d2875fc84d8949a4bc59d3a528e14ff40a3259b","schema_version":"1.0","event_id":"sha256:56d32fefe4e0986a180d3f694d2875fc84d8949a4bc59d3a528e14ff40a3259b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:64CJM7CGGG4IRC4HWP4RDUJTPW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BanditRank: Learning to Rank Using Contextual Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Phanideep Gampa, Sumio Fujita","submitted_at":"2019-10-23T08:32:14Z","abstract_excerpt":"We propose an extensible deep learning method that uses reinforcement learning to train neural networks for offline ranking in information retrieval (IR). We call our method BanditRank as it treats ranking as a contextual bandit problem. In the domain of learning to rank for IR, current deep learning models are trained on objective functions different from the measures they are evaluated on. Since most evaluation measures are discrete quantities, they cannot be leveraged by directly using gradient descent algorithms without an approximation. BanditRank bridges this gap by directly optimizing a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.10410","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/1910.10410/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":"2026-07-05T00:14:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oqQVkC8WbHCvaDVDjhwWCBTEMKiPL5aTNobN0Lv+0+ER66wMTlGAqubWR8GIHcyNfy/PjmF2TU54hwquVXSIDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:36:42.946777Z"},"content_sha256":"9b733721004d2d1fe3906273ad862bd17d0e800d6ad51260d584b78f39d04e5b","schema_version":"1.0","event_id":"sha256:9b733721004d2d1fe3906273ad862bd17d0e800d6ad51260d584b78f39d04e5b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/64CJM7CGGG4IRC4HWP4RDUJTPW/bundle.json","state_url":"https://pith.science/pith/64CJM7CGGG4IRC4HWP4RDUJTPW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/64CJM7CGGG4IRC4HWP4RDUJTPW/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":"2026-07-07T08:36:42Z","links":{"resolver":"https://pith.science/pith/64CJM7CGGG4IRC4HWP4RDUJTPW","bundle":"https://pith.science/pith/64CJM7CGGG4IRC4HWP4RDUJTPW/bundle.json","state":"https://pith.science/pith/64CJM7CGGG4IRC4HWP4RDUJTPW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/64CJM7CGGG4IRC4HWP4RDUJTPW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:64CJM7CGGG4IRC4HWP4RDUJTPW","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":"5d3b63a0d2431031dcd40ef46577026a5ee963dec9842fd2e268875720359f61","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-10-23T08:32:14Z","title_canon_sha256":"d47b937ed518acf30aa4559fba2f4189ed37daaf6b7a0bbcb5ade61eda2536dd"},"schema_version":"1.0","source":{"id":"1910.10410","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.10410","created_at":"2026-07-05T00:14:24Z"},{"alias_kind":"arxiv_version","alias_value":"1910.10410v1","created_at":"2026-07-05T00:14:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.10410","created_at":"2026-07-05T00:14:24Z"},{"alias_kind":"pith_short_12","alias_value":"64CJM7CGGG4I","created_at":"2026-07-05T00:14:24Z"},{"alias_kind":"pith_short_16","alias_value":"64CJM7CGGG4IRC4H","created_at":"2026-07-05T00:14:24Z"},{"alias_kind":"pith_short_8","alias_value":"64CJM7CG","created_at":"2026-07-05T00:14:24Z"}],"graph_snapshots":[{"event_id":"sha256:9b733721004d2d1fe3906273ad862bd17d0e800d6ad51260d584b78f39d04e5b","target":"graph","created_at":"2026-07-05T00:14:24Z","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/1910.10410/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose an extensible deep learning method that uses reinforcement learning to train neural networks for offline ranking in information retrieval (IR). We call our method BanditRank as it treats ranking as a contextual bandit problem. In the domain of learning to rank for IR, current deep learning models are trained on objective functions different from the measures they are evaluated on. Since most evaluation measures are discrete quantities, they cannot be leveraged by directly using gradient descent algorithms without an approximation. BanditRank bridges this gap by directly optimizing a","authors_text":"Phanideep Gampa, Sumio Fujita","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-10-23T08:32:14Z","title":"BanditRank: Learning to Rank Using Contextual Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.10410","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":"sha256:56d32fefe4e0986a180d3f694d2875fc84d8949a4bc59d3a528e14ff40a3259b","target":"record","created_at":"2026-07-05T00:14:24Z","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":"5d3b63a0d2431031dcd40ef46577026a5ee963dec9842fd2e268875720359f61","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-10-23T08:32:14Z","title_canon_sha256":"d47b937ed518acf30aa4559fba2f4189ed37daaf6b7a0bbcb5ade61eda2536dd"},"schema_version":"1.0","source":{"id":"1910.10410","kind":"arxiv","version":1}},"canonical_sha256":"f704967c4631b8888b87b3f911d1337db141269c1c1d25174e9142585a388a51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f704967c4631b8888b87b3f911d1337db141269c1c1d25174e9142585a388a51","first_computed_at":"2026-07-05T00:14:24.651966Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:14:24.651966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vfceemUZyc9bHEP/I6WeytvZ8HtgmhGO7EcbO9H1t/2ivzNrNp/tnlN295HT5ubAZKEBANpGucDL0dW/kGUsDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:14:24.652372Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.10410","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56d32fefe4e0986a180d3f694d2875fc84d8949a4bc59d3a528e14ff40a3259b","sha256:9b733721004d2d1fe3906273ad862bd17d0e800d6ad51260d584b78f39d04e5b"],"state_sha256":"24ab57f030076e92748f402fab9e69529527293f07435e963b7936298c2346a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oWYoe3dNGUlGkfGjvd2PwcjfdQsJvLcCjC1jWT5SwbUuDAeNdn17TZoY66Oo95C2F7ddbBU0TEo5B87X8u9YDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:36:42.948642Z","bundle_sha256":"5a6972267c9d18cec3cb6b7e8907f912a681f2f9ecc476645ff547c4133d546e"}}