{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PNROW6HO7IBPMWNBCCAHPJEW6K","short_pith_number":"pith:PNROW6HO","canonical_record":{"source":{"id":"2106.00589","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-01T15:58:05Z","cross_cats_sorted":[],"title_canon_sha256":"8920464acffe7bc8090417dd16647e11f936bc8d9f4ab3dcf738ffe10bc0d636","abstract_canon_sha256":"362762cb50ad25d5b3b7d1c2fc264989612f25def45f14092cc8b2651a4ee0f6"},"schema_version":"1.0"},"canonical_sha256":"7b62eb78eefa02f659a1108077a496f2a4e072bf1065ac3c22d7f13199bad81d","source":{"kind":"arxiv","id":"2106.00589","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.00589","created_at":"2026-07-05T03:14:35Z"},{"alias_kind":"arxiv_version","alias_value":"2106.00589v2","created_at":"2026-07-05T03:14:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00589","created_at":"2026-07-05T03:14:35Z"},{"alias_kind":"pith_short_12","alias_value":"PNROW6HO7IBP","created_at":"2026-07-05T03:14:35Z"},{"alias_kind":"pith_short_16","alias_value":"PNROW6HO7IBPMWNB","created_at":"2026-07-05T03:14:35Z"},{"alias_kind":"pith_short_8","alias_value":"PNROW6HO","created_at":"2026-07-05T03:14:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PNROW6HO7IBPMWNBCCAHPJEW6K","target":"record","payload":{"canonical_record":{"source":{"id":"2106.00589","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-01T15:58:05Z","cross_cats_sorted":[],"title_canon_sha256":"8920464acffe7bc8090417dd16647e11f936bc8d9f4ab3dcf738ffe10bc0d636","abstract_canon_sha256":"362762cb50ad25d5b3b7d1c2fc264989612f25def45f14092cc8b2651a4ee0f6"},"schema_version":"1.0"},"canonical_sha256":"7b62eb78eefa02f659a1108077a496f2a4e072bf1065ac3c22d7f13199bad81d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:14:35.019687Z","signature_b64":"g0o/SiTQCLe/RZNeg3q5zNfesEfDwthZc0qa76nVw73wO7Qz7IgUMtH9KEEQXxePkZZiUg9WQBqLUwW+ekffBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b62eb78eefa02f659a1108077a496f2a4e072bf1065ac3c22d7f13199bad81d","last_reissued_at":"2026-07-05T03:14:35.018768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:14:35.018768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.00589","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:14:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"thlmbaVejpzgmT9+L2ZF5uuAd8rO7/ytB+YX1l2kagjRFFPf6RykbiMvfdSUD3Dl5tBRNOsKM6pakcmbR/TuAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:46:48.180029Z"},"content_sha256":"dd7fcf8166ffeb3a5f2741eba29b51369841417092daed6f97f6c4f4ff2d5284","schema_version":"1.0","event_id":"sha256:dd7fcf8166ffeb3a5f2741eba29b51369841417092daed6f97f6c4f4ff2d5284"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PNROW6HO7IBPMWNBCCAHPJEW6K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Long-Term Metrics in Recommendation Systems using Short-Horizon Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adith Swaminathan, Bogdan Mazoure, Doina Precup, Paul Mineiro, Pavithra Srinath, Reza Sharifi Sedeh","submitted_at":"2021-06-01T15:58:05Z","abstract_excerpt":"We study session-based recommendation scenarios where we want to recommend items to users during sequential interactions to improve their long-term utility. Optimizing a long-term metric is challenging because the learning signal (whether the recommendations achieved their desired goals) is delayed and confounded by other user interactions with the system. Targeting immediately measurable proxies such as clicks can lead to suboptimal recommendations due to misalignment with the long-term metric. We develop a new reinforcement learning algorithm called Short Horizon Policy Improvement (SHPI) th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00589","kind":"arxiv","version":2},"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/2106.00589/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":"2026-07-05T03:14:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EjT9XE6OiRvnen1ti+7Da/f85aTUpPJ7lg10SuZ3wx2X0poX5+DwtlyVYu4RivvTGhSZwEt44RF7/cUZJC8aAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:46:48.180568Z"},"content_sha256":"c16d1ca1de55707ac15f38eaca7ace4a3aa4dc48cbd5fb831eef3d4597345659","schema_version":"1.0","event_id":"sha256:c16d1ca1de55707ac15f38eaca7ace4a3aa4dc48cbd5fb831eef3d4597345659"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PNROW6HO7IBPMWNBCCAHPJEW6K/bundle.json","state_url":"https://pith.science/pith/PNROW6HO7IBPMWNBCCAHPJEW6K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PNROW6HO7IBPMWNBCCAHPJEW6K/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":"2026-08-06T06:46:48Z","links":{"resolver":"https://pith.science/pith/PNROW6HO7IBPMWNBCCAHPJEW6K","bundle":"https://pith.science/pith/PNROW6HO7IBPMWNBCCAHPJEW6K/bundle.json","state":"https://pith.science/pith/PNROW6HO7IBPMWNBCCAHPJEW6K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PNROW6HO7IBPMWNBCCAHPJEW6K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PNROW6HO7IBPMWNBCCAHPJEW6K","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":"362762cb50ad25d5b3b7d1c2fc264989612f25def45f14092cc8b2651a4ee0f6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-01T15:58:05Z","title_canon_sha256":"8920464acffe7bc8090417dd16647e11f936bc8d9f4ab3dcf738ffe10bc0d636"},"schema_version":"1.0","source":{"id":"2106.00589","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.00589","created_at":"2026-07-05T03:14:35Z"},{"alias_kind":"arxiv_version","alias_value":"2106.00589v2","created_at":"2026-07-05T03:14:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00589","created_at":"2026-07-05T03:14:35Z"},{"alias_kind":"pith_short_12","alias_value":"PNROW6HO7IBP","created_at":"2026-07-05T03:14:35Z"},{"alias_kind":"pith_short_16","alias_value":"PNROW6HO7IBPMWNB","created_at":"2026-07-05T03:14:35Z"},{"alias_kind":"pith_short_8","alias_value":"PNROW6HO","created_at":"2026-07-05T03:14:35Z"}],"graph_snapshots":[{"event_id":"sha256:c16d1ca1de55707ac15f38eaca7ace4a3aa4dc48cbd5fb831eef3d4597345659","target":"graph","created_at":"2026-07-05T03:14:35Z","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/2106.00589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study session-based recommendation scenarios where we want to recommend items to users during sequential interactions to improve their long-term utility. Optimizing a long-term metric is challenging because the learning signal (whether the recommendations achieved their desired goals) is delayed and confounded by other user interactions with the system. Targeting immediately measurable proxies such as clicks can lead to suboptimal recommendations due to misalignment with the long-term metric. We develop a new reinforcement learning algorithm called Short Horizon Policy Improvement (SHPI) th","authors_text":"Adith Swaminathan, Bogdan Mazoure, Doina Precup, Paul Mineiro, Pavithra Srinath, Reza Sharifi Sedeh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-01T15:58:05Z","title":"Improving Long-Term Metrics in Recommendation Systems using Short-Horizon Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00589","kind":"arxiv","version":2},"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:dd7fcf8166ffeb3a5f2741eba29b51369841417092daed6f97f6c4f4ff2d5284","target":"record","created_at":"2026-07-05T03:14:35Z","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":"362762cb50ad25d5b3b7d1c2fc264989612f25def45f14092cc8b2651a4ee0f6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-01T15:58:05Z","title_canon_sha256":"8920464acffe7bc8090417dd16647e11f936bc8d9f4ab3dcf738ffe10bc0d636"},"schema_version":"1.0","source":{"id":"2106.00589","kind":"arxiv","version":2}},"canonical_sha256":"7b62eb78eefa02f659a1108077a496f2a4e072bf1065ac3c22d7f13199bad81d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b62eb78eefa02f659a1108077a496f2a4e072bf1065ac3c22d7f13199bad81d","first_computed_at":"2026-07-05T03:14:35.018768Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:14:35.018768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g0o/SiTQCLe/RZNeg3q5zNfesEfDwthZc0qa76nVw73wO7Qz7IgUMtH9KEEQXxePkZZiUg9WQBqLUwW+ekffBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:14:35.019687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.00589","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd7fcf8166ffeb3a5f2741eba29b51369841417092daed6f97f6c4f4ff2d5284","sha256:c16d1ca1de55707ac15f38eaca7ace4a3aa4dc48cbd5fb831eef3d4597345659"],"state_sha256":"7a44cc9122b02b58e1e2070578055379d726a964c8d528a64fab32d36be2b6c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GalpSGXN3dD38LrzT4HapCAGCG7JY6EoXXEDdiE30COKpkOUcSc0fMN0NECA1ZEzb7xNkgZCVxm+sEj8ZnO1Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:46:48.186110Z","bundle_sha256":"a6ba5867c6efe84fc9c0d8e86017309d3d07592f507cb6e7639bded7f5d9895e"}}