{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:FDCPCC6WOJVC7R3E6X4PQJOJLD","short_pith_number":"pith:FDCPCC6W","canonical_record":{"source":{"id":"1708.04378","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-08-15T01:53:12Z","cross_cats_sorted":[],"title_canon_sha256":"4d6c42b7a5cc3d170166dd2dd38d723eb5505729530960d477680b5063a6b1db","abstract_canon_sha256":"613cdf734931ddea932a7d7ff81ba2e26ab7096d2ac80c362a00dc75d51a41d6"},"schema_version":"1.0"},"canonical_sha256":"28c4f10bd6726a2fc764f5f8f825c958d89ba7f4e2c0a5ac169fb5f3ee185686","source":{"kind":"arxiv","id":"1708.04378","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.04378","created_at":"2026-05-18T00:37:59Z"},{"alias_kind":"arxiv_version","alias_value":"1708.04378v1","created_at":"2026-05-18T00:37:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.04378","created_at":"2026-05-18T00:37:59Z"},{"alias_kind":"pith_short_12","alias_value":"FDCPCC6WOJVC","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FDCPCC6WOJVC7R3E","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FDCPCC6W","created_at":"2026-05-18T12:31:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:FDCPCC6WOJVC7R3E6X4PQJOJLD","target":"record","payload":{"canonical_record":{"source":{"id":"1708.04378","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-08-15T01:53:12Z","cross_cats_sorted":[],"title_canon_sha256":"4d6c42b7a5cc3d170166dd2dd38d723eb5505729530960d477680b5063a6b1db","abstract_canon_sha256":"613cdf734931ddea932a7d7ff81ba2e26ab7096d2ac80c362a00dc75d51a41d6"},"schema_version":"1.0"},"canonical_sha256":"28c4f10bd6726a2fc764f5f8f825c958d89ba7f4e2c0a5ac169fb5f3ee185686","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:59.508506Z","signature_b64":"gCniaOVSmsQxhcF/AkwP3RWlCiFLsqZxH061sHRNrT4OLBSE2Hzt6nE/hvOeVqhEV6R6agDQUlhJnBuFgu46Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28c4f10bd6726a2fc764f5f8f825c958d89ba7f4e2c0a5ac169fb5f3ee185686","last_reissued_at":"2026-05-18T00:37:59.507887Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:59.507887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.04378","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":"2026-05-18T00:37:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZjKU3Ncm79CoUtqzg10B7TIBcv4xauKMhHk/Z5wVYR8Buc/oF62eywMWtgPq138LXZy8gFBiluEF0jxvES/XCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T11:06:02.479282Z"},"content_sha256":"e42fe16f88d98a76b115d7bddb07e60249097b42e8c1cdc27477df7def01e41d","schema_version":"1.0","event_id":"sha256:e42fe16f88d98a76b115d7bddb07e60249097b42e8c1cdc27477df7def01e41d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:FDCPCC6WOJVC7R3E6X4PQJOJLD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Learning Reward Functions from User Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Artem Grotov, Julia Kiseleva, Maarten de Rijke, Ziming Li","submitted_at":"2017-08-15T01:53:12Z","abstract_excerpt":"In the physical world, people have dynamic preferences, e.g., the same situation can lead to satisfaction for some humans and to frustration for others. Personalization is called for. The same observation holds for online behavior with interactive systems. It is natural to represent the behavior of users who are engaging with interactive systems such as a search engine or a recommender system, as a sequence of actions where each next action depends on the current situation and the user reward of taking a particular action. By and large, current online evaluation metrics for interactive systems"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.04378","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":"2026-05-18T00:37:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p9j8ImcsvrkqY1wgt5LZcxEGauAs8eQA0TdDLO+o6ptgnGdeccsGk6tvew9m7+mcg8Wq0Ji3TlxMWYct1ZXXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T11:06:02.479660Z"},"content_sha256":"11cc0c67aa93232dbe297e4c9028aaa9d849be0a11be410e54cafdfb2f8d4410","schema_version":"1.0","event_id":"sha256:11cc0c67aa93232dbe297e4c9028aaa9d849be0a11be410e54cafdfb2f8d4410"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FDCPCC6WOJVC7R3E6X4PQJOJLD/bundle.json","state_url":"https://pith.science/pith/FDCPCC6WOJVC7R3E6X4PQJOJLD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FDCPCC6WOJVC7R3E6X4PQJOJLD/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":"2026-06-02T11:06:02Z","links":{"resolver":"https://pith.science/pith/FDCPCC6WOJVC7R3E6X4PQJOJLD","bundle":"https://pith.science/pith/FDCPCC6WOJVC7R3E6X4PQJOJLD/bundle.json","state":"https://pith.science/pith/FDCPCC6WOJVC7R3E6X4PQJOJLD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FDCPCC6WOJVC7R3E6X4PQJOJLD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:FDCPCC6WOJVC7R3E6X4PQJOJLD","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":"613cdf734931ddea932a7d7ff81ba2e26ab7096d2ac80c362a00dc75d51a41d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-08-15T01:53:12Z","title_canon_sha256":"4d6c42b7a5cc3d170166dd2dd38d723eb5505729530960d477680b5063a6b1db"},"schema_version":"1.0","source":{"id":"1708.04378","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.04378","created_at":"2026-05-18T00:37:59Z"},{"alias_kind":"arxiv_version","alias_value":"1708.04378v1","created_at":"2026-05-18T00:37:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.04378","created_at":"2026-05-18T00:37:59Z"},{"alias_kind":"pith_short_12","alias_value":"FDCPCC6WOJVC","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_16","alias_value":"FDCPCC6WOJVC7R3E","created_at":"2026-05-18T12:31:15Z"},{"alias_kind":"pith_short_8","alias_value":"FDCPCC6W","created_at":"2026-05-18T12:31:15Z"}],"graph_snapshots":[{"event_id":"sha256:11cc0c67aa93232dbe297e4c9028aaa9d849be0a11be410e54cafdfb2f8d4410","target":"graph","created_at":"2026-05-18T00:37:59Z","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":"In the physical world, people have dynamic preferences, e.g., the same situation can lead to satisfaction for some humans and to frustration for others. Personalization is called for. The same observation holds for online behavior with interactive systems. It is natural to represent the behavior of users who are engaging with interactive systems such as a search engine or a recommender system, as a sequence of actions where each next action depends on the current situation and the user reward of taking a particular action. By and large, current online evaluation metrics for interactive systems","authors_text":"Artem Grotov, Julia Kiseleva, Maarten de Rijke, Ziming Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-08-15T01:53:12Z","title":"Towards Learning Reward Functions from User Interactions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.04378","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:e42fe16f88d98a76b115d7bddb07e60249097b42e8c1cdc27477df7def01e41d","target":"record","created_at":"2026-05-18T00:37:59Z","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":"613cdf734931ddea932a7d7ff81ba2e26ab7096d2ac80c362a00dc75d51a41d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-08-15T01:53:12Z","title_canon_sha256":"4d6c42b7a5cc3d170166dd2dd38d723eb5505729530960d477680b5063a6b1db"},"schema_version":"1.0","source":{"id":"1708.04378","kind":"arxiv","version":1}},"canonical_sha256":"28c4f10bd6726a2fc764f5f8f825c958d89ba7f4e2c0a5ac169fb5f3ee185686","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28c4f10bd6726a2fc764f5f8f825c958d89ba7f4e2c0a5ac169fb5f3ee185686","first_computed_at":"2026-05-18T00:37:59.507887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:37:59.507887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gCniaOVSmsQxhcF/AkwP3RWlCiFLsqZxH061sHRNrT4OLBSE2Hzt6nE/hvOeVqhEV6R6agDQUlhJnBuFgu46Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:37:59.508506Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.04378","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e42fe16f88d98a76b115d7bddb07e60249097b42e8c1cdc27477df7def01e41d","sha256:11cc0c67aa93232dbe297e4c9028aaa9d849be0a11be410e54cafdfb2f8d4410"],"state_sha256":"8fad0c609a887a926c5273da28aefaae08db9875e91af7da6b5da640ae889a84"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x78wXwVHDUhc0LaBRcnxngGpH75vJL28aEM+BggipkgCzSdj4pZLPRAi5dO/unKRf1z/aqAfnWfJ7ODNafG2Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T11:06:02.481580Z","bundle_sha256":"dd318eb84cc3c6799c16f0d155106e2807a9d686c34613c79bae7bd2e540fcdc"}}