{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:U3DRX3PFCOHEQV7IL5EGNCW5ZN","short_pith_number":"pith:U3DRX3PF","canonical_record":{"source":{"id":"2505.01907","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-03T19:24:40Z","cross_cats_sorted":[],"title_canon_sha256":"7fd4be09bbf35f5d0a3955dca0ad840063512d38c72e3ecb04df30c054192670","abstract_canon_sha256":"1e139187da2248739cbdeaabfa0e1abe958532f3af8e29045737985f5b719b7a"},"schema_version":"1.0"},"canonical_sha256":"a6c71bede5138e4857e85f48668addcb5c52e2a7ae2cf10db9f323890eccc657","source":{"kind":"arxiv","id":"2505.01907","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.01907","created_at":"2026-07-05T11:33:04Z"},{"alias_kind":"arxiv_version","alias_value":"2505.01907v2","created_at":"2026-07-05T11:33:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01907","created_at":"2026-07-05T11:33:04Z"},{"alias_kind":"pith_short_12","alias_value":"U3DRX3PFCOHE","created_at":"2026-07-05T11:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"U3DRX3PFCOHEQV7I","created_at":"2026-07-05T11:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"U3DRX3PF","created_at":"2026-07-05T11:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:U3DRX3PFCOHEQV7IL5EGNCW5ZN","target":"record","payload":{"canonical_record":{"source":{"id":"2505.01907","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-03T19:24:40Z","cross_cats_sorted":[],"title_canon_sha256":"7fd4be09bbf35f5d0a3955dca0ad840063512d38c72e3ecb04df30c054192670","abstract_canon_sha256":"1e139187da2248739cbdeaabfa0e1abe958532f3af8e29045737985f5b719b7a"},"schema_version":"1.0"},"canonical_sha256":"a6c71bede5138e4857e85f48668addcb5c52e2a7ae2cf10db9f323890eccc657","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:04.983586Z","signature_b64":"ZD7d2W/BGZoFPNkZIzHtyRWG6bYry0HDTSN0kb9vZrYPEiLmaE3qvDu+6LCFNBS1Oo1j8O+A+7G+p8J0h6MRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6c71bede5138e4857e85f48668addcb5c52e2a7ae2cf10db9f323890eccc657","last_reissued_at":"2026-07-05T11:33:04.983133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:04.983133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.01907","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":"2026-07-05T11:33:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y2eXvmd+2R1komnZuHLZH2y5qgdajSZLwTJ7A1ImU9TbMqUETivBc8uVhHrzHgWVAJ96SfvnwluZ1qlynUDVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:17:23.172885Z"},"content_sha256":"5ea953c37d757358e3649b121c9b6564b136a16490bc7cd3b77d77a292d5d31d","schema_version":"1.0","event_id":"sha256:5ea953c37d757358e3649b121c9b6564b136a16490bc7cd3b77d77a292d5d31d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:U3DRX3PFCOHEQV7IL5EGNCW5ZN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Generalised and Adaptable Reinforcement Learning Stopping Method","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Mark Stevenson, Reem Bin-Hezam","submitted_at":"2025-05-03T19:24:40Z","abstract_excerpt":"This paper presents a Technology Assisted Review (TAR) stopping approach based on Reinforcement Learning (RL). Previous such approaches offered limited control over stopping behaviour, such as fixing the target recall and tradeoff between preferring to maximise recall or cost. These limitations are overcome by introducing a novel RL environment, GRLStop, that allows a single model to be applied to multiple target recalls, balances the recall/cost tradeoff and integrates a classifier. Experiments were carried out on six benchmark datasets (CLEF e-Health datasets 2017-9, TREC Total Recall, TREC "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01907","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/2505.01907/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":"2026-07-05T11:33:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QnMnqMTRAyTPZpE/7BTCiK0TJeEwfQzyznliIFR48GtLh8mt41BSrLJDZmKNu33c0bEumX47RL6x3+Sm9eO5Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:17:23.173522Z"},"content_sha256":"eb5ee56254eea9f8743345a626da1587e0a9251b8cdc280d5751da0e98ab7376","schema_version":"1.0","event_id":"sha256:eb5ee56254eea9f8743345a626da1587e0a9251b8cdc280d5751da0e98ab7376"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U3DRX3PFCOHEQV7IL5EGNCW5ZN/bundle.json","state_url":"https://pith.science/pith/U3DRX3PFCOHEQV7IL5EGNCW5ZN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U3DRX3PFCOHEQV7IL5EGNCW5ZN/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":"2026-08-22T09:17:23Z","links":{"resolver":"https://pith.science/pith/U3DRX3PFCOHEQV7IL5EGNCW5ZN","bundle":"https://pith.science/pith/U3DRX3PFCOHEQV7IL5EGNCW5ZN/bundle.json","state":"https://pith.science/pith/U3DRX3PFCOHEQV7IL5EGNCW5ZN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U3DRX3PFCOHEQV7IL5EGNCW5ZN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U3DRX3PFCOHEQV7IL5EGNCW5ZN","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":"1e139187da2248739cbdeaabfa0e1abe958532f3af8e29045737985f5b719b7a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-03T19:24:40Z","title_canon_sha256":"7fd4be09bbf35f5d0a3955dca0ad840063512d38c72e3ecb04df30c054192670"},"schema_version":"1.0","source":{"id":"2505.01907","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.01907","created_at":"2026-07-05T11:33:04Z"},{"alias_kind":"arxiv_version","alias_value":"2505.01907v2","created_at":"2026-07-05T11:33:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01907","created_at":"2026-07-05T11:33:04Z"},{"alias_kind":"pith_short_12","alias_value":"U3DRX3PFCOHE","created_at":"2026-07-05T11:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"U3DRX3PFCOHEQV7I","created_at":"2026-07-05T11:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"U3DRX3PF","created_at":"2026-07-05T11:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:eb5ee56254eea9f8743345a626da1587e0a9251b8cdc280d5751da0e98ab7376","target":"graph","created_at":"2026-07-05T11:33:04Z","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/2505.01907/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a Technology Assisted Review (TAR) stopping approach based on Reinforcement Learning (RL). Previous such approaches offered limited control over stopping behaviour, such as fixing the target recall and tradeoff between preferring to maximise recall or cost. These limitations are overcome by introducing a novel RL environment, GRLStop, that allows a single model to be applied to multiple target recalls, balances the recall/cost tradeoff and integrates a classifier. Experiments were carried out on six benchmark datasets (CLEF e-Health datasets 2017-9, TREC Total Recall, TREC ","authors_text":"Mark Stevenson, Reem Bin-Hezam","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-03T19:24:40Z","title":"A Generalised and Adaptable Reinforcement Learning Stopping Method"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01907","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":"sha256:5ea953c37d757358e3649b121c9b6564b136a16490bc7cd3b77d77a292d5d31d","target":"record","created_at":"2026-07-05T11:33:04Z","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":"1e139187da2248739cbdeaabfa0e1abe958532f3af8e29045737985f5b719b7a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-03T19:24:40Z","title_canon_sha256":"7fd4be09bbf35f5d0a3955dca0ad840063512d38c72e3ecb04df30c054192670"},"schema_version":"1.0","source":{"id":"2505.01907","kind":"arxiv","version":2}},"canonical_sha256":"a6c71bede5138e4857e85f48668addcb5c52e2a7ae2cf10db9f323890eccc657","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6c71bede5138e4857e85f48668addcb5c52e2a7ae2cf10db9f323890eccc657","first_computed_at":"2026-07-05T11:33:04.983133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:04.983133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZD7d2W/BGZoFPNkZIzHtyRWG6bYry0HDTSN0kb9vZrYPEiLmaE3qvDu+6LCFNBS1Oo1j8O+A+7G+p8J0h6MRDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:04.983586Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.01907","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ea953c37d757358e3649b121c9b6564b136a16490bc7cd3b77d77a292d5d31d","sha256:eb5ee56254eea9f8743345a626da1587e0a9251b8cdc280d5751da0e98ab7376"],"state_sha256":"ca9d8c7df2fe87515bafbc93c8c741135f1a1f8ef98ca920c50599b1a4286d2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AeIISIXqNEU6e+07e5XC8/iZ7SX9ut8P3LtjsXqo2Y2AN0BkhmYJzclJFaFlfIco5r+RSpzKPWXX7yUic0twBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T09:17:23.178213Z","bundle_sha256":"c142d069c368b3537e5d1227cf94ab80d30fba599d4b644d734fbde7f25715ce"}}