{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:P37DUGNAX3M3HJ22KK22DCRRRL","short_pith_number":"pith:P37DUGNA","canonical_record":{"source":{"id":"2503.00223","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-02-28T22:16:42Z","cross_cats_sorted":[],"title_canon_sha256":"baf4740d7e516f34cae257d787fd365df33f69fd669e94669c8da263f995b6eb","abstract_canon_sha256":"22a5d9ea0dc6116470453ac327c3a4b0f028cdffb6d9c48504489279290420a7"},"schema_version":"1.0"},"canonical_sha256":"7efe3a19a0bed9b3a75a52b5a18a318ac4f10003a5090270d7f4b200a2ed8672","source":{"kind":"arxiv","id":"2503.00223","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00223","created_at":"2026-07-05T10:47:57Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00223v3","created_at":"2026-07-05T10:47:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00223","created_at":"2026-07-05T10:47:57Z"},{"alias_kind":"pith_short_12","alias_value":"P37DUGNAX3M3","created_at":"2026-07-05T10:47:57Z"},{"alias_kind":"pith_short_16","alias_value":"P37DUGNAX3M3HJ22","created_at":"2026-07-05T10:47:57Z"},{"alias_kind":"pith_short_8","alias_value":"P37DUGNA","created_at":"2026-07-05T10:47:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:P37DUGNAX3M3HJ22KK22DCRRRL","target":"record","payload":{"canonical_record":{"source":{"id":"2503.00223","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-02-28T22:16:42Z","cross_cats_sorted":[],"title_canon_sha256":"baf4740d7e516f34cae257d787fd365df33f69fd669e94669c8da263f995b6eb","abstract_canon_sha256":"22a5d9ea0dc6116470453ac327c3a4b0f028cdffb6d9c48504489279290420a7"},"schema_version":"1.0"},"canonical_sha256":"7efe3a19a0bed9b3a75a52b5a18a318ac4f10003a5090270d7f4b200a2ed8672","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:57.458942Z","signature_b64":"rdTsAV+CK4lh3ZsRs9E1kOeU5A37lO/ar0N9Wdozh/Z+4C/TK844A4378LFrYytEW9m0PkLD2U0z3+05xiaAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7efe3a19a0bed9b3a75a52b5a18a318ac4f10003a5090270d7f4b200a2ed8672","last_reissued_at":"2026-07-05T10:47:57.458247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:57.458247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.00223","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":"2026-07-05T10:47:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3oty9HvN2g+0dCtGIW2y72JSwgoCDr/pZuTqcEvD4UXQul/TjYlrn9f7VbqMVsNN3wHBFm5P+/vGRSCDpKlvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:05:18.666813Z"},"content_sha256":"baf3a777c601f7120c32a8800447461b7b32439e1db9ed1b87437dfa49ca4dff","schema_version":"1.0","event_id":"sha256:baf3a777c601f7120c32a8800447461b7b32439e1db9ed1b87437dfa49ca4dff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:P37DUGNAX3M3HJ22KK22DCRRRL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jiacheng Lin, Jiawei Han, Jimeng Sun, Lang Cao, Pengcheng Jiang, Runchu Tian, SeongKu Kang, Zifeng Wang","submitted_at":"2025-02-28T22:16:42Z","abstract_excerpt":"Information retrieval systems are crucial for enabling effective access to large document collections. Recent approaches have leveraged Large Language Models (LLMs) to enhance retrieval performance through query augmentation, but often rely on expensive supervised learning or distillation techniques that require significant computational resources and hand-labeled data. We introduce DeepRetrieval, a reinforcement learning (RL) approach that trains LLMs for query generation through trial and error without supervised data (reference query). Using retrieval metrics as rewards, our system generate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00223","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.00223/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":"2026-07-05T10:47:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"67+C+c2IXfw+gEKVZfIc7TpjtZa+8hzgTEYtIuH9LwwJvJIq6zYWv9J0TxgPEE+g1rlIGbQK0XnTjNxrWzQVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:05:18.667529Z"},"content_sha256":"2b068c7554e15df496632f3610a9f311e67a196cfc05443ca28994122513f313","schema_version":"1.0","event_id":"sha256:2b068c7554e15df496632f3610a9f311e67a196cfc05443ca28994122513f313"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P37DUGNAX3M3HJ22KK22DCRRRL/bundle.json","state_url":"https://pith.science/pith/P37DUGNAX3M3HJ22KK22DCRRRL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P37DUGNAX3M3HJ22KK22DCRRRL/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":"2026-08-09T04:05:18Z","links":{"resolver":"https://pith.science/pith/P37DUGNAX3M3HJ22KK22DCRRRL","bundle":"https://pith.science/pith/P37DUGNAX3M3HJ22KK22DCRRRL/bundle.json","state":"https://pith.science/pith/P37DUGNAX3M3HJ22KK22DCRRRL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P37DUGNAX3M3HJ22KK22DCRRRL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P37DUGNAX3M3HJ22KK22DCRRRL","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":"22a5d9ea0dc6116470453ac327c3a4b0f028cdffb6d9c48504489279290420a7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-02-28T22:16:42Z","title_canon_sha256":"baf4740d7e516f34cae257d787fd365df33f69fd669e94669c8da263f995b6eb"},"schema_version":"1.0","source":{"id":"2503.00223","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00223","created_at":"2026-07-05T10:47:57Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00223v3","created_at":"2026-07-05T10:47:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00223","created_at":"2026-07-05T10:47:57Z"},{"alias_kind":"pith_short_12","alias_value":"P37DUGNAX3M3","created_at":"2026-07-05T10:47:57Z"},{"alias_kind":"pith_short_16","alias_value":"P37DUGNAX3M3HJ22","created_at":"2026-07-05T10:47:57Z"},{"alias_kind":"pith_short_8","alias_value":"P37DUGNA","created_at":"2026-07-05T10:47:57Z"}],"graph_snapshots":[{"event_id":"sha256:2b068c7554e15df496632f3610a9f311e67a196cfc05443ca28994122513f313","target":"graph","created_at":"2026-07-05T10:47:57Z","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/2503.00223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Information retrieval systems are crucial for enabling effective access to large document collections. Recent approaches have leveraged Large Language Models (LLMs) to enhance retrieval performance through query augmentation, but often rely on expensive supervised learning or distillation techniques that require significant computational resources and hand-labeled data. We introduce DeepRetrieval, a reinforcement learning (RL) approach that trains LLMs for query generation through trial and error without supervised data (reference query). Using retrieval metrics as rewards, our system generate","authors_text":"Jiacheng Lin, Jiawei Han, Jimeng Sun, Lang Cao, Pengcheng Jiang, Runchu Tian, SeongKu Kang, Zifeng Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-02-28T22:16:42Z","title":"DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00223","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:baf3a777c601f7120c32a8800447461b7b32439e1db9ed1b87437dfa49ca4dff","target":"record","created_at":"2026-07-05T10:47:57Z","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":"22a5d9ea0dc6116470453ac327c3a4b0f028cdffb6d9c48504489279290420a7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-02-28T22:16:42Z","title_canon_sha256":"baf4740d7e516f34cae257d787fd365df33f69fd669e94669c8da263f995b6eb"},"schema_version":"1.0","source":{"id":"2503.00223","kind":"arxiv","version":3}},"canonical_sha256":"7efe3a19a0bed9b3a75a52b5a18a318ac4f10003a5090270d7f4b200a2ed8672","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7efe3a19a0bed9b3a75a52b5a18a318ac4f10003a5090270d7f4b200a2ed8672","first_computed_at":"2026-07-05T10:47:57.458247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:57.458247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rdTsAV+CK4lh3ZsRs9E1kOeU5A37lO/ar0N9Wdozh/Z+4C/TK844A4378LFrYytEW9m0PkLD2U0z3+05xiaAAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:57.458942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.00223","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:baf3a777c601f7120c32a8800447461b7b32439e1db9ed1b87437dfa49ca4dff","sha256:2b068c7554e15df496632f3610a9f311e67a196cfc05443ca28994122513f313"],"state_sha256":"6a2fdd5a416b55cd11b84590c9bf79c59161bf0aa14a652d0e214bd3affb150e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g5aFbYzbdIzLqYEwAwYYI1oXoH4Iyc9OO1CzFTxCADQ4tHU22ZX4Pa8v1CjBKCaGBlV8JY9o39bEKrF/mCzcCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:05:18.672860Z","bundle_sha256":"5b09aa1af365cdb8292caff78105b74907c23e3990748c4521614a80d5d07cf8"}}