{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4BOMORNFFBWSMU6EG6Q2IWKUHK","short_pith_number":"pith:4BOMORNF","canonical_record":{"source":{"id":"2509.06650","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-08T13:04:07Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"16b83112187768bf484acba5bdb286157bd6029f790f90994c520400147b613b","abstract_canon_sha256":"6437c3dc5bc3244f5902ff9ad172ceaa78af175d7982e643b0a47b1e04b55735"},"schema_version":"1.0"},"canonical_sha256":"e05cc745a5286d2653c437a1a459543a87e499b5dbfacab6e8e41a317c7de80f","source":{"kind":"arxiv","id":"2509.06650","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06650","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06650v1","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06650","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_12","alias_value":"4BOMORNFFBWS","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_16","alias_value":"4BOMORNFFBWSMU6E","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_8","alias_value":"4BOMORNF","created_at":"2026-07-05T12:06:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4BOMORNFFBWSMU6EG6Q2IWKUHK","target":"record","payload":{"canonical_record":{"source":{"id":"2509.06650","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-08T13:04:07Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"16b83112187768bf484acba5bdb286157bd6029f790f90994c520400147b613b","abstract_canon_sha256":"6437c3dc5bc3244f5902ff9ad172ceaa78af175d7982e643b0a47b1e04b55735"},"schema_version":"1.0"},"canonical_sha256":"e05cc745a5286d2653c437a1a459543a87e499b5dbfacab6e8e41a317c7de80f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:39.673675Z","signature_b64":"pzPpzaLzfj6VRsO3QI+ySOm7rAZURX0Lvm5GYUHiRe054OTvmNRLiRcP76o4JiU4a9y9oRrSMVN5jfSnyhArAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e05cc745a5286d2653c437a1a459543a87e499b5dbfacab6e8e41a317c7de80f","last_reissued_at":"2026-07-05T12:06:39.673307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:39.673307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.06650","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":"2026-07-05T12:06:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"psyZLb1MVbFj3O8cQeKKkwaq1e6WKeJaij93796eOtNdsXNC695N1LbCIRAqFCXCSSrI64FsvCtwHWOen8qfDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:00:26.947235Z"},"content_sha256":"063bd4c3269465f011d9a2c6e096244c960965f0ba3d9205fe1dcb5265ac111d","schema_version":"1.0","event_id":"sha256:063bd4c3269465f011d9a2c6e096244c960965f0ba3d9205fe1dcb5265ac111d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4BOMORNFFBWSMU6EG6Q2IWKUHK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Domain-Aware RAG: MoL-Enhanced RL for Efficient Training and Scalable Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Hao Lin, Jie Lin, Jingxue Chen, Peitong Xie, Qianchun Lu, Qingkun Tang","submitted_at":"2025-09-08T13:04:07Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems rely heavily on the retrieval stage, particularly the coarse-ranking process. Existing coarse-ranking optimization approaches often struggle to balance domain-specific knowledge learning with query enhencement, resulting in suboptimal retrieval performance. To address this challenge, we propose MoLER, a domain-aware RAG method that uses MoL-Enhanced Reinforcement Learning to optimize retrieval. MoLER has a two-stage pipeline: a continual pre-training (CPT) phase using a Mixture of Losses (MoL) to balance domain-specific knowledge with general langua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06650","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/2509.06650/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":"2026-07-05T12:06:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OCef2CINv5C2PJXLvoWO+TQ7LFNOcx8u3PbVktJ5pbcb2BvsVkXdRFCts+6AFUpmWm3IzxyMjRGQa1Nndy15BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:00:26.948078Z"},"content_sha256":"8ec76f79241e6b52754efd1cecdd31de352e9ec6ea7030bfdc87891314ab7897","schema_version":"1.0","event_id":"sha256:8ec76f79241e6b52754efd1cecdd31de352e9ec6ea7030bfdc87891314ab7897"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4BOMORNFFBWSMU6EG6Q2IWKUHK/bundle.json","state_url":"https://pith.science/pith/4BOMORNFFBWSMU6EG6Q2IWKUHK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4BOMORNFFBWSMU6EG6Q2IWKUHK/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":"2026-08-06T05:00:26Z","links":{"resolver":"https://pith.science/pith/4BOMORNFFBWSMU6EG6Q2IWKUHK","bundle":"https://pith.science/pith/4BOMORNFFBWSMU6EG6Q2IWKUHK/bundle.json","state":"https://pith.science/pith/4BOMORNFFBWSMU6EG6Q2IWKUHK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4BOMORNFFBWSMU6EG6Q2IWKUHK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4BOMORNFFBWSMU6EG6Q2IWKUHK","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":"6437c3dc5bc3244f5902ff9ad172ceaa78af175d7982e643b0a47b1e04b55735","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-08T13:04:07Z","title_canon_sha256":"16b83112187768bf484acba5bdb286157bd6029f790f90994c520400147b613b"},"schema_version":"1.0","source":{"id":"2509.06650","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06650","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06650v1","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06650","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_12","alias_value":"4BOMORNFFBWS","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_16","alias_value":"4BOMORNFFBWSMU6E","created_at":"2026-07-05T12:06:39Z"},{"alias_kind":"pith_short_8","alias_value":"4BOMORNF","created_at":"2026-07-05T12:06:39Z"}],"graph_snapshots":[{"event_id":"sha256:8ec76f79241e6b52754efd1cecdd31de352e9ec6ea7030bfdc87891314ab7897","target":"graph","created_at":"2026-07-05T12:06:39Z","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/2509.06650/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems rely heavily on the retrieval stage, particularly the coarse-ranking process. Existing coarse-ranking optimization approaches often struggle to balance domain-specific knowledge learning with query enhencement, resulting in suboptimal retrieval performance. To address this challenge, we propose MoLER, a domain-aware RAG method that uses MoL-Enhanced Reinforcement Learning to optimize retrieval. MoLER has a two-stage pipeline: a continual pre-training (CPT) phase using a Mixture of Losses (MoL) to balance domain-specific knowledge with general langua","authors_text":"Hao Lin, Jie Lin, Jingxue Chen, Peitong Xie, Qianchun Lu, Qingkun Tang","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-08T13:04:07Z","title":"Domain-Aware RAG: MoL-Enhanced RL for Efficient Training and Scalable Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06650","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":"sha256:063bd4c3269465f011d9a2c6e096244c960965f0ba3d9205fe1dcb5265ac111d","target":"record","created_at":"2026-07-05T12:06:39Z","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":"6437c3dc5bc3244f5902ff9ad172ceaa78af175d7982e643b0a47b1e04b55735","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-08T13:04:07Z","title_canon_sha256":"16b83112187768bf484acba5bdb286157bd6029f790f90994c520400147b613b"},"schema_version":"1.0","source":{"id":"2509.06650","kind":"arxiv","version":1}},"canonical_sha256":"e05cc745a5286d2653c437a1a459543a87e499b5dbfacab6e8e41a317c7de80f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e05cc745a5286d2653c437a1a459543a87e499b5dbfacab6e8e41a317c7de80f","first_computed_at":"2026-07-05T12:06:39.673307Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:39.673307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pzPpzaLzfj6VRsO3QI+ySOm7rAZURX0Lvm5GYUHiRe054OTvmNRLiRcP76o4JiU4a9y9oRrSMVN5jfSnyhArAg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:39.673675Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.06650","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:063bd4c3269465f011d9a2c6e096244c960965f0ba3d9205fe1dcb5265ac111d","sha256:8ec76f79241e6b52754efd1cecdd31de352e9ec6ea7030bfdc87891314ab7897"],"state_sha256":"50869728f70b301b37574db41b0788f46c9dd34e7c6558944f0dcf6c81e8a6b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"te3zeaZ3XazDO9iNuZsbSDxtIZg9Nx/81V7NtJT6OGt6R8MMgRLjwSSgtzdT+XpJWbA4tduNE3yixNSqK8/ZCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:00:26.954953Z","bundle_sha256":"eee2ffd2209da74f78117f59fc3bf480ba6c4494f5af2bacd80b936920c1ee24"}}