{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z5BE5BBNTHX6HDQUY5S7OYZO7C","short_pith_number":"pith:Z5BE5BBN","schema_version":"1.0","canonical_sha256":"cf424e842d99efe38e14c765f7632ef8b249dbb891219b8cdcf0a304561d1e3e","source":{"kind":"arxiv","id":"2410.11315","version":1},"attestation_state":"computed","paper":{"title":"SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baotian Hu, Boren Hu, Dongfang Li, Min Zhang, Xinping Zhao, Yan Zhong, Yibin Chen","submitted_at":"2024-10-15T06:26:24Z","abstract_excerpt":"Recent studies in Retrieval-Augmented Generation (RAG) have investigated extracting evidence from retrieved passages to reduce computational costs and enhance the final RAG performance, yet it remains challenging. Existing methods heavily rely on heuristic-based augmentation, encountering several issues: (1) Poor generalization due to hand-crafted context filtering; (2) Semantics deficiency due to rule-based context chunking; (3) Skewed length due to sentence-wise filter learning. To address these issues, we propose a model-based evidence extraction learning framework, SEER, optimizing a vanil"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.11315","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T06:26:24Z","cross_cats_sorted":[],"title_canon_sha256":"08f16da53e53c1106d49e21669d73d3f6aea6e0e6974c11b2ea055e9b694c720","abstract_canon_sha256":"80d2294de37d42b28268b57dee78a635d980813bcc9475cdf3fea5b22cee58dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:51.641874Z","signature_b64":"wWeLpq+vy6MRhbpgrKmU1KriqKRARdc0017aRLMhFFsuK92KHtNtBTk3265kREyfaTN+29YYkx14wtgDngOPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf424e842d99efe38e14c765f7632ef8b249dbb891219b8cdcf0a304561d1e3e","last_reissued_at":"2026-07-05T09:20:51.641286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:51.641286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baotian Hu, Boren Hu, Dongfang Li, Min Zhang, Xinping Zhao, Yan Zhong, Yibin Chen","submitted_at":"2024-10-15T06:26:24Z","abstract_excerpt":"Recent studies in Retrieval-Augmented Generation (RAG) have investigated extracting evidence from retrieved passages to reduce computational costs and enhance the final RAG performance, yet it remains challenging. Existing methods heavily rely on heuristic-based augmentation, encountering several issues: (1) Poor generalization due to hand-crafted context filtering; (2) Semantics deficiency due to rule-based context chunking; (3) Skewed length due to sentence-wise filter learning. To address these issues, we propose a model-based evidence extraction learning framework, SEER, optimizing a vanil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11315","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/2410.11315/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.11315","created_at":"2026-07-05T09:20:51.641369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11315v1","created_at":"2026-07-05T09:20:51.641369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11315","created_at":"2026-07-05T09:20:51.641369+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5BE5BBNTHX6","created_at":"2026-07-05T09:20:51.641369+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5BE5BBNTHX6HDQU","created_at":"2026-07-05T09:20:51.641369+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5BE5BBN","created_at":"2026-07-05T09:20:51.641369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04066","citing_title":"Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning","ref_index":288,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z5BE5BBNTHX6HDQUY5S7OYZO7C","json":"https://pith.science/pith/Z5BE5BBNTHX6HDQUY5S7OYZO7C.json","graph_json":"https://pith.science/api/pith-number/Z5BE5BBNTHX6HDQUY5S7OYZO7C/graph.json","events_json":"https://pith.science/api/pith-number/Z5BE5BBNTHX6HDQUY5S7OYZO7C/events.json","paper":"https://pith.science/paper/Z5BE5BBN"},"agent_actions":{"view_html":"https://pith.science/pith/Z5BE5BBNTHX6HDQUY5S7OYZO7C","download_json":"https://pith.science/pith/Z5BE5BBNTHX6HDQUY5S7OYZO7C.json","view_paper":"https://pith.science/paper/Z5BE5BBN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11315&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5BE5BBNTHX6HDQUY5S7OYZO7C/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5BE5BBNTHX6HDQUY5S7OYZO7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5BE5BBNTHX6HDQUY5S7OYZO7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5BE5BBNTHX6HDQUY5S7OYZO7C/action/storage_attestation","attest_author":"https://pith.science/pith/Z5BE5BBNTHX6HDQUY5S7OYZO7C/action/author_attestation","sign_citation":"https://pith.science/pith/Z5BE5BBNTHX6HDQUY5S7OYZO7C/action/citation_signature","submit_replication":"https://pith.science/pith/Z5BE5BBNTHX6HDQUY5S7OYZO7C/action/replication_record"}},"created_at":"2026-07-05T09:20:51.641369+00:00","updated_at":"2026-07-05T09:20:51.641369+00:00"}