{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IWE72NPD6XCKZZ2LDNRN32RR3M","short_pith_number":"pith:IWE72NPD","schema_version":"1.0","canonical_sha256":"4589fd35e3f5c4ace74b1b62ddea31db3fb330eafda71eafb2af6b336a74a62e","source":{"kind":"arxiv","id":"2412.11404","version":1},"attestation_state":"computed","paper":{"title":"Attention with Dependency Parsing Augmentation for Fine-Grained Attribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lvzhou Luo, Ping Luo, Qiang Ding, Yixuan Cao","submitted_at":"2024-12-16T03:12:13Z","abstract_excerpt":"To assist humans in efficiently validating RAG-generated content, developing a fine-grained attribution mechanism that provides supporting evidence from retrieved documents for every answer span is essential. Existing fine-grained attribution methods rely on model-internal similarity metrics between responses and documents, such as saliency scores and hidden state similarity. However, these approaches suffer from either high computational complexity or coarse-grained representations. Additionally, a common problem shared by the previous works is their reliance on decoder-only Transformers, lim"},"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":"2412.11404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T03:12:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"61711391fe4f8e72d144104fadbfd60aea6f14a8d7b69c19f0ffa6c5e0c51023","abstract_canon_sha256":"69e53c2f1b72c3605d6a39a68a54648c2d6ac08aa98d4683a752a2dc0383ef79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:32.364988Z","signature_b64":"BlvARFeyRdIy5QI80mRQPR4hID0+PCK+DsDlbIwQya78VfY5F/9kZ+fSOJx9sZWaIUZkBc65g7hjaom3TfmuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4589fd35e3f5c4ace74b1b62ddea31db3fb330eafda71eafb2af6b336a74a62e","last_reissued_at":"2026-07-05T09:49:32.364460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:32.364460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention with Dependency Parsing Augmentation for Fine-Grained Attribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lvzhou Luo, Ping Luo, Qiang Ding, Yixuan Cao","submitted_at":"2024-12-16T03:12:13Z","abstract_excerpt":"To assist humans in efficiently validating RAG-generated content, developing a fine-grained attribution mechanism that provides supporting evidence from retrieved documents for every answer span is essential. Existing fine-grained attribution methods rely on model-internal similarity metrics between responses and documents, such as saliency scores and hidden state similarity. However, these approaches suffer from either high computational complexity or coarse-grained representations. Additionally, a common problem shared by the previous works is their reliance on decoder-only Transformers, lim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11404","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/2412.11404/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":"2412.11404","created_at":"2026-07-05T09:49:32.364518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11404v1","created_at":"2026-07-05T09:49:32.364518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11404","created_at":"2026-07-05T09:49:32.364518+00:00"},{"alias_kind":"pith_short_12","alias_value":"IWE72NPD6XCK","created_at":"2026-07-05T09:49:32.364518+00:00"},{"alias_kind":"pith_short_16","alias_value":"IWE72NPD6XCKZZ2L","created_at":"2026-07-05T09:49:32.364518+00:00"},{"alias_kind":"pith_short_8","alias_value":"IWE72NPD","created_at":"2026-07-05T09:49:32.364518+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.05958","citing_title":"MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IWE72NPD6XCKZZ2LDNRN32RR3M","json":"https://pith.science/pith/IWE72NPD6XCKZZ2LDNRN32RR3M.json","graph_json":"https://pith.science/api/pith-number/IWE72NPD6XCKZZ2LDNRN32RR3M/graph.json","events_json":"https://pith.science/api/pith-number/IWE72NPD6XCKZZ2LDNRN32RR3M/events.json","paper":"https://pith.science/paper/IWE72NPD"},"agent_actions":{"view_html":"https://pith.science/pith/IWE72NPD6XCKZZ2LDNRN32RR3M","download_json":"https://pith.science/pith/IWE72NPD6XCKZZ2LDNRN32RR3M.json","view_paper":"https://pith.science/paper/IWE72NPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11404&json=true","fetch_graph":"https://pith.science/api/pith-number/IWE72NPD6XCKZZ2LDNRN32RR3M/graph.json","fetch_events":"https://pith.science/api/pith-number/IWE72NPD6XCKZZ2LDNRN32RR3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IWE72NPD6XCKZZ2LDNRN32RR3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IWE72NPD6XCKZZ2LDNRN32RR3M/action/storage_attestation","attest_author":"https://pith.science/pith/IWE72NPD6XCKZZ2LDNRN32RR3M/action/author_attestation","sign_citation":"https://pith.science/pith/IWE72NPD6XCKZZ2LDNRN32RR3M/action/citation_signature","submit_replication":"https://pith.science/pith/IWE72NPD6XCKZZ2LDNRN32RR3M/action/replication_record"}},"created_at":"2026-07-05T09:49:32.364518+00:00","updated_at":"2026-07-05T09:49:32.364518+00:00"}