{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4DW3NSRBQCMALP3XXE3N7C566Y","short_pith_number":"pith:4DW3NSRB","canonical_record":{"source":{"id":"2411.02959","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-05T09:58:36Z","cross_cats_sorted":[],"title_canon_sha256":"2fca5fb3871d9cc8778983bbfdb2126267481f445fd6f9f60b4fdf4f3e9473ce","abstract_canon_sha256":"10be2c20df01438c63fdacca397ce442e171167b12887dd537e47757d7d753e1"},"schema_version":"1.0"},"canonical_sha256":"e0edb6ca21809805bf77b936df8bbef613bc82f29b07a689d404e77b8e815a8c","source":{"kind":"arxiv","id":"2411.02959","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02959","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02959v2","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02959","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"pith_short_12","alias_value":"4DW3NSRBQCMA","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"pith_short_16","alias_value":"4DW3NSRBQCMALP3X","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"pith_short_8","alias_value":"4DW3NSRB","created_at":"2026-07-05T10:10:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4DW3NSRBQCMALP3XXE3N7C566Y","target":"record","payload":{"canonical_record":{"source":{"id":"2411.02959","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-05T09:58:36Z","cross_cats_sorted":[],"title_canon_sha256":"2fca5fb3871d9cc8778983bbfdb2126267481f445fd6f9f60b4fdf4f3e9473ce","abstract_canon_sha256":"10be2c20df01438c63fdacca397ce442e171167b12887dd537e47757d7d753e1"},"schema_version":"1.0"},"canonical_sha256":"e0edb6ca21809805bf77b936df8bbef613bc82f29b07a689d404e77b8e815a8c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:45.962033Z","signature_b64":"hMKQOEXqkESScp2IMe5z4xJo7ca9k5fHAl++pceBBUeD5fuvrfJYNU7ue0dhijrg3S5bmMIo13u66zh53/dVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0edb6ca21809805bf77b936df8bbef613bc82f29b07a689d404e77b8e815a8c","last_reissued_at":"2026-07-05T10:10:45.961616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:45.961616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.02959","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":"2026-07-05T10:10:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KRXuQrzonnXjbum3wREDrMn8RbZ0ULS1Kme0VxL+XrPIN83v8GinKiJkPmH/FIvUiT5Ou+Xl8LSApdsdIGOfBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:13:14.459617Z"},"content_sha256":"b3f6f1a06ba1a727e4508e41b80a9e42eca9f952f4fd330ffb282c24e27fda8d","schema_version":"1.0","event_id":"sha256:b3f6f1a06ba1a727e4508e41b80a9e42eca9f952f4fd330ffb282c24e27fda8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4DW3NSRBQCMALP3XXE3N7C566Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jiejun Tan, Ji-Rong Wen, Mang Wang, Weipeng Chen, Wen Wang, Zhicheng Dou","submitted_at":"2024-11-05T09:58:36Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has been shown to improve knowledge capabilities and alleviate the hallucination problem of LLMs. The Web is a major source of external knowledge used in RAG systems, and many commercial RAG systems have used Web search engines as their major retrieval systems. Typically, such RAG systems retrieve search results, download HTML sources of the results, and then extract plain texts from the HTML sources. Plain text documents or chunks are fed into the LLMs to augment the generation. However, much of the structural and semantic information inherent in HTML, suc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02959","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/2411.02959/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":"2026-07-05T10:10:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f4sWcer94txMaWyzfD2hQ+Uy7klJZm79eKHSEdu4ZOQbrpXKy8WMiWaQ/ymu9DWIpPZjH+ZnuRxSGgOLJhH1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:13:14.460724Z"},"content_sha256":"1d953199dc673a2da212cfac99f0f751728f4dba982522d857031b75543a3210","schema_version":"1.0","event_id":"sha256:1d953199dc673a2da212cfac99f0f751728f4dba982522d857031b75543a3210"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4DW3NSRBQCMALP3XXE3N7C566Y/bundle.json","state_url":"https://pith.science/pith/4DW3NSRBQCMALP3XXE3N7C566Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4DW3NSRBQCMALP3XXE3N7C566Y/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":"2026-08-06T14:13:14Z","links":{"resolver":"https://pith.science/pith/4DW3NSRBQCMALP3XXE3N7C566Y","bundle":"https://pith.science/pith/4DW3NSRBQCMALP3XXE3N7C566Y/bundle.json","state":"https://pith.science/pith/4DW3NSRBQCMALP3XXE3N7C566Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4DW3NSRBQCMALP3XXE3N7C566Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4DW3NSRBQCMALP3XXE3N7C566Y","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":"10be2c20df01438c63fdacca397ce442e171167b12887dd537e47757d7d753e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-05T09:58:36Z","title_canon_sha256":"2fca5fb3871d9cc8778983bbfdb2126267481f445fd6f9f60b4fdf4f3e9473ce"},"schema_version":"1.0","source":{"id":"2411.02959","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02959","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02959v2","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02959","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"pith_short_12","alias_value":"4DW3NSRBQCMA","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"pith_short_16","alias_value":"4DW3NSRBQCMALP3X","created_at":"2026-07-05T10:10:45Z"},{"alias_kind":"pith_short_8","alias_value":"4DW3NSRB","created_at":"2026-07-05T10:10:45Z"}],"graph_snapshots":[{"event_id":"sha256:1d953199dc673a2da212cfac99f0f751728f4dba982522d857031b75543a3210","target":"graph","created_at":"2026-07-05T10:10:45Z","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/2411.02959/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) has been shown to improve knowledge capabilities and alleviate the hallucination problem of LLMs. The Web is a major source of external knowledge used in RAG systems, and many commercial RAG systems have used Web search engines as their major retrieval systems. Typically, such RAG systems retrieve search results, download HTML sources of the results, and then extract plain texts from the HTML sources. Plain text documents or chunks are fed into the LLMs to augment the generation. However, much of the structural and semantic information inherent in HTML, suc","authors_text":"Jiejun Tan, Ji-Rong Wen, Mang Wang, Weipeng Chen, Wen Wang, Zhicheng Dou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-05T09:58:36Z","title":"HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02959","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:b3f6f1a06ba1a727e4508e41b80a9e42eca9f952f4fd330ffb282c24e27fda8d","target":"record","created_at":"2026-07-05T10:10:45Z","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":"10be2c20df01438c63fdacca397ce442e171167b12887dd537e47757d7d753e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-11-05T09:58:36Z","title_canon_sha256":"2fca5fb3871d9cc8778983bbfdb2126267481f445fd6f9f60b4fdf4f3e9473ce"},"schema_version":"1.0","source":{"id":"2411.02959","kind":"arxiv","version":2}},"canonical_sha256":"e0edb6ca21809805bf77b936df8bbef613bc82f29b07a689d404e77b8e815a8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0edb6ca21809805bf77b936df8bbef613bc82f29b07a689d404e77b8e815a8c","first_computed_at":"2026-07-05T10:10:45.961616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:45.961616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hMKQOEXqkESScp2IMe5z4xJo7ca9k5fHAl++pceBBUeD5fuvrfJYNU7ue0dhijrg3S5bmMIo13u66zh53/dVBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:45.962033Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.02959","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3f6f1a06ba1a727e4508e41b80a9e42eca9f952f4fd330ffb282c24e27fda8d","sha256:1d953199dc673a2da212cfac99f0f751728f4dba982522d857031b75543a3210"],"state_sha256":"a997b9c93b81a08b67053094c59d5072206bc725f764aa3c9c2508ab5f0415db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kz4H5hhL+iAMEo32+qe/LgiKe3/5cfhZMX+6QNoPxit2K9OVJrCehPxCkeEoqOQ+Y2jdaqjsmQv4qr6G5VGQDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T14:13:14.481676Z","bundle_sha256":"c8893d8c7e0978097b4fbcd33717e6e3d4932c9b40835daf4bbbb8a4e12d1251"}}