{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XSZ3DF6OEOYZWOEHWQWTWSHX5V","short_pith_number":"pith:XSZ3DF6O","canonical_record":{"source":{"id":"2405.16933","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T08:26:45Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"06c9960fce653bfc332084d8685e43bd75d2ec44a7da4a466cdf3d416e4ef684","abstract_canon_sha256":"eb087265bded1c02df6f98bb1d2265e13316dd94b7629984965efbc61b085a02"},"schema_version":"1.0"},"canonical_sha256":"bcb3b197ce23b19b3887b42d3b48f7ed50ae266334f80bd66f2b334a4ed10e02","source":{"kind":"arxiv","id":"2405.16933","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16933","created_at":"2026-07-05T08:23:37Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16933v1","created_at":"2026-07-05T08:23:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16933","created_at":"2026-07-05T08:23:37Z"},{"alias_kind":"pith_short_12","alias_value":"XSZ3DF6OEOYZ","created_at":"2026-07-05T08:23:37Z"},{"alias_kind":"pith_short_16","alias_value":"XSZ3DF6OEOYZWOEH","created_at":"2026-07-05T08:23:37Z"},{"alias_kind":"pith_short_8","alias_value":"XSZ3DF6O","created_at":"2026-07-05T08:23:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XSZ3DF6OEOYZWOEHWQWTWSHX5V","target":"record","payload":{"canonical_record":{"source":{"id":"2405.16933","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T08:26:45Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"06c9960fce653bfc332084d8685e43bd75d2ec44a7da4a466cdf3d416e4ef684","abstract_canon_sha256":"eb087265bded1c02df6f98bb1d2265e13316dd94b7629984965efbc61b085a02"},"schema_version":"1.0"},"canonical_sha256":"bcb3b197ce23b19b3887b42d3b48f7ed50ae266334f80bd66f2b334a4ed10e02","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:37.657404Z","signature_b64":"A1iJ1PmQ2H3IhPBzO901EMbR9L4KkX0g1RRky7+KmGG/RkYuGoTeihtvTZmeBzvRTH2vcPaokT65DXitHRreCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcb3b197ce23b19b3887b42d3b48f7ed50ae266334f80bd66f2b334a4ed10e02","last_reissued_at":"2026-07-05T08:23:37.656906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:37.656906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.16933","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":"2026-07-05T08:23:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OFxvDoR6ICrzuPAzKy9Aw3KOIznUu3mjxlTakYyWh+cFsDNwcj/H+lozLQAVmELtV3S6mGPmfYCgqFstEitNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:39:03.504173Z"},"content_sha256":"b8292c21e6d75f52d1b5c076e577f3cb2a8c41b3de939bbb773b0de0dd6feaa2","schema_version":"1.0","event_id":"sha256:b8292c21e6d75f52d1b5c076e577f3cb2a8c41b3de939bbb773b0de0dd6feaa2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XSZ3DF6OEOYZWOEHWQWTWSHX5V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Bo Tang, Chenyang Xi, Feiyu Xiong, Hanyu Wang, Jiawei Yang, Sensen Zhang, Shichao Song, Simin Niu, Xun Liang, Zhiyu Li","submitted_at":"2024-05-27T08:26:45Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) offers a cost-effective approach to injecting real-time knowledge into large language models (LLMs). Nevertheless, constructing and validating high-quality knowledge repositories require considerable effort. We propose a pre-retrieval framework named Pseudo-Graph Retrieval-Augmented Generation (PG-RAG), which conceptualizes LLMs as students by providing them with abundant raw reading materials and encouraging them to engage in autonomous reading to record factual information in their own words. The resulting concise, well-organized mental indices are interc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16933","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/2405.16933/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":"2026-07-05T08:23:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bSVn97XIyXKKjlWVVzOhyoo2OrPmy3zCI/AcXhHWcIXf6XO+EGIP8QJnv4VvJIsC4TuhGpFnV7bqoO0ABL5pCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:39:03.504718Z"},"content_sha256":"bbf63b357648b61dcfc2c0394b9f0e1dd7b4efff7e77a0aa7bdd27f6c469c94d","schema_version":"1.0","event_id":"sha256:bbf63b357648b61dcfc2c0394b9f0e1dd7b4efff7e77a0aa7bdd27f6c469c94d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XSZ3DF6OEOYZWOEHWQWTWSHX5V/bundle.json","state_url":"https://pith.science/pith/XSZ3DF6OEOYZWOEHWQWTWSHX5V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XSZ3DF6OEOYZWOEHWQWTWSHX5V/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":"2026-08-05T15:39:03Z","links":{"resolver":"https://pith.science/pith/XSZ3DF6OEOYZWOEHWQWTWSHX5V","bundle":"https://pith.science/pith/XSZ3DF6OEOYZWOEHWQWTWSHX5V/bundle.json","state":"https://pith.science/pith/XSZ3DF6OEOYZWOEHWQWTWSHX5V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XSZ3DF6OEOYZWOEHWQWTWSHX5V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XSZ3DF6OEOYZWOEHWQWTWSHX5V","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":"eb087265bded1c02df6f98bb1d2265e13316dd94b7629984965efbc61b085a02","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T08:26:45Z","title_canon_sha256":"06c9960fce653bfc332084d8685e43bd75d2ec44a7da4a466cdf3d416e4ef684"},"schema_version":"1.0","source":{"id":"2405.16933","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16933","created_at":"2026-07-05T08:23:37Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16933v1","created_at":"2026-07-05T08:23:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16933","created_at":"2026-07-05T08:23:37Z"},{"alias_kind":"pith_short_12","alias_value":"XSZ3DF6OEOYZ","created_at":"2026-07-05T08:23:37Z"},{"alias_kind":"pith_short_16","alias_value":"XSZ3DF6OEOYZWOEH","created_at":"2026-07-05T08:23:37Z"},{"alias_kind":"pith_short_8","alias_value":"XSZ3DF6O","created_at":"2026-07-05T08:23:37Z"}],"graph_snapshots":[{"event_id":"sha256:bbf63b357648b61dcfc2c0394b9f0e1dd7b4efff7e77a0aa7bdd27f6c469c94d","target":"graph","created_at":"2026-07-05T08:23:37Z","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/2405.16933/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) offers a cost-effective approach to injecting real-time knowledge into large language models (LLMs). Nevertheless, constructing and validating high-quality knowledge repositories require considerable effort. We propose a pre-retrieval framework named Pseudo-Graph Retrieval-Augmented Generation (PG-RAG), which conceptualizes LLMs as students by providing them with abundant raw reading materials and encouraging them to engage in autonomous reading to record factual information in their own words. The resulting concise, well-organized mental indices are interc","authors_text":"Bo Tang, Chenyang Xi, Feiyu Xiong, Hanyu Wang, Jiawei Yang, Sensen Zhang, Shichao Song, Simin Niu, Xun Liang, Zhiyu Li","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T08:26:45Z","title":"Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16933","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:b8292c21e6d75f52d1b5c076e577f3cb2a8c41b3de939bbb773b0de0dd6feaa2","target":"record","created_at":"2026-07-05T08:23:37Z","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":"eb087265bded1c02df6f98bb1d2265e13316dd94b7629984965efbc61b085a02","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T08:26:45Z","title_canon_sha256":"06c9960fce653bfc332084d8685e43bd75d2ec44a7da4a466cdf3d416e4ef684"},"schema_version":"1.0","source":{"id":"2405.16933","kind":"arxiv","version":1}},"canonical_sha256":"bcb3b197ce23b19b3887b42d3b48f7ed50ae266334f80bd66f2b334a4ed10e02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcb3b197ce23b19b3887b42d3b48f7ed50ae266334f80bd66f2b334a4ed10e02","first_computed_at":"2026-07-05T08:23:37.656906Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:37.656906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A1iJ1PmQ2H3IhPBzO901EMbR9L4KkX0g1RRky7+KmGG/RkYuGoTeihtvTZmeBzvRTH2vcPaokT65DXitHRreCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:37.657404Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16933","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8292c21e6d75f52d1b5c076e577f3cb2a8c41b3de939bbb773b0de0dd6feaa2","sha256:bbf63b357648b61dcfc2c0394b9f0e1dd7b4efff7e77a0aa7bdd27f6c469c94d"],"state_sha256":"2e5e7c60560bf3b2e88551e403116da57796039b535bbfce3d7de5566fba480c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fvkPRoKqTvng63boXUZKVQQEF6FFCYF0FWqkYb1ugtgihFIAbUnMXV2ptyRS16ami96mqVqR7rKEuSbciuacDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:39:03.510503Z","bundle_sha256":"ae3026d4a129e06a71de77b9fd5bba2511f06675d68f3843d797e0a61963664b"}}