{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:H6NDB6V2ZJYWXIS3ACHKERT4KT","short_pith_number":"pith:H6NDB6V2","canonical_record":{"source":{"id":"2406.04638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T04:52:46Z","cross_cats_sorted":[],"title_canon_sha256":"6da0f4cd40b0469118422e7a0abec2c95aebb6626a25c7ad1b6ebd6c9382dc76","abstract_canon_sha256":"bb38192f9a68a52f0d462c7b9fb897423579abb54f0fd2b1a131d9681d6a74ee"},"schema_version":"1.0"},"canonical_sha256":"3f9a30fabaca716ba25b008ea2467c54fa9d7f476f14c86dd74a67af47e9475c","source":{"kind":"arxiv","id":"2406.04638","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04638","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04638v1","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04638","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"pith_short_12","alias_value":"H6NDB6V2ZJYW","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"H6NDB6V2ZJYWXIS3","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"H6NDB6V2","created_at":"2026-07-05T08:28:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:H6NDB6V2ZJYWXIS3ACHKERT4KT","target":"record","payload":{"canonical_record":{"source":{"id":"2406.04638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T04:52:46Z","cross_cats_sorted":[],"title_canon_sha256":"6da0f4cd40b0469118422e7a0abec2c95aebb6626a25c7ad1b6ebd6c9382dc76","abstract_canon_sha256":"bb38192f9a68a52f0d462c7b9fb897423579abb54f0fd2b1a131d9681d6a74ee"},"schema_version":"1.0"},"canonical_sha256":"3f9a30fabaca716ba25b008ea2467c54fa9d7f476f14c86dd74a67af47e9475c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:46.858983Z","signature_b64":"U0CWt6iHSUaOwYCExgJUHF3zGZJgoD7gSffL3jQFQB60Cn7TbdgSx+QeLDx9zoHqTr1X71O8UBTzFklbMk2SBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f9a30fabaca716ba25b008ea2467c54fa9d7f476f14c86dd74a67af47e9475c","last_reissued_at":"2026-07-05T08:28:46.858599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:46.858599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.04638","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":"2026-07-05T08:28:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ldSA70UusOZQv0w4OvoJrzye/w2cCxDPz6egZhVpbyDYBwYXaTc8vqvLyQB2tX1ziLlDSbH/zecCxkkolw7FBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T06:00:35.804489Z"},"content_sha256":"26f81c312492995a8d6e240d1af059abef42f22061d2be0929323c35d4d11b50","schema_version":"1.0","event_id":"sha256:26f81c312492995a8d6e240d1af059abef42f22061d2be0929323c35d4d11b50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:H6NDB6V2ZJYWXIS3ACHKERT4KT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Model-guided Document Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ruoming Pang, Tom Gunter, Xiang Kong","submitted_at":"2024-06-07T04:52:46Z","abstract_excerpt":"Large Language Model (LLM) pre-training exhausts an ever growing compute budget, yet recent research has demonstrated that careful document selection enables comparable model quality with only a fraction of the FLOPs. Inspired by efforts suggesting that domain-specific training document selection is in fact an interpretable process [Gunasekar et al., 2023], as well as research showing that instruction-finetuned LLMs are adept zero-shot data labelers [Gilardi et al.,2023], we explore a promising direction for scalable general-domain document selection; employing a prompted LLM as a document gra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04638","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/2406.04638/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":"2026-07-05T08:28:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/hqOs7iEKXwPx9s+S0tYuZM9RpZRaAtRqYCOivjcp5fRD2AOs83fWq9wCL/iwO1YLTDn2D8ln2yWcx9oSg6nDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T06:00:35.805466Z"},"content_sha256":"437c30ca2c8a9437ca14dd52feb9b52611bb675b1f925df6845c9ab82ea1b0c4","schema_version":"1.0","event_id":"sha256:437c30ca2c8a9437ca14dd52feb9b52611bb675b1f925df6845c9ab82ea1b0c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H6NDB6V2ZJYWXIS3ACHKERT4KT/bundle.json","state_url":"https://pith.science/pith/H6NDB6V2ZJYWXIS3ACHKERT4KT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H6NDB6V2ZJYWXIS3ACHKERT4KT/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":"2026-08-15T06:00:35Z","links":{"resolver":"https://pith.science/pith/H6NDB6V2ZJYWXIS3ACHKERT4KT","bundle":"https://pith.science/pith/H6NDB6V2ZJYWXIS3ACHKERT4KT/bundle.json","state":"https://pith.science/pith/H6NDB6V2ZJYWXIS3ACHKERT4KT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H6NDB6V2ZJYWXIS3ACHKERT4KT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H6NDB6V2ZJYWXIS3ACHKERT4KT","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":"bb38192f9a68a52f0d462c7b9fb897423579abb54f0fd2b1a131d9681d6a74ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T04:52:46Z","title_canon_sha256":"6da0f4cd40b0469118422e7a0abec2c95aebb6626a25c7ad1b6ebd6c9382dc76"},"schema_version":"1.0","source":{"id":"2406.04638","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04638","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04638v1","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04638","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"pith_short_12","alias_value":"H6NDB6V2ZJYW","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"H6NDB6V2ZJYWXIS3","created_at":"2026-07-05T08:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"H6NDB6V2","created_at":"2026-07-05T08:28:46Z"}],"graph_snapshots":[{"event_id":"sha256:437c30ca2c8a9437ca14dd52feb9b52611bb675b1f925df6845c9ab82ea1b0c4","target":"graph","created_at":"2026-07-05T08:28:46Z","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/2406.04638/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Model (LLM) pre-training exhausts an ever growing compute budget, yet recent research has demonstrated that careful document selection enables comparable model quality with only a fraction of the FLOPs. Inspired by efforts suggesting that domain-specific training document selection is in fact an interpretable process [Gunasekar et al., 2023], as well as research showing that instruction-finetuned LLMs are adept zero-shot data labelers [Gilardi et al.,2023], we explore a promising direction for scalable general-domain document selection; employing a prompted LLM as a document gra","authors_text":"Ruoming Pang, Tom Gunter, Xiang Kong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T04:52:46Z","title":"Large Language Model-guided Document Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04638","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":"sha256:26f81c312492995a8d6e240d1af059abef42f22061d2be0929323c35d4d11b50","target":"record","created_at":"2026-07-05T08:28:46Z","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":"bb38192f9a68a52f0d462c7b9fb897423579abb54f0fd2b1a131d9681d6a74ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T04:52:46Z","title_canon_sha256":"6da0f4cd40b0469118422e7a0abec2c95aebb6626a25c7ad1b6ebd6c9382dc76"},"schema_version":"1.0","source":{"id":"2406.04638","kind":"arxiv","version":1}},"canonical_sha256":"3f9a30fabaca716ba25b008ea2467c54fa9d7f476f14c86dd74a67af47e9475c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f9a30fabaca716ba25b008ea2467c54fa9d7f476f14c86dd74a67af47e9475c","first_computed_at":"2026-07-05T08:28:46.858599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:46.858599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U0CWt6iHSUaOwYCExgJUHF3zGZJgoD7gSffL3jQFQB60Cn7TbdgSx+QeLDx9zoHqTr1X71O8UBTzFklbMk2SBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:46.858983Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04638","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26f81c312492995a8d6e240d1af059abef42f22061d2be0929323c35d4d11b50","sha256:437c30ca2c8a9437ca14dd52feb9b52611bb675b1f925df6845c9ab82ea1b0c4"],"state_sha256":"48edfdb51125ed88afd23030bb683af219a19ba77e6c063a9c36c8e7249d8a9b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/0tK4SL55WxcuGw3/DXgWoAf74JKV57ceiegZDJP2qNk1JVf1Y2KU7lVaKlrzHSACb3RusYPBYkzJ/uk2s1pCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T06:00:35.812032Z","bundle_sha256":"1c9ea360f49d1c16e57bbe6e3fa83d871efef07eac9df35606e25d7a09a2d2aa"}}