{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4BHVSGH35KFNUIX3CAJD6RKQ7Z","short_pith_number":"pith:4BHVSGH3","canonical_record":{"source":{"id":"2410.09335","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-12T02:48:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"49d4843896f6667bab9e792becf24acf9c7d6534e2e47337b137bd01685008ae","abstract_canon_sha256":"18010861e7480a626a00786a3e5caa67edf1f7c331ea927a98c8dcfe020e2e2d"},"schema_version":"1.0"},"canonical_sha256":"e04f5918fbea8ada22fb10123f4550fe504fdbcc628a2fe8d8ff0046c6e331f3","source":{"kind":"arxiv","id":"2410.09335","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09335","created_at":"2026-07-05T09:45:56Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09335v2","created_at":"2026-07-05T09:45:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09335","created_at":"2026-07-05T09:45:56Z"},{"alias_kind":"pith_short_12","alias_value":"4BHVSGH35KFN","created_at":"2026-07-05T09:45:56Z"},{"alias_kind":"pith_short_16","alias_value":"4BHVSGH35KFNUIX3","created_at":"2026-07-05T09:45:56Z"},{"alias_kind":"pith_short_8","alias_value":"4BHVSGH3","created_at":"2026-07-05T09:45:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4BHVSGH35KFNUIX3CAJD6RKQ7Z","target":"record","payload":{"canonical_record":{"source":{"id":"2410.09335","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-12T02:48:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"49d4843896f6667bab9e792becf24acf9c7d6534e2e47337b137bd01685008ae","abstract_canon_sha256":"18010861e7480a626a00786a3e5caa67edf1f7c331ea927a98c8dcfe020e2e2d"},"schema_version":"1.0"},"canonical_sha256":"e04f5918fbea8ada22fb10123f4550fe504fdbcc628a2fe8d8ff0046c6e331f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:56.128553Z","signature_b64":"FAfXSXUJUBj2fGeLgJIBIlB/3H7KwTv0aJVOmvPW+Q3QKws7pzpRim+0cpLDqICvbgHTvydaj1J4fqzLg5PODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e04f5918fbea8ada22fb10123f4550fe504fdbcc628a2fe8d8ff0046c6e331f3","last_reissued_at":"2026-07-05T09:45:56.128081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:56.128081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.09335","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":"2026-07-05T09:45:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2rKyZ5R/B9LNE5nET1y1DQVgLf5TG/akSIv3MYOPO72rU5VH52vs47bFWIEJ9gfQTv/JYgQhSwXLG4A9l+9/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:22:41.030670Z"},"content_sha256":"b175eb1990a2169e5560e2f4399f47318a8f134f8d21cafd2489a9fea54b6555","schema_version":"1.0","event_id":"sha256:b175eb1990a2169e5560e2f4399f47318a8f134f8d21cafd2489a9fea54b6555"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4BHVSGH35KFNUIX3CAJD6RKQ7Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking Data Selection at Scale: Random Selection is Almost All You Need","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"An Yang, Bowen Yu, Junyang Lin, Kai Dang, Tingyu Xia, Yi Chang, Yuan Tian, Yuan Wu","submitted_at":"2024-10-12T02:48:34Z","abstract_excerpt":"Supervised fine-tuning (SFT) is crucial for aligning Large Language Models (LLMs) with human instructions. The primary goal during SFT is to select a small yet representative subset of training data from the larger pool, such that fine-tuning with this subset achieves results comparable to or even exceeding those obtained using the entire dataset. However, most existing data selection techniques are designed for small-scale data pools, which fail to meet the demands of real-world SFT scenarios. In this paper, we replicated several self-scoring methods those that do not rely on external model a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09335","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/2410.09335/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":"2026-07-05T09:45:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9pex+wWVHxV1Q+h8fIiAjidR2v+wnhigQcew96W9bYghvZf6mF0aQf30y6KniaiEYmQ6B0Whem9Aa+njwVnDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:22:41.031180Z"},"content_sha256":"155ed7dadf4e9c78ff62057453b66284d14b41dc38b9439a47d237238c003959","schema_version":"1.0","event_id":"sha256:155ed7dadf4e9c78ff62057453b66284d14b41dc38b9439a47d237238c003959"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4BHVSGH35KFNUIX3CAJD6RKQ7Z/bundle.json","state_url":"https://pith.science/pith/4BHVSGH35KFNUIX3CAJD6RKQ7Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4BHVSGH35KFNUIX3CAJD6RKQ7Z/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":"2026-08-09T14:22:41Z","links":{"resolver":"https://pith.science/pith/4BHVSGH35KFNUIX3CAJD6RKQ7Z","bundle":"https://pith.science/pith/4BHVSGH35KFNUIX3CAJD6RKQ7Z/bundle.json","state":"https://pith.science/pith/4BHVSGH35KFNUIX3CAJD6RKQ7Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4BHVSGH35KFNUIX3CAJD6RKQ7Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4BHVSGH35KFNUIX3CAJD6RKQ7Z","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":"18010861e7480a626a00786a3e5caa67edf1f7c331ea927a98c8dcfe020e2e2d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-12T02:48:34Z","title_canon_sha256":"49d4843896f6667bab9e792becf24acf9c7d6534e2e47337b137bd01685008ae"},"schema_version":"1.0","source":{"id":"2410.09335","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.09335","created_at":"2026-07-05T09:45:56Z"},{"alias_kind":"arxiv_version","alias_value":"2410.09335v2","created_at":"2026-07-05T09:45:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09335","created_at":"2026-07-05T09:45:56Z"},{"alias_kind":"pith_short_12","alias_value":"4BHVSGH35KFN","created_at":"2026-07-05T09:45:56Z"},{"alias_kind":"pith_short_16","alias_value":"4BHVSGH35KFNUIX3","created_at":"2026-07-05T09:45:56Z"},{"alias_kind":"pith_short_8","alias_value":"4BHVSGH3","created_at":"2026-07-05T09:45:56Z"}],"graph_snapshots":[{"event_id":"sha256:155ed7dadf4e9c78ff62057453b66284d14b41dc38b9439a47d237238c003959","target":"graph","created_at":"2026-07-05T09:45:56Z","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/2410.09335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised fine-tuning (SFT) is crucial for aligning Large Language Models (LLMs) with human instructions. The primary goal during SFT is to select a small yet representative subset of training data from the larger pool, such that fine-tuning with this subset achieves results comparable to or even exceeding those obtained using the entire dataset. However, most existing data selection techniques are designed for small-scale data pools, which fail to meet the demands of real-world SFT scenarios. In this paper, we replicated several self-scoring methods those that do not rely on external model a","authors_text":"An Yang, Bowen Yu, Junyang Lin, Kai Dang, Tingyu Xia, Yi Chang, Yuan Tian, Yuan Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-12T02:48:34Z","title":"Rethinking Data Selection at Scale: Random Selection is Almost All You Need"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09335","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:b175eb1990a2169e5560e2f4399f47318a8f134f8d21cafd2489a9fea54b6555","target":"record","created_at":"2026-07-05T09:45:56Z","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":"18010861e7480a626a00786a3e5caa67edf1f7c331ea927a98c8dcfe020e2e2d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-12T02:48:34Z","title_canon_sha256":"49d4843896f6667bab9e792becf24acf9c7d6534e2e47337b137bd01685008ae"},"schema_version":"1.0","source":{"id":"2410.09335","kind":"arxiv","version":2}},"canonical_sha256":"e04f5918fbea8ada22fb10123f4550fe504fdbcc628a2fe8d8ff0046c6e331f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e04f5918fbea8ada22fb10123f4550fe504fdbcc628a2fe8d8ff0046c6e331f3","first_computed_at":"2026-07-05T09:45:56.128081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:56.128081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FAfXSXUJUBj2fGeLgJIBIlB/3H7KwTv0aJVOmvPW+Q3QKws7pzpRim+0cpLDqICvbgHTvydaj1J4fqzLg5PODg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:56.128553Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.09335","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b175eb1990a2169e5560e2f4399f47318a8f134f8d21cafd2489a9fea54b6555","sha256:155ed7dadf4e9c78ff62057453b66284d14b41dc38b9439a47d237238c003959"],"state_sha256":"64fdc7e12f7fc3840f27e4f741fbaf0e7829c45d3a316c3a0fb2a9aa9f9ccb74"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D+sRnoqpszWANNZv9SHolhGaFWJ7p/WPO/F+NPcz8CgzJLGw4rSAml6lP2v9A91FI4eDP1p37mjoZ4Z5tMj3Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:22:41.034974Z","bundle_sha256":"3234792693acecbec86c30fa36549557676e0d54750184d18eab567e79bc7a05"}}