{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:REYWJHSYSM6DFAL3CPFCJTIAQ6","short_pith_number":"pith:REYWJHSY","canonical_record":{"source":{"id":"2402.00530","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T11:57:53Z","cross_cats_sorted":[],"title_canon_sha256":"0fee5d61f475fa209fa66f4c3f4f154a1d5eaaaed3435cec8bbd4823931bd0b0","abstract_canon_sha256":"9935a988be37599c319333772039d65a0e0412b8a35065391dc429539b5ca294"},"schema_version":"1.0"},"canonical_sha256":"8931649e58933c32817b13ca24cd00878139affda9d89d268d0c97ed39c30437","source":{"kind":"arxiv","id":"2402.00530","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.00530","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"arxiv_version","alias_value":"2402.00530v2","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00530","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"pith_short_12","alias_value":"REYWJHSYSM6D","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"pith_short_16","alias_value":"REYWJHSYSM6DFAL3","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"pith_short_8","alias_value":"REYWJHSY","created_at":"2026-07-05T08:28:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:REYWJHSYSM6DFAL3CPFCJTIAQ6","target":"record","payload":{"canonical_record":{"source":{"id":"2402.00530","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T11:57:53Z","cross_cats_sorted":[],"title_canon_sha256":"0fee5d61f475fa209fa66f4c3f4f154a1d5eaaaed3435cec8bbd4823931bd0b0","abstract_canon_sha256":"9935a988be37599c319333772039d65a0e0412b8a35065391dc429539b5ca294"},"schema_version":"1.0"},"canonical_sha256":"8931649e58933c32817b13ca24cd00878139affda9d89d268d0c97ed39c30437","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:58.878055Z","signature_b64":"5tsyaN/XSGCqPzdpOfDQZQxdSyMX4lqUq3lGB5dqGAaxJO5H4bMi+eV+3jA7NJO19u+aNDwgJgmRC8tg2lEoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8931649e58933c32817b13ca24cd00878139affda9d89d268d0c97ed39c30437","last_reissued_at":"2026-07-05T08:28:58.877537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:58.877537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.00530","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":"2026-07-05T08:28:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a2X0V9VBFkaBJcZNPHieHCAv2apXdjNqCeK26Mdzdl0ei2ND5yKcv1KfnUcypo6ogLa8p8Wf6T7no6rmXf2jBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:23:09.042141Z"},"content_sha256":"731d57ea0e5bff4069a73518dd8afb751b72ea0c9349c4b762eddd546246a048","schema_version":"1.0","event_id":"sha256:731d57ea0e5bff4069a73518dd8afb751b72ea0c9349c4b762eddd546246a048"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:REYWJHSYSM6DFAL3CPFCJTIAQ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongyu Zhao, Jianzong Wang, Ming Li, Ning Cheng, Shwai He, Tianyi Zhou, Yong Zhang, Zhitao Li","submitted_at":"2024-02-01T11:57:53Z","abstract_excerpt":"Instruction tuning is critical to improve LLMs but usually suffers from low-quality and redundant data. Data filtering for instruction tuning has proved important in improving both the efficiency and performance of the tuning process. But it also leads to extra cost and computation due to the involvement of LLMs in this process. To reduce the filtering cost, we study Superfiltering: Can we use a smaller and weaker model to select data for finetuning a larger and stronger model? Despite the performance gap between weak and strong language models, we find their highly consistent capability to pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00530","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/2402.00530/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":"2026-07-05T08:28:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZXnMFqIFE6MXqFnYBUpIa4oV3anOTjbnwZBfBz9nkz0SX1nrr4g4T4xf9c6Vbk66+gBqsNrnaTp/iSaKxhquCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:23:09.042646Z"},"content_sha256":"ca9fe7013ceaeecc235c8f2a969f14c9ea0c20f061cb684e4b639c687697e12e","schema_version":"1.0","event_id":"sha256:ca9fe7013ceaeecc235c8f2a969f14c9ea0c20f061cb684e4b639c687697e12e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/REYWJHSYSM6DFAL3CPFCJTIAQ6/bundle.json","state_url":"https://pith.science/pith/REYWJHSYSM6DFAL3CPFCJTIAQ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/REYWJHSYSM6DFAL3CPFCJTIAQ6/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":"2026-08-09T03:23:09Z","links":{"resolver":"https://pith.science/pith/REYWJHSYSM6DFAL3CPFCJTIAQ6","bundle":"https://pith.science/pith/REYWJHSYSM6DFAL3CPFCJTIAQ6/bundle.json","state":"https://pith.science/pith/REYWJHSYSM6DFAL3CPFCJTIAQ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/REYWJHSYSM6DFAL3CPFCJTIAQ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:REYWJHSYSM6DFAL3CPFCJTIAQ6","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":"9935a988be37599c319333772039d65a0e0412b8a35065391dc429539b5ca294","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T11:57:53Z","title_canon_sha256":"0fee5d61f475fa209fa66f4c3f4f154a1d5eaaaed3435cec8bbd4823931bd0b0"},"schema_version":"1.0","source":{"id":"2402.00530","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.00530","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"arxiv_version","alias_value":"2402.00530v2","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00530","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"pith_short_12","alias_value":"REYWJHSYSM6D","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"pith_short_16","alias_value":"REYWJHSYSM6DFAL3","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"pith_short_8","alias_value":"REYWJHSY","created_at":"2026-07-05T08:28:58Z"}],"graph_snapshots":[{"event_id":"sha256:ca9fe7013ceaeecc235c8f2a969f14c9ea0c20f061cb684e4b639c687697e12e","target":"graph","created_at":"2026-07-05T08:28:58Z","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/2402.00530/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning is critical to improve LLMs but usually suffers from low-quality and redundant data. Data filtering for instruction tuning has proved important in improving both the efficiency and performance of the tuning process. But it also leads to extra cost and computation due to the involvement of LLMs in this process. To reduce the filtering cost, we study Superfiltering: Can we use a smaller and weaker model to select data for finetuning a larger and stronger model? Despite the performance gap between weak and strong language models, we find their highly consistent capability to pe","authors_text":"Hongyu Zhao, Jianzong Wang, Ming Li, Ning Cheng, Shwai He, Tianyi Zhou, Yong Zhang, Zhitao Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T11:57:53Z","title":"Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00530","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":"sha256:731d57ea0e5bff4069a73518dd8afb751b72ea0c9349c4b762eddd546246a048","target":"record","created_at":"2026-07-05T08:28:58Z","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":"9935a988be37599c319333772039d65a0e0412b8a35065391dc429539b5ca294","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T11:57:53Z","title_canon_sha256":"0fee5d61f475fa209fa66f4c3f4f154a1d5eaaaed3435cec8bbd4823931bd0b0"},"schema_version":"1.0","source":{"id":"2402.00530","kind":"arxiv","version":2}},"canonical_sha256":"8931649e58933c32817b13ca24cd00878139affda9d89d268d0c97ed39c30437","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8931649e58933c32817b13ca24cd00878139affda9d89d268d0c97ed39c30437","first_computed_at":"2026-07-05T08:28:58.877537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:58.877537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5tsyaN/XSGCqPzdpOfDQZQxdSyMX4lqUq3lGB5dqGAaxJO5H4bMi+eV+3jA7NJO19u+aNDwgJgmRC8tg2lEoCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:58.878055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.00530","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:731d57ea0e5bff4069a73518dd8afb751b72ea0c9349c4b762eddd546246a048","sha256:ca9fe7013ceaeecc235c8f2a969f14c9ea0c20f061cb684e4b639c687697e12e"],"state_sha256":"14e8cb2a76417f1713c01465de948addb6f74d9565f5448cc13018ea517a1cca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kzoWf7wnC2frWDyXHyIDshr0t+Ya5vLoREAU0UHC5lKuTMmUZARJQUutcfNmOTLgF1sOOja4VFZDaxil2GRHDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:23:09.046874Z","bundle_sha256":"af54b31bcf1342e48dff939640d2f825539503bf0d912af011109fcf694a0634"}}