{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4TG2TGAXA2NX662TYU4Y6XEZ6P","short_pith_number":"pith:4TG2TGAX","canonical_record":{"source":{"id":"2412.14809","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T12:57:47Z","cross_cats_sorted":[],"title_canon_sha256":"53783b9b676cdec00c2b4dbb863f949c2784ae181e8f9c33da2e414b5d36205b","abstract_canon_sha256":"f08993424373e73f126b8d263bf314502f996f5be20c30357aeb8d405a8ac327"},"schema_version":"1.0"},"canonical_sha256":"e4cda99817069b7f7b53c5398f5c99f3f0edec7207dd0725669e2aca17fb7887","source":{"kind":"arxiv","id":"2412.14809","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14809","created_at":"2026-07-05T10:04:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14809v3","created_at":"2026-07-05T10:04:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14809","created_at":"2026-07-05T10:04:58Z"},{"alias_kind":"pith_short_12","alias_value":"4TG2TGAXA2NX","created_at":"2026-07-05T10:04:58Z"},{"alias_kind":"pith_short_16","alias_value":"4TG2TGAXA2NX662T","created_at":"2026-07-05T10:04:58Z"},{"alias_kind":"pith_short_8","alias_value":"4TG2TGAX","created_at":"2026-07-05T10:04:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4TG2TGAXA2NX662TYU4Y6XEZ6P","target":"record","payload":{"canonical_record":{"source":{"id":"2412.14809","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T12:57:47Z","cross_cats_sorted":[],"title_canon_sha256":"53783b9b676cdec00c2b4dbb863f949c2784ae181e8f9c33da2e414b5d36205b","abstract_canon_sha256":"f08993424373e73f126b8d263bf314502f996f5be20c30357aeb8d405a8ac327"},"schema_version":"1.0"},"canonical_sha256":"e4cda99817069b7f7b53c5398f5c99f3f0edec7207dd0725669e2aca17fb7887","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:58.951896Z","signature_b64":"6m+sAAd/xpOJBlEQBhxykr04dGWM+TU6seqpN9yIYCf5hRD6DNqrFDs9LYRx9xfTb4yXznBCgjZA1mlIj9/lDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4cda99817069b7f7b53c5398f5c99f3f0edec7207dd0725669e2aca17fb7887","last_reissued_at":"2026-07-05T10:04:58.951542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:58.951542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.14809","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:04:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CNLU+hipnfv2VbUW+1/GZT9tU0cjNHsUHW68Z3rPySrv+V+a72Vx6IwV73ystdnOi5jq/IBvmy2Cjs5NFyBoBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:00:07.125971Z"},"content_sha256":"0aef885201298d944a9e00c5f151fa396df591db6bd4d5bc893bb0ef3b851dd6","schema_version":"1.0","event_id":"sha256:0aef885201298d944a9e00c5f151fa396df591db6bd4d5bc893bb0ef3b851dd6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4TG2TGAXA2NX662TYU4Y6XEZ6P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jun Liu, Ming Li, Tianyu Qi, Xiangdi Meng, Yu He, Zeao Tu, Zihan Yao","submitted_at":"2024-12-19T12:57:47Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable effectiveness across various domains, with data augmentation methods utilizing GPT for synthetic data generation becoming prevalent. However, the quality and utility of augmented data remain questionable, and current methods lack clear metrics for evaluating data characteristics. To address these challenges, we propose ResoFilter, a novel method that integrates models, data, and tasks to refine datasets. ResoFilter leverages the fine-tuning process to obtain Data-Parameter features for data selection, offering improved interpretability by repr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14809","kind":"arxiv","version":3},"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/2412.14809/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":"2026-07-05T10:04:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"thiTlF2uLSVp+OrCFkA27O0/46joCbQaCL4lV/3vHWdZDeUnEjWe0HtedQwdURLNh/Vy4czYqaZIQOIHJcJWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:00:07.126504Z"},"content_sha256":"0316c86c01d769c79709da404a0b2f7f203746607fd4897219c06e0595aa74ef","schema_version":"1.0","event_id":"sha256:0316c86c01d769c79709da404a0b2f7f203746607fd4897219c06e0595aa74ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4TG2TGAXA2NX662TYU4Y6XEZ6P/bundle.json","state_url":"https://pith.science/pith/4TG2TGAXA2NX662TYU4Y6XEZ6P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4TG2TGAXA2NX662TYU4Y6XEZ6P/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":"2026-08-14T18:00:07Z","links":{"resolver":"https://pith.science/pith/4TG2TGAXA2NX662TYU4Y6XEZ6P","bundle":"https://pith.science/pith/4TG2TGAXA2NX662TYU4Y6XEZ6P/bundle.json","state":"https://pith.science/pith/4TG2TGAXA2NX662TYU4Y6XEZ6P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4TG2TGAXA2NX662TYU4Y6XEZ6P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4TG2TGAXA2NX662TYU4Y6XEZ6P","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":"f08993424373e73f126b8d263bf314502f996f5be20c30357aeb8d405a8ac327","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T12:57:47Z","title_canon_sha256":"53783b9b676cdec00c2b4dbb863f949c2784ae181e8f9c33da2e414b5d36205b"},"schema_version":"1.0","source":{"id":"2412.14809","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14809","created_at":"2026-07-05T10:04:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14809v3","created_at":"2026-07-05T10:04:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14809","created_at":"2026-07-05T10:04:58Z"},{"alias_kind":"pith_short_12","alias_value":"4TG2TGAXA2NX","created_at":"2026-07-05T10:04:58Z"},{"alias_kind":"pith_short_16","alias_value":"4TG2TGAXA2NX662T","created_at":"2026-07-05T10:04:58Z"},{"alias_kind":"pith_short_8","alias_value":"4TG2TGAX","created_at":"2026-07-05T10:04:58Z"}],"graph_snapshots":[{"event_id":"sha256:0316c86c01d769c79709da404a0b2f7f203746607fd4897219c06e0595aa74ef","target":"graph","created_at":"2026-07-05T10:04:58Z","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/2412.14809/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown remarkable effectiveness across various domains, with data augmentation methods utilizing GPT for synthetic data generation becoming prevalent. However, the quality and utility of augmented data remain questionable, and current methods lack clear metrics for evaluating data characteristics. To address these challenges, we propose ResoFilter, a novel method that integrates models, data, and tasks to refine datasets. ResoFilter leverages the fine-tuning process to obtain Data-Parameter features for data selection, offering improved interpretability by repr","authors_text":"Jun Liu, Ming Li, Tianyu Qi, Xiangdi Meng, Yu He, Zeao Tu, Zihan Yao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T12:57:47Z","title":"ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14809","kind":"arxiv","version":3},"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":"sha256:0aef885201298d944a9e00c5f151fa396df591db6bd4d5bc893bb0ef3b851dd6","target":"record","created_at":"2026-07-05T10:04:58Z","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":"f08993424373e73f126b8d263bf314502f996f5be20c30357aeb8d405a8ac327","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T12:57:47Z","title_canon_sha256":"53783b9b676cdec00c2b4dbb863f949c2784ae181e8f9c33da2e414b5d36205b"},"schema_version":"1.0","source":{"id":"2412.14809","kind":"arxiv","version":3}},"canonical_sha256":"e4cda99817069b7f7b53c5398f5c99f3f0edec7207dd0725669e2aca17fb7887","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4cda99817069b7f7b53c5398f5c99f3f0edec7207dd0725669e2aca17fb7887","first_computed_at":"2026-07-05T10:04:58.951542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:58.951542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6m+sAAd/xpOJBlEQBhxykr04dGWM+TU6seqpN9yIYCf5hRD6DNqrFDs9LYRx9xfTb4yXznBCgjZA1mlIj9/lDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:58.951896Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14809","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0aef885201298d944a9e00c5f151fa396df591db6bd4d5bc893bb0ef3b851dd6","sha256:0316c86c01d769c79709da404a0b2f7f203746607fd4897219c06e0595aa74ef"],"state_sha256":"fa3e3716d8a392d67db2fea4bc4288cf235912c79861c3739295af889c4f8b08"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"skXbHnuUwe4AjHWVyobWMdhV+kyPL8HBGL0HSwe1J1WWu5APvPQR13EHc7XURTcQx4P8GN2/ks166dB9kdSuCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T18:00:07.147389Z","bundle_sha256":"fa88f101735397d928b011a956067956a0b30f13b83b7bfaa97862e4d62432b4"}}