{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:U5BTJUIOBW2F5RIJ7Q4OQOO2IT","short_pith_number":"pith:U5BTJUIO","canonical_record":{"source":{"id":"2507.00038","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T06:59:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bc9fc848e7082d5ba29f8dd16641a03e9446db0115379f6a858bca4df8cac2b4","abstract_canon_sha256":"2b0bef65c2eaef104d7974387718856e4d88d157334a8c11a072cb4f89ce7f58"},"schema_version":"1.0"},"canonical_sha256":"a74334d10e0db45ec509fc38e839da44ff7c2e5604517a8970d913190864d92e","source":{"kind":"arxiv","id":"2507.00038","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00038","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00038v3","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00038","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_12","alias_value":"U5BTJUIOBW2F","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_16","alias_value":"U5BTJUIOBW2F5RIJ","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_8","alias_value":"U5BTJUIO","created_at":"2026-07-05T11:50:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:U5BTJUIOBW2F5RIJ7Q4OQOO2IT","target":"record","payload":{"canonical_record":{"source":{"id":"2507.00038","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T06:59:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bc9fc848e7082d5ba29f8dd16641a03e9446db0115379f6a858bca4df8cac2b4","abstract_canon_sha256":"2b0bef65c2eaef104d7974387718856e4d88d157334a8c11a072cb4f89ce7f58"},"schema_version":"1.0"},"canonical_sha256":"a74334d10e0db45ec509fc38e839da44ff7c2e5604517a8970d913190864d92e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:38.024640Z","signature_b64":"T+reGgCD5elN4lxV/yqx763B2ccqPaAci1ia9DfAytFHdG8hPeOxFiq2iX8Xeh+4UJsot7A/4pBkhViMCSDFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a74334d10e0db45ec509fc38e839da44ff7c2e5604517a8970d913190864d92e","last_reissued_at":"2026-07-05T11:50:38.024168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:38.024168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.00038","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":"2026-07-05T11:50:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FVy+72E2ZXFonwC/L3tWStUASTu0Y1oVORxWDfg+hnaW33L9U36v4/+iGHFn3qD/GKSjcdB23NIR4r+LJXXqDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:52:54.168815Z"},"content_sha256":"be76f40bd3767c2f31f26f5dc131dc8cb2248c9b22637fa281a30298cec99de7","schema_version":"1.0","event_id":"sha256:be76f40bd3767c2f31f26f5dc131dc8cb2248c9b22637fa281a30298cec99de7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:U5BTJUIOBW2F5RIJ7Q4OQOO2IT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quality over Quantity: An Effective Large-Scale Data Reduction Strategy Based on Pointwise V-Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fei Chen, Wenchi Zhou","submitted_at":"2025-06-19T06:59:19Z","abstract_excerpt":"In order to increase the effectiveness of model training, data reduction is essential to data-centric Artificial Intelligence (AI). It achieves this by locating the most instructive examples in massive datasets. To increase data quality and training efficiency, the main difficulty is choosing the best examples rather than the complete datasets. In this paper, we propose an effective data reduction strategy based on Pointwise V-Information (PVI). To enable a static method, we first use PVI to quantify instance difficulty and remove instances with low difficulty. Experiments show that classifier"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00038","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/2507.00038/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":"2026-07-05T11:50:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7K8v33OzcRVBkCwyUFFkl04s/5n/jvgLrEMzH+vaPBQtXViWzSFxKopeWfZye8KuIhZsuA77Y44QTUyClokrAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:52:54.169759Z"},"content_sha256":"e78c9b36189b8705e9f1b97212976318c614e9873e18228ea867836a66c515da","schema_version":"1.0","event_id":"sha256:e78c9b36189b8705e9f1b97212976318c614e9873e18228ea867836a66c515da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U5BTJUIOBW2F5RIJ7Q4OQOO2IT/bundle.json","state_url":"https://pith.science/pith/U5BTJUIOBW2F5RIJ7Q4OQOO2IT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U5BTJUIOBW2F5RIJ7Q4OQOO2IT/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":"2026-08-07T19:52:54Z","links":{"resolver":"https://pith.science/pith/U5BTJUIOBW2F5RIJ7Q4OQOO2IT","bundle":"https://pith.science/pith/U5BTJUIOBW2F5RIJ7Q4OQOO2IT/bundle.json","state":"https://pith.science/pith/U5BTJUIOBW2F5RIJ7Q4OQOO2IT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U5BTJUIOBW2F5RIJ7Q4OQOO2IT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U5BTJUIOBW2F5RIJ7Q4OQOO2IT","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":"2b0bef65c2eaef104d7974387718856e4d88d157334a8c11a072cb4f89ce7f58","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T06:59:19Z","title_canon_sha256":"bc9fc848e7082d5ba29f8dd16641a03e9446db0115379f6a858bca4df8cac2b4"},"schema_version":"1.0","source":{"id":"2507.00038","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00038","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00038v3","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00038","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_12","alias_value":"U5BTJUIOBW2F","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_16","alias_value":"U5BTJUIOBW2F5RIJ","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_8","alias_value":"U5BTJUIO","created_at":"2026-07-05T11:50:38Z"}],"graph_snapshots":[{"event_id":"sha256:e78c9b36189b8705e9f1b97212976318c614e9873e18228ea867836a66c515da","target":"graph","created_at":"2026-07-05T11:50:38Z","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/2507.00038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In order to increase the effectiveness of model training, data reduction is essential to data-centric Artificial Intelligence (AI). It achieves this by locating the most instructive examples in massive datasets. To increase data quality and training efficiency, the main difficulty is choosing the best examples rather than the complete datasets. In this paper, we propose an effective data reduction strategy based on Pointwise V-Information (PVI). To enable a static method, we first use PVI to quantify instance difficulty and remove instances with low difficulty. Experiments show that classifier","authors_text":"Fei Chen, Wenchi Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T06:59:19Z","title":"Quality over Quantity: An Effective Large-Scale Data Reduction Strategy Based on Pointwise V-Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00038","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:be76f40bd3767c2f31f26f5dc131dc8cb2248c9b22637fa281a30298cec99de7","target":"record","created_at":"2026-07-05T11:50:38Z","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":"2b0bef65c2eaef104d7974387718856e4d88d157334a8c11a072cb4f89ce7f58","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T06:59:19Z","title_canon_sha256":"bc9fc848e7082d5ba29f8dd16641a03e9446db0115379f6a858bca4df8cac2b4"},"schema_version":"1.0","source":{"id":"2507.00038","kind":"arxiv","version":3}},"canonical_sha256":"a74334d10e0db45ec509fc38e839da44ff7c2e5604517a8970d913190864d92e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a74334d10e0db45ec509fc38e839da44ff7c2e5604517a8970d913190864d92e","first_computed_at":"2026-07-05T11:50:38.024168Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:38.024168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T+reGgCD5elN4lxV/yqx763B2ccqPaAci1ia9DfAytFHdG8hPeOxFiq2iX8Xeh+4UJsot7A/4pBkhViMCSDFAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:38.024640Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00038","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be76f40bd3767c2f31f26f5dc131dc8cb2248c9b22637fa281a30298cec99de7","sha256:e78c9b36189b8705e9f1b97212976318c614e9873e18228ea867836a66c515da"],"state_sha256":"8c7a600322b6adb7ff33681cc07666c36a2e2cc81ee777358ceb291cc5c5cdb8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"umarvdyFIOPdCmnZ9TYGYCiLf+fPupyw0SxJNsXffXutxU9lsK3kxMUwtWSq4VDLikN2QCljZ5macEQQ/Gg/Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:52:54.176453Z","bundle_sha256":"ca92b4147ba2e437be34757bb36849ce3de0f912135780ab45486b62c50b6ce5"}}