{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6PSCJXXBAK34VV6UVZBLFTZCBR","short_pith_number":"pith:6PSCJXXB","canonical_record":{"source":{"id":"2507.12750","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T03:08:26Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0419b4792ca211de38618c9d891a9807e7afd68e151f7081b995661fcb40d0db","abstract_canon_sha256":"06c0437ad7e89cf11caf05aabebd2e46d1e89fe8702b503fa73196d4bdf8167d"},"schema_version":"1.0"},"canonical_sha256":"f3e424dee102b7cad7d4ae42b2cf220c5c9bef0eea52f7f405180947f19113dc","source":{"kind":"arxiv","id":"2507.12750","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12750","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12750v1","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12750","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"pith_short_12","alias_value":"6PSCJXXBAK34","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"pith_short_16","alias_value":"6PSCJXXBAK34VV6U","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"pith_short_8","alias_value":"6PSCJXXB","created_at":"2026-07-05T11:38:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6PSCJXXBAK34VV6UVZBLFTZCBR","target":"record","payload":{"canonical_record":{"source":{"id":"2507.12750","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T03:08:26Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0419b4792ca211de38618c9d891a9807e7afd68e151f7081b995661fcb40d0db","abstract_canon_sha256":"06c0437ad7e89cf11caf05aabebd2e46d1e89fe8702b503fa73196d4bdf8167d"},"schema_version":"1.0"},"canonical_sha256":"f3e424dee102b7cad7d4ae42b2cf220c5c9bef0eea52f7f405180947f19113dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:38.452650Z","signature_b64":"Q7O/OYWe/oxJqwFNEyntyILvLi1gQEdjiFKi8euEio5QGONW2yrI3JNb99z7mTNaAJlpa/cfDh3yey133fxZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3e424dee102b7cad7d4ae42b2cf220c5c9bef0eea52f7f405180947f19113dc","last_reissued_at":"2026-07-05T11:38:38.452150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:38.452150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.12750","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":"2026-07-05T11:38:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1xxB8D3NbX1Hkgl8qR1GKe7YOnN1UZ3NwPnBmZnTG8ZC9GbsmZ7eCJMqGZJtjQmzTBzm/PzhSfozzNwDuXsfAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:23:50.442148Z"},"content_sha256":"be9cc765130954798e080a8c6f22e922f0042343b720a3c9d8476d3447bcdaae","schema_version":"1.0","event_id":"sha256:be9cc765130954798e080a8c6f22e922f0042343b720a3c9d8476d3447bcdaae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6PSCJXXBAK34VV6UVZBLFTZCBR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal-Guided Dynamic Dataset Pruning for Robust and Efficient Data-Centric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dongzhan Zhou, Furao Shen, Peijia Li, Peng Ye, Suorong Yang, Wanli Ouyang, Yujie Liu, Zhiming Xu","submitted_at":"2025-07-17T03:08:26Z","abstract_excerpt":"Modern deep models are trained on large real-world datasets, where data quality varies and redundancy is common. Data-centric approaches such as dataset pruning have shown promise in improving training efficiency and model performance. However, most existing methods rely on static heuristics or task-specific metrics, limiting their robustness and generalizability across domains. In this work, we introduce a dynamic dataset pruning framework that adaptively selects training samples based on both task-driven difficulty and cross-modality semantic consistency. By incorporating supervision from pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12750","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/2507.12750/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":"2026-07-05T11:38:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7GGU+u2GjbdRX6OoxI3v2LLd2CUE15ucgr631Ua+2XuSL/GgRc3uJuCs3EjsBugdcI7jncZDv0BFZ43bNwJDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:23:50.443794Z"},"content_sha256":"c0e8e136f4a6398228ecc61bfad1b2001110b5bac39c4f33c4d955522551b6c5","schema_version":"1.0","event_id":"sha256:c0e8e136f4a6398228ecc61bfad1b2001110b5bac39c4f33c4d955522551b6c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6PSCJXXBAK34VV6UVZBLFTZCBR/bundle.json","state_url":"https://pith.science/pith/6PSCJXXBAK34VV6UVZBLFTZCBR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6PSCJXXBAK34VV6UVZBLFTZCBR/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":"2026-08-10T18:23:50Z","links":{"resolver":"https://pith.science/pith/6PSCJXXBAK34VV6UVZBLFTZCBR","bundle":"https://pith.science/pith/6PSCJXXBAK34VV6UVZBLFTZCBR/bundle.json","state":"https://pith.science/pith/6PSCJXXBAK34VV6UVZBLFTZCBR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6PSCJXXBAK34VV6UVZBLFTZCBR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6PSCJXXBAK34VV6UVZBLFTZCBR","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":"06c0437ad7e89cf11caf05aabebd2e46d1e89fe8702b503fa73196d4bdf8167d","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T03:08:26Z","title_canon_sha256":"0419b4792ca211de38618c9d891a9807e7afd68e151f7081b995661fcb40d0db"},"schema_version":"1.0","source":{"id":"2507.12750","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12750","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12750v1","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12750","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"pith_short_12","alias_value":"6PSCJXXBAK34","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"pith_short_16","alias_value":"6PSCJXXBAK34VV6U","created_at":"2026-07-05T11:38:38Z"},{"alias_kind":"pith_short_8","alias_value":"6PSCJXXB","created_at":"2026-07-05T11:38:38Z"}],"graph_snapshots":[{"event_id":"sha256:c0e8e136f4a6398228ecc61bfad1b2001110b5bac39c4f33c4d955522551b6c5","target":"graph","created_at":"2026-07-05T11:38:38Z","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/2507.12750/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern deep models are trained on large real-world datasets, where data quality varies and redundancy is common. Data-centric approaches such as dataset pruning have shown promise in improving training efficiency and model performance. However, most existing methods rely on static heuristics or task-specific metrics, limiting their robustness and generalizability across domains. In this work, we introduce a dynamic dataset pruning framework that adaptively selects training samples based on both task-driven difficulty and cross-modality semantic consistency. By incorporating supervision from pr","authors_text":"Dongzhan Zhou, Furao Shen, Peijia Li, Peng Ye, Suorong Yang, Wanli Ouyang, Yujie Liu, Zhiming Xu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T03:08:26Z","title":"Multimodal-Guided Dynamic Dataset Pruning for Robust and Efficient Data-Centric Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12750","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:be9cc765130954798e080a8c6f22e922f0042343b720a3c9d8476d3447bcdaae","target":"record","created_at":"2026-07-05T11:38:38Z","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":"06c0437ad7e89cf11caf05aabebd2e46d1e89fe8702b503fa73196d4bdf8167d","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T03:08:26Z","title_canon_sha256":"0419b4792ca211de38618c9d891a9807e7afd68e151f7081b995661fcb40d0db"},"schema_version":"1.0","source":{"id":"2507.12750","kind":"arxiv","version":1}},"canonical_sha256":"f3e424dee102b7cad7d4ae42b2cf220c5c9bef0eea52f7f405180947f19113dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3e424dee102b7cad7d4ae42b2cf220c5c9bef0eea52f7f405180947f19113dc","first_computed_at":"2026-07-05T11:38:38.452150Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:38.452150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q7O/OYWe/oxJqwFNEyntyILvLi1gQEdjiFKi8euEio5QGONW2yrI3JNb99z7mTNaAJlpa/cfDh3yey133fxZBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:38.452650Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.12750","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be9cc765130954798e080a8c6f22e922f0042343b720a3c9d8476d3447bcdaae","sha256:c0e8e136f4a6398228ecc61bfad1b2001110b5bac39c4f33c4d955522551b6c5"],"state_sha256":"c54eb5b26da4c6809bfbc97da9211fff1138d0865dc9c7575e045bbe32c3a077"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w+hR0RsHr6kLlYdQX+sc10pM1LcpPZ9WttuGCZVWQh9MSp50SmEeFpXFfQ1yS7I+MZIeJkCjvIOkag/kdg0wAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:23:50.450586Z","bundle_sha256":"59c37ba8fe10daa8fefcc7a5a1b4375838a457f9f95e944124f73acfacb64b2e"}}