{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XAVTGLFPJG6VNG7FHXJRHUL46A","short_pith_number":"pith:XAVTGLFP","canonical_record":{"source":{"id":"2506.01701","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T14:06:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df1d8fed4d821daec0f19f7548a0bb9ce0e3dcc6825c42d9ba429ba262dd3219","abstract_canon_sha256":"e44df43eb05b832b61d281e3ca322f4e54b865be79ca8b968745056daddd53a3"},"schema_version":"1.0"},"canonical_sha256":"b82b332caf49bd569be53dd313d17cf01bf47603ac0cc295539cc24570c7505e","source":{"kind":"arxiv","id":"2506.01701","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01701","created_at":"2026-07-05T11:53:47Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01701v2","created_at":"2026-07-05T11:53:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01701","created_at":"2026-07-05T11:53:47Z"},{"alias_kind":"pith_short_12","alias_value":"XAVTGLFPJG6V","created_at":"2026-07-05T11:53:47Z"},{"alias_kind":"pith_short_16","alias_value":"XAVTGLFPJG6VNG7F","created_at":"2026-07-05T11:53:47Z"},{"alias_kind":"pith_short_8","alias_value":"XAVTGLFP","created_at":"2026-07-05T11:53:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XAVTGLFPJG6VNG7FHXJRHUL46A","target":"record","payload":{"canonical_record":{"source":{"id":"2506.01701","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T14:06:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df1d8fed4d821daec0f19f7548a0bb9ce0e3dcc6825c42d9ba429ba262dd3219","abstract_canon_sha256":"e44df43eb05b832b61d281e3ca322f4e54b865be79ca8b968745056daddd53a3"},"schema_version":"1.0"},"canonical_sha256":"b82b332caf49bd569be53dd313d17cf01bf47603ac0cc295539cc24570c7505e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:47.372375Z","signature_b64":"a1dQqlcatKVOW0McdCIPzmYhN7qj//D3hwows2wbkRukgY1bBCEZzBnFiVJeI2+SwOLOx77Xl4Fbq9hNRnwmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b82b332caf49bd569be53dd313d17cf01bf47603ac0cc295539cc24570c7505e","last_reissued_at":"2026-07-05T11:53:47.371664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:47.371664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.01701","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":"2026-07-05T11:53:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"INHVCN0gmiFliMbysRqvZC3kEjJ0ZHodxkM/87PHCHO4KYH+17NPSYZLdHNwlmqaQ+RUwCGY90vjp17UdJ/XBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:50:18.125757Z"},"content_sha256":"719b5bf3d664e7c9697612316cfad5949566c675ca3743a1f42e20ff669734c7","schema_version":"1.0","event_id":"sha256:719b5bf3d664e7c9697612316cfad5949566c675ca3743a1f42e20ff669734c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XAVTGLFPJG6VNG7FHXJRHUL46A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Pruning by Information Maximization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoru Tan, Shizhen Zhao, Sitong Wu, Wei Huang, Xiaojuan Qi","submitted_at":"2025-06-02T14:06:42Z","abstract_excerpt":"In this paper, we present InfoMax, a novel data pruning method, also known as coreset selection, designed to maximize the information content of selected samples while minimizing redundancy. By doing so, InfoMax enhances the overall informativeness of the coreset. The information of individual samples is measured by importance scores, which capture their influence or difficulty in model learning. To quantify redundancy, we use pairwise sample similarities, based on the premise that similar samples contribute similarly to the learning process. We formalize the coreset selection problem as a dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01701","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/2506.01701/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":"2026-07-05T11:53:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4kyqFZpq6iPdlb05LE+QGP/T7rhCmhKdc8rcMO5blVmIstYwzsgHLfygUSlKeM4RDpoEoFC+gx0MdT0HY9uVAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:50:18.126289Z"},"content_sha256":"38566ca87d1e37e8e57a854df0eec8ba45a272c3e5bf9a64017d738ac74c515c","schema_version":"1.0","event_id":"sha256:38566ca87d1e37e8e57a854df0eec8ba45a272c3e5bf9a64017d738ac74c515c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XAVTGLFPJG6VNG7FHXJRHUL46A/bundle.json","state_url":"https://pith.science/pith/XAVTGLFPJG6VNG7FHXJRHUL46A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XAVTGLFPJG6VNG7FHXJRHUL46A/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":"2026-08-08T11:50:18Z","links":{"resolver":"https://pith.science/pith/XAVTGLFPJG6VNG7FHXJRHUL46A","bundle":"https://pith.science/pith/XAVTGLFPJG6VNG7FHXJRHUL46A/bundle.json","state":"https://pith.science/pith/XAVTGLFPJG6VNG7FHXJRHUL46A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XAVTGLFPJG6VNG7FHXJRHUL46A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XAVTGLFPJG6VNG7FHXJRHUL46A","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":"e44df43eb05b832b61d281e3ca322f4e54b865be79ca8b968745056daddd53a3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T14:06:42Z","title_canon_sha256":"df1d8fed4d821daec0f19f7548a0bb9ce0e3dcc6825c42d9ba429ba262dd3219"},"schema_version":"1.0","source":{"id":"2506.01701","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01701","created_at":"2026-07-05T11:53:47Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01701v2","created_at":"2026-07-05T11:53:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01701","created_at":"2026-07-05T11:53:47Z"},{"alias_kind":"pith_short_12","alias_value":"XAVTGLFPJG6V","created_at":"2026-07-05T11:53:47Z"},{"alias_kind":"pith_short_16","alias_value":"XAVTGLFPJG6VNG7F","created_at":"2026-07-05T11:53:47Z"},{"alias_kind":"pith_short_8","alias_value":"XAVTGLFP","created_at":"2026-07-05T11:53:47Z"}],"graph_snapshots":[{"event_id":"sha256:38566ca87d1e37e8e57a854df0eec8ba45a272c3e5bf9a64017d738ac74c515c","target":"graph","created_at":"2026-07-05T11:53:47Z","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/2506.01701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present InfoMax, a novel data pruning method, also known as coreset selection, designed to maximize the information content of selected samples while minimizing redundancy. By doing so, InfoMax enhances the overall informativeness of the coreset. The information of individual samples is measured by importance scores, which capture their influence or difficulty in model learning. To quantify redundancy, we use pairwise sample similarities, based on the premise that similar samples contribute similarly to the learning process. We formalize the coreset selection problem as a dis","authors_text":"Haoru Tan, Shizhen Zhao, Sitong Wu, Wei Huang, Xiaojuan Qi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T14:06:42Z","title":"Data Pruning by Information Maximization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01701","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":"sha256:719b5bf3d664e7c9697612316cfad5949566c675ca3743a1f42e20ff669734c7","target":"record","created_at":"2026-07-05T11:53:47Z","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":"e44df43eb05b832b61d281e3ca322f4e54b865be79ca8b968745056daddd53a3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T14:06:42Z","title_canon_sha256":"df1d8fed4d821daec0f19f7548a0bb9ce0e3dcc6825c42d9ba429ba262dd3219"},"schema_version":"1.0","source":{"id":"2506.01701","kind":"arxiv","version":2}},"canonical_sha256":"b82b332caf49bd569be53dd313d17cf01bf47603ac0cc295539cc24570c7505e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b82b332caf49bd569be53dd313d17cf01bf47603ac0cc295539cc24570c7505e","first_computed_at":"2026-07-05T11:53:47.371664Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:47.371664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a1dQqlcatKVOW0McdCIPzmYhN7qj//D3hwows2wbkRukgY1bBCEZzBnFiVJeI2+SwOLOx77Xl4Fbq9hNRnwmAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:47.372375Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01701","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:719b5bf3d664e7c9697612316cfad5949566c675ca3743a1f42e20ff669734c7","sha256:38566ca87d1e37e8e57a854df0eec8ba45a272c3e5bf9a64017d738ac74c515c"],"state_sha256":"10065841f7fcfbca9f66277b936182182c84dd5eeb6ed223e2eb462c0b0f361f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4z3rES1TAXFb27CNmxVyNSVxPwKZY11w8mBGauoOXSrHvNGxEX9KeR7v2uAzVPEMMeqoK9HsxXeAf+c8Sv6gCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:50:18.131661Z","bundle_sha256":"1cd3399f773872779da9508897d1cf1abd6418895198d72e236ad28f34c40f2f"}}