{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4J7K7QLCJJRT6S3INMCKAHGC7L","short_pith_number":"pith:4J7K7QLC","canonical_record":{"source":{"id":"2403.18301","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-27T06:55:23Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"6d05a94718c93cb1779e3faa62b91ec29dc30eeb4d1507d679671ca37263d457","abstract_canon_sha256":"32a428261061ae8d7223065ac25946695e4554af6b92df33a6ad8f87c78ea386"},"schema_version":"1.0"},"canonical_sha256":"e27eafc1624a633f4b686b04a01cc2faf26124549567a56106c11cf92888bc87","source":{"kind":"arxiv","id":"2403.18301","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.18301","created_at":"2026-07-05T08:01:07Z"},{"alias_kind":"arxiv_version","alias_value":"2403.18301v1","created_at":"2026-07-05T08:01:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18301","created_at":"2026-07-05T08:01:07Z"},{"alias_kind":"pith_short_12","alias_value":"4J7K7QLCJJRT","created_at":"2026-07-05T08:01:07Z"},{"alias_kind":"pith_short_16","alias_value":"4J7K7QLCJJRT6S3I","created_at":"2026-07-05T08:01:07Z"},{"alias_kind":"pith_short_8","alias_value":"4J7K7QLC","created_at":"2026-07-05T08:01:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4J7K7QLCJJRT6S3INMCKAHGC7L","target":"record","payload":{"canonical_record":{"source":{"id":"2403.18301","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-27T06:55:23Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"6d05a94718c93cb1779e3faa62b91ec29dc30eeb4d1507d679671ca37263d457","abstract_canon_sha256":"32a428261061ae8d7223065ac25946695e4554af6b92df33a6ad8f87c78ea386"},"schema_version":"1.0"},"canonical_sha256":"e27eafc1624a633f4b686b04a01cc2faf26124549567a56106c11cf92888bc87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:07.624191Z","signature_b64":"Oo0NrvAm2CAxfxdIdKPVs+dxvmaOo4BTUUVy/ka4IxuoOAQithVrTL5oqlpXTmD1fEdJ+8DLT1GVCZokiRbbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e27eafc1624a633f4b686b04a01cc2faf26124549567a56106c11cf92888bc87","last_reissued_at":"2026-07-05T08:01:07.623776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:07.623776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.18301","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":"2026-07-05T08:01:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7DnUZDUgaUPmfngaz63s5Wo5KQ+J4NGdtbSjEGt6GAjCw4wS3ZfCxSqhp8/t1/JOheFv+ZgaS+o/el5lTdJQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:58:27.271970Z"},"content_sha256":"df2eac0b0c58846d31f6dde2e388f5a58691635da32ef5951e6d31d1adde6e7a","schema_version":"1.0","event_id":"sha256:df2eac0b0c58846d31f6dde2e388f5a58691635da32ef5951e6d31d1adde6e7a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4J7K7QLCJJRT6S3INMCKAHGC7L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Harsh Rangwani, Kunal Samanta, Sho Takemori, Shrinivas Ramasubramanian, Venkatesh Babu Radhakrishnan, Yuhei Umeda","submitted_at":"2024-03-27T06:55:23Z","abstract_excerpt":"The rise in internet usage has led to the generation of massive amounts of data, resulting in the adoption of various supervised and semi-supervised machine learning algorithms, which can effectively utilize the colossal amount of data to train models. However, before deploying these models in the real world, these must be strictly evaluated on performance measures like worst-case recall and satisfy constraints such as fairness. We find that current state-of-the-art empirical techniques offer sub-optimal performance on these practical, non-decomposable performance objectives. On the other hand"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18301","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/2403.18301/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":"2026-07-05T08:01:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I1eGX/7ahUSyJ/ZWC09ZyXjDhHK5FVjXsHZ4zfzeNxJchOed30QH9LJlRdF3EUbQUdSYqVdNgvwdoE3jqjwdAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:58:27.272472Z"},"content_sha256":"8d6bd0584953605123d5b97b57fda7da96a9c7a2aab71e4ed78ea33b229bc087","schema_version":"1.0","event_id":"sha256:8d6bd0584953605123d5b97b57fda7da96a9c7a2aab71e4ed78ea33b229bc087"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4J7K7QLCJJRT6S3INMCKAHGC7L/bundle.json","state_url":"https://pith.science/pith/4J7K7QLCJJRT6S3INMCKAHGC7L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4J7K7QLCJJRT6S3INMCKAHGC7L/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":"2026-08-05T04:58:27Z","links":{"resolver":"https://pith.science/pith/4J7K7QLCJJRT6S3INMCKAHGC7L","bundle":"https://pith.science/pith/4J7K7QLCJJRT6S3INMCKAHGC7L/bundle.json","state":"https://pith.science/pith/4J7K7QLCJJRT6S3INMCKAHGC7L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4J7K7QLCJJRT6S3INMCKAHGC7L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4J7K7QLCJJRT6S3INMCKAHGC7L","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":"32a428261061ae8d7223065ac25946695e4554af6b92df33a6ad8f87c78ea386","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-27T06:55:23Z","title_canon_sha256":"6d05a94718c93cb1779e3faa62b91ec29dc30eeb4d1507d679671ca37263d457"},"schema_version":"1.0","source":{"id":"2403.18301","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.18301","created_at":"2026-07-05T08:01:07Z"},{"alias_kind":"arxiv_version","alias_value":"2403.18301v1","created_at":"2026-07-05T08:01:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18301","created_at":"2026-07-05T08:01:07Z"},{"alias_kind":"pith_short_12","alias_value":"4J7K7QLCJJRT","created_at":"2026-07-05T08:01:07Z"},{"alias_kind":"pith_short_16","alias_value":"4J7K7QLCJJRT6S3I","created_at":"2026-07-05T08:01:07Z"},{"alias_kind":"pith_short_8","alias_value":"4J7K7QLC","created_at":"2026-07-05T08:01:07Z"}],"graph_snapshots":[{"event_id":"sha256:8d6bd0584953605123d5b97b57fda7da96a9c7a2aab71e4ed78ea33b229bc087","target":"graph","created_at":"2026-07-05T08:01:07Z","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/2403.18301/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rise in internet usage has led to the generation of massive amounts of data, resulting in the adoption of various supervised and semi-supervised machine learning algorithms, which can effectively utilize the colossal amount of data to train models. However, before deploying these models in the real world, these must be strictly evaluated on performance measures like worst-case recall and satisfy constraints such as fairness. We find that current state-of-the-art empirical techniques offer sub-optimal performance on these practical, non-decomposable performance objectives. On the other hand","authors_text":"Harsh Rangwani, Kunal Samanta, Sho Takemori, Shrinivas Ramasubramanian, Venkatesh Babu Radhakrishnan, Yuhei Umeda","cross_cats":["cs.AI","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-27T06:55:23Z","title":"Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18301","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:df2eac0b0c58846d31f6dde2e388f5a58691635da32ef5951e6d31d1adde6e7a","target":"record","created_at":"2026-07-05T08:01:07Z","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":"32a428261061ae8d7223065ac25946695e4554af6b92df33a6ad8f87c78ea386","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-27T06:55:23Z","title_canon_sha256":"6d05a94718c93cb1779e3faa62b91ec29dc30eeb4d1507d679671ca37263d457"},"schema_version":"1.0","source":{"id":"2403.18301","kind":"arxiv","version":1}},"canonical_sha256":"e27eafc1624a633f4b686b04a01cc2faf26124549567a56106c11cf92888bc87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e27eafc1624a633f4b686b04a01cc2faf26124549567a56106c11cf92888bc87","first_computed_at":"2026-07-05T08:01:07.623776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:07.623776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Oo0NrvAm2CAxfxdIdKPVs+dxvmaOo4BTUUVy/ka4IxuoOAQithVrTL5oqlpXTmD1fEdJ+8DLT1GVCZokiRbbAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:07.624191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.18301","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df2eac0b0c58846d31f6dde2e388f5a58691635da32ef5951e6d31d1adde6e7a","sha256:8d6bd0584953605123d5b97b57fda7da96a9c7a2aab71e4ed78ea33b229bc087"],"state_sha256":"6d1e0e90f3e1f8765731a006a7f8792041dc79bf77c98b322e034e5c15013dde"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P4vJxZwjFhDgnWarW3nV6GtrZtrt0d1jhe1APXvKigWffgxk08ZsT2MMtRQ5y2/l1H60J6SbW6tbjZnUYmkTCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:58:27.277889Z","bundle_sha256":"87a9654f07a10df9439732983b95c93554ff3ffc387f52f8415fc545c79930c1"}}