{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UBFVPX5H6LWNHNTXEE6RPCAMI2","short_pith_number":"pith:UBFVPX5H","canonical_record":{"source":{"id":"2507.22186","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-29T19:29:52Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"75b4b3283c1abe0f596b163ebba6f11e88b26b29856ac2bff4fcd959ace0b5cd","abstract_canon_sha256":"43b0a2d864f668629164040675e104e0e2ca35ad4b6e46ef46e095572a179324"},"schema_version":"1.0"},"canonical_sha256":"a04b57dfa7f2ecd3b677213d17880c46af349ed82492e387e52dbbc39becd2ec","source":{"kind":"arxiv","id":"2507.22186","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22186","created_at":"2026-07-05T11:46:46Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22186v2","created_at":"2026-07-05T11:46:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22186","created_at":"2026-07-05T11:46:46Z"},{"alias_kind":"pith_short_12","alias_value":"UBFVPX5H6LWN","created_at":"2026-07-05T11:46:46Z"},{"alias_kind":"pith_short_16","alias_value":"UBFVPX5H6LWNHNTX","created_at":"2026-07-05T11:46:46Z"},{"alias_kind":"pith_short_8","alias_value":"UBFVPX5H","created_at":"2026-07-05T11:46:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UBFVPX5H6LWNHNTXEE6RPCAMI2","target":"record","payload":{"canonical_record":{"source":{"id":"2507.22186","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-29T19:29:52Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"75b4b3283c1abe0f596b163ebba6f11e88b26b29856ac2bff4fcd959ace0b5cd","abstract_canon_sha256":"43b0a2d864f668629164040675e104e0e2ca35ad4b6e46ef46e095572a179324"},"schema_version":"1.0"},"canonical_sha256":"a04b57dfa7f2ecd3b677213d17880c46af349ed82492e387e52dbbc39becd2ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:46.117103Z","signature_b64":"S0ZrGzIal8DwL3UCFvDWuDYa+08biN4ia9B2ZpOqwkc7D1S28dedjYhyyIpCqtlUP+xFHF6vRQw1RuW6e2WNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a04b57dfa7f2ecd3b677213d17880c46af349ed82492e387e52dbbc39becd2ec","last_reissued_at":"2026-07-05T11:46:46.116578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:46.116578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.22186","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":"2026-07-05T11:46:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ldIJnP2fu3sNPn9goEqKCvT1ZLEYPefBlzx1sZoa+NrMp0+x8PV/GyLCEXp36NYCIESNiePACCKzACDrUFkIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:19:30.494739Z"},"content_sha256":"7c605a68093d7b00533978bdb746e12d28595568a14085a511e444eef68905b9","schema_version":"1.0","event_id":"sha256:7c605a68093d7b00533978bdb746e12d28595568a14085a511e444eef68905b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UBFVPX5H6LWNHNTXEE6RPCAMI2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SourceSplice: Source Selection for Machine Learning Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.LG","authors_text":"Ambarish Singh, Romila Pradhan","submitted_at":"2025-07-29T19:29:52Z","abstract_excerpt":"Data quality plays a pivotal role in the predictive performance of machine learning (ML) tasks - a challenge amplified by the deluge of data sources available in modern organizations. Prior work in data discovery largely focus on metadata matching, semantic similarity or identifying tables that should be joined to answer a particular query, but do not consider source quality for high performance of the downstream ML task. This paper addresses the problem of determining the best subset of data sources that must be combined to construct the underlying training dataset for a given ML task. We pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22186","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/2507.22186/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":"2026-07-05T11:46:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vPuIT0xY+H6lNWDTTcIwyupks2FMVtEkycCrrGXvQDQottiL3uQ+NXVAu2YYKlGPfeEnOa8MUAmv/shV8/dFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:19:30.495343Z"},"content_sha256":"0ce9a5aa9aac144006e9c91e4321b93c5e8e4cd34b476257ce2f56147c7958a7","schema_version":"1.0","event_id":"sha256:0ce9a5aa9aac144006e9c91e4321b93c5e8e4cd34b476257ce2f56147c7958a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UBFVPX5H6LWNHNTXEE6RPCAMI2/bundle.json","state_url":"https://pith.science/pith/UBFVPX5H6LWNHNTXEE6RPCAMI2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UBFVPX5H6LWNHNTXEE6RPCAMI2/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":"2026-08-08T09:19:30Z","links":{"resolver":"https://pith.science/pith/UBFVPX5H6LWNHNTXEE6RPCAMI2","bundle":"https://pith.science/pith/UBFVPX5H6LWNHNTXEE6RPCAMI2/bundle.json","state":"https://pith.science/pith/UBFVPX5H6LWNHNTXEE6RPCAMI2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UBFVPX5H6LWNHNTXEE6RPCAMI2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UBFVPX5H6LWNHNTXEE6RPCAMI2","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":"43b0a2d864f668629164040675e104e0e2ca35ad4b6e46ef46e095572a179324","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-29T19:29:52Z","title_canon_sha256":"75b4b3283c1abe0f596b163ebba6f11e88b26b29856ac2bff4fcd959ace0b5cd"},"schema_version":"1.0","source":{"id":"2507.22186","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22186","created_at":"2026-07-05T11:46:46Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22186v2","created_at":"2026-07-05T11:46:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22186","created_at":"2026-07-05T11:46:46Z"},{"alias_kind":"pith_short_12","alias_value":"UBFVPX5H6LWN","created_at":"2026-07-05T11:46:46Z"},{"alias_kind":"pith_short_16","alias_value":"UBFVPX5H6LWNHNTX","created_at":"2026-07-05T11:46:46Z"},{"alias_kind":"pith_short_8","alias_value":"UBFVPX5H","created_at":"2026-07-05T11:46:46Z"}],"graph_snapshots":[{"event_id":"sha256:0ce9a5aa9aac144006e9c91e4321b93c5e8e4cd34b476257ce2f56147c7958a7","target":"graph","created_at":"2026-07-05T11:46:46Z","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/2507.22186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data quality plays a pivotal role in the predictive performance of machine learning (ML) tasks - a challenge amplified by the deluge of data sources available in modern organizations. Prior work in data discovery largely focus on metadata matching, semantic similarity or identifying tables that should be joined to answer a particular query, but do not consider source quality for high performance of the downstream ML task. This paper addresses the problem of determining the best subset of data sources that must be combined to construct the underlying training dataset for a given ML task. We pro","authors_text":"Ambarish Singh, Romila Pradhan","cross_cats":["cs.AI","cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-29T19:29:52Z","title":"SourceSplice: Source Selection for Machine Learning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22186","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":"sha256:7c605a68093d7b00533978bdb746e12d28595568a14085a511e444eef68905b9","target":"record","created_at":"2026-07-05T11:46:46Z","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":"43b0a2d864f668629164040675e104e0e2ca35ad4b6e46ef46e095572a179324","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-29T19:29:52Z","title_canon_sha256":"75b4b3283c1abe0f596b163ebba6f11e88b26b29856ac2bff4fcd959ace0b5cd"},"schema_version":"1.0","source":{"id":"2507.22186","kind":"arxiv","version":2}},"canonical_sha256":"a04b57dfa7f2ecd3b677213d17880c46af349ed82492e387e52dbbc39becd2ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a04b57dfa7f2ecd3b677213d17880c46af349ed82492e387e52dbbc39becd2ec","first_computed_at":"2026-07-05T11:46:46.116578Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:46.116578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S0ZrGzIal8DwL3UCFvDWuDYa+08biN4ia9B2ZpOqwkc7D1S28dedjYhyyIpCqtlUP+xFHF6vRQw1RuW6e2WNBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:46.117103Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.22186","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c605a68093d7b00533978bdb746e12d28595568a14085a511e444eef68905b9","sha256:0ce9a5aa9aac144006e9c91e4321b93c5e8e4cd34b476257ce2f56147c7958a7"],"state_sha256":"7ee667e36feb36cdd909ccb5173a49f1af2981d9623498273075177dfd54f93a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t5c7JDg1i8GKCQEW0dSCNfzFwWYHt5k64JJhFSaysVArYDFHfzmGWPXlwFAOLq/e3ep+Tv6Gvf3S+o+hvfpWBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:19:30.499392Z","bundle_sha256":"6680d33604f999d9e4862a8cd68b4c37b0e6a36d62b9b895330f6b614fef7c12"}}