{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CRQSDZVNGLPJQNN2YGVJDVMGSU","short_pith_number":"pith:CRQSDZVN","canonical_record":{"source":{"id":"2410.11303","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T05:54:17Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7628271d6afa73f4e114a0d6da3ead60ce6f2490b8169e756075c675c8acbddb","abstract_canon_sha256":"012bfb457cb336744933cbaa3e31f935ffac3da0bbbfbcb66aa48438fd53dda9"},"schema_version":"1.0"},"canonical_sha256":"146121e6ad32de9835bac1aa91d5869508a67b6f23babcf605fe2c9081541dc4","source":{"kind":"arxiv","id":"2410.11303","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11303","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11303v3","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11303","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_12","alias_value":"CRQSDZVNGLPJ","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_16","alias_value":"CRQSDZVNGLPJQNN2","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_8","alias_value":"CRQSDZVN","created_at":"2026-07-05T09:54:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CRQSDZVNGLPJQNN2YGVJDVMGSU","target":"record","payload":{"canonical_record":{"source":{"id":"2410.11303","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T05:54:17Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7628271d6afa73f4e114a0d6da3ead60ce6f2490b8169e756075c675c8acbddb","abstract_canon_sha256":"012bfb457cb336744933cbaa3e31f935ffac3da0bbbfbcb66aa48438fd53dda9"},"schema_version":"1.0"},"canonical_sha256":"146121e6ad32de9835bac1aa91d5869508a67b6f23babcf605fe2c9081541dc4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:05.036942Z","signature_b64":"kipJHA/A6uQoj7zd1NpiUm6kyceJOY8UduyHdZX2tDTuiRf6n9DDSUuQHQjJTFjTpO24EUOqOW776MRUWJ9nDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"146121e6ad32de9835bac1aa91d5869508a67b6f23babcf605fe2c9081541dc4","last_reissued_at":"2026-07-05T09:54:05.036446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:05.036446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.11303","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":"2026-07-05T09:54:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0LqvrI4lbZ3IFYY3JBUL4KGuNxpdPYJR39iEKDS89aIMw88q9/QNJHijS35hhjno7FhNQg61ClPJC3LAYHZPDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:48:03.966780Z"},"content_sha256":"881e80b404b87c1a5b9bd2c2dba8e70e4092af9f882e7456507d4f8ea2216e26","schema_version":"1.0","event_id":"sha256:881e80b404b87c1a5b9bd2c2dba8e70e4092af9f882e7456507d4f8ea2216e26"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CRQSDZVNGLPJQNN2YGVJDVMGSU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TSDS: Data Selection for Task-Specific Model Finetuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Amin Karbasi, Theodoros Rekatsinas, Zifan Liu","submitted_at":"2024-10-15T05:54:17Z","abstract_excerpt":"Finetuning foundation models for specific tasks is an emerging paradigm in modern machine learning. The efficacy of task-specific finetuning largely depends on the selection of appropriate training data. We present TSDS (Task-Specific Data Selection), a framework to select data for task-specific model finetuning, guided by a small but representative set of examples from the target task. To do so, we formulate data selection for task-specific finetuning as an optimization problem with a distribution alignment loss based on optimal transport to capture the discrepancy between the selected data a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11303","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/2410.11303/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":"2026-07-05T09:54:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l1R10A3x4ZvxVaO7Z1rTi+fWe4GmnSneLfyaf69vwBIVJG3q5/NPNKeOzJB+57BrtngETuKxJgRCVQc0Hl4KDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:48:03.967311Z"},"content_sha256":"0a4f9d8cb1f1ac8685434596fe037b49d3aaf41ed9cffa1c166af8052a78801c","schema_version":"1.0","event_id":"sha256:0a4f9d8cb1f1ac8685434596fe037b49d3aaf41ed9cffa1c166af8052a78801c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CRQSDZVNGLPJQNN2YGVJDVMGSU/bundle.json","state_url":"https://pith.science/pith/CRQSDZVNGLPJQNN2YGVJDVMGSU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CRQSDZVNGLPJQNN2YGVJDVMGSU/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":"2026-08-09T19:48:03Z","links":{"resolver":"https://pith.science/pith/CRQSDZVNGLPJQNN2YGVJDVMGSU","bundle":"https://pith.science/pith/CRQSDZVNGLPJQNN2YGVJDVMGSU/bundle.json","state":"https://pith.science/pith/CRQSDZVNGLPJQNN2YGVJDVMGSU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CRQSDZVNGLPJQNN2YGVJDVMGSU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CRQSDZVNGLPJQNN2YGVJDVMGSU","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":"012bfb457cb336744933cbaa3e31f935ffac3da0bbbfbcb66aa48438fd53dda9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T05:54:17Z","title_canon_sha256":"7628271d6afa73f4e114a0d6da3ead60ce6f2490b8169e756075c675c8acbddb"},"schema_version":"1.0","source":{"id":"2410.11303","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11303","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11303v3","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11303","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_12","alias_value":"CRQSDZVNGLPJ","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_16","alias_value":"CRQSDZVNGLPJQNN2","created_at":"2026-07-05T09:54:05Z"},{"alias_kind":"pith_short_8","alias_value":"CRQSDZVN","created_at":"2026-07-05T09:54:05Z"}],"graph_snapshots":[{"event_id":"sha256:0a4f9d8cb1f1ac8685434596fe037b49d3aaf41ed9cffa1c166af8052a78801c","target":"graph","created_at":"2026-07-05T09:54:05Z","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/2410.11303/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Finetuning foundation models for specific tasks is an emerging paradigm in modern machine learning. The efficacy of task-specific finetuning largely depends on the selection of appropriate training data. We present TSDS (Task-Specific Data Selection), a framework to select data for task-specific model finetuning, guided by a small but representative set of examples from the target task. To do so, we formulate data selection for task-specific finetuning as an optimization problem with a distribution alignment loss based on optimal transport to capture the discrepancy between the selected data a","authors_text":"Amin Karbasi, Theodoros Rekatsinas, Zifan Liu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T05:54:17Z","title":"TSDS: Data Selection for Task-Specific Model Finetuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11303","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":"sha256:881e80b404b87c1a5b9bd2c2dba8e70e4092af9f882e7456507d4f8ea2216e26","target":"record","created_at":"2026-07-05T09:54:05Z","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":"012bfb457cb336744933cbaa3e31f935ffac3da0bbbfbcb66aa48438fd53dda9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T05:54:17Z","title_canon_sha256":"7628271d6afa73f4e114a0d6da3ead60ce6f2490b8169e756075c675c8acbddb"},"schema_version":"1.0","source":{"id":"2410.11303","kind":"arxiv","version":3}},"canonical_sha256":"146121e6ad32de9835bac1aa91d5869508a67b6f23babcf605fe2c9081541dc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"146121e6ad32de9835bac1aa91d5869508a67b6f23babcf605fe2c9081541dc4","first_computed_at":"2026-07-05T09:54:05.036446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:05.036446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kipJHA/A6uQoj7zd1NpiUm6kyceJOY8UduyHdZX2tDTuiRf6n9DDSUuQHQjJTFjTpO24EUOqOW776MRUWJ9nDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:05.036942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.11303","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:881e80b404b87c1a5b9bd2c2dba8e70e4092af9f882e7456507d4f8ea2216e26","sha256:0a4f9d8cb1f1ac8685434596fe037b49d3aaf41ed9cffa1c166af8052a78801c"],"state_sha256":"0bea2378dfecb88650c78da6cb64aeb88b57d14916c93fa5fc8283e9e1c7eec5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IhSJUb0xquAfl5EyDeiIAHtmpGbmZJVvIBdne1IE+q5opKJXofDBwmInXpsEOFUSibB2tIERG160YXFmikKvBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:48:03.970694Z","bundle_sha256":"9ddb2ef4e7f84255533e6f83197fbcdc9fea1eb3c29b4c606038ff66ccab137e"}}