{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JNLFFXM3K7DLAUJSE2JEZIB3YU","short_pith_number":"pith:JNLFFXM3","canonical_record":{"source":{"id":"2408.03560","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-07T05:48:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"eb9ad73cf01b09bf8b3db2e91be89c4785e985a5f8429a3b01b4208cc88959ec","abstract_canon_sha256":"e9986fc43be1cb88ec17785e19209a22c8e983d2787a0456bee9c6634713cba8"},"schema_version":"1.0"},"canonical_sha256":"4b5652dd9b57c6b0513226924ca03bc5371048cc73e9cd9816dca7d692fef3f1","source":{"kind":"arxiv","id":"2408.03560","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.03560","created_at":"2026-07-05T09:15:13Z"},{"alias_kind":"arxiv_version","alias_value":"2408.03560v2","created_at":"2026-07-05T09:15:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03560","created_at":"2026-07-05T09:15:13Z"},{"alias_kind":"pith_short_12","alias_value":"JNLFFXM3K7DL","created_at":"2026-07-05T09:15:13Z"},{"alias_kind":"pith_short_16","alias_value":"JNLFFXM3K7DLAUJS","created_at":"2026-07-05T09:15:13Z"},{"alias_kind":"pith_short_8","alias_value":"JNLFFXM3","created_at":"2026-07-05T09:15:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JNLFFXM3K7DLAUJSE2JEZIB3YU","target":"record","payload":{"canonical_record":{"source":{"id":"2408.03560","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-07T05:48:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"eb9ad73cf01b09bf8b3db2e91be89c4785e985a5f8429a3b01b4208cc88959ec","abstract_canon_sha256":"e9986fc43be1cb88ec17785e19209a22c8e983d2787a0456bee9c6634713cba8"},"schema_version":"1.0"},"canonical_sha256":"4b5652dd9b57c6b0513226924ca03bc5371048cc73e9cd9816dca7d692fef3f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:13.822795Z","signature_b64":"rbXslx/T10Q31B8yePaXiRllkAWGixqZ/VinNCr3hOxcXZ4es05krtWdZlAIykXPM+MONB5MoFsnQ646H84eDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b5652dd9b57c6b0513226924ca03bc5371048cc73e9cd9816dca7d692fef3f1","last_reissued_at":"2026-07-05T09:15:13.822274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:13.822274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.03560","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":"2026-07-05T09:15:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h4akT+ZBDbSn/vTrHvqoy9tspMdkeagYO6XVqWR66dFXqyJLsrALQuPa5hWw8dj90raKJbG263KL2slK+ml2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:15:26.047685Z"},"content_sha256":"88563ec0066cc8afb9599f6840d4d8a9a1bdf30c50a864ebaca17d99cfdb013a","schema_version":"1.0","event_id":"sha256:88563ec0066cc8afb9599f6840d4d8a9a1bdf30c50a864ebaca17d99cfdb013a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JNLFFXM3K7DLAUJSE2JEZIB3YU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"In2Core: Leveraging Influence Functions for Coreset Selection in Instruction Finetuning of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ayrton San Joaquin, Bin Wang, Brian Lim, Nancy F. Chen, Nicholas Asher, Philippe Muller, Zhengyuan Liu","submitted_at":"2024-08-07T05:48:05Z","abstract_excerpt":"Despite advancements, fine-tuning Large Language Models (LLMs) remains costly due to the extensive parameter count and substantial data requirements for model generalization. Accessibility to computing resources remains a barrier for the open-source community. To address this challenge, we propose the In2Core algorithm, which selects a coreset by analyzing the correlation between training and evaluation samples with a trained model. Notably, we assess the model's internal gradients to estimate this relationship, aiming to rank the contribution of each training point. To enhance efficiency, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03560","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/2408.03560/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":"2026-07-05T09:15:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YNLtSCUVNG4CAPsSSUm6m/tCShxlkFQ4Pgxl8QmT5O8A0c5GO3Pn3nnFZiS0arRTCr0Ru2eQ12b93B8EiNOwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:15:26.048200Z"},"content_sha256":"1335275a0859fefeaac2fcd7f430ac70bcf91d46d3d085c993b1166eb844ea57","schema_version":"1.0","event_id":"sha256:1335275a0859fefeaac2fcd7f430ac70bcf91d46d3d085c993b1166eb844ea57"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JNLFFXM3K7DLAUJSE2JEZIB3YU/bundle.json","state_url":"https://pith.science/pith/JNLFFXM3K7DLAUJSE2JEZIB3YU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JNLFFXM3K7DLAUJSE2JEZIB3YU/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":"2026-08-08T13:15:26Z","links":{"resolver":"https://pith.science/pith/JNLFFXM3K7DLAUJSE2JEZIB3YU","bundle":"https://pith.science/pith/JNLFFXM3K7DLAUJSE2JEZIB3YU/bundle.json","state":"https://pith.science/pith/JNLFFXM3K7DLAUJSE2JEZIB3YU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JNLFFXM3K7DLAUJSE2JEZIB3YU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JNLFFXM3K7DLAUJSE2JEZIB3YU","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":"e9986fc43be1cb88ec17785e19209a22c8e983d2787a0456bee9c6634713cba8","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-07T05:48:05Z","title_canon_sha256":"eb9ad73cf01b09bf8b3db2e91be89c4785e985a5f8429a3b01b4208cc88959ec"},"schema_version":"1.0","source":{"id":"2408.03560","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.03560","created_at":"2026-07-05T09:15:13Z"},{"alias_kind":"arxiv_version","alias_value":"2408.03560v2","created_at":"2026-07-05T09:15:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03560","created_at":"2026-07-05T09:15:13Z"},{"alias_kind":"pith_short_12","alias_value":"JNLFFXM3K7DL","created_at":"2026-07-05T09:15:13Z"},{"alias_kind":"pith_short_16","alias_value":"JNLFFXM3K7DLAUJS","created_at":"2026-07-05T09:15:13Z"},{"alias_kind":"pith_short_8","alias_value":"JNLFFXM3","created_at":"2026-07-05T09:15:13Z"}],"graph_snapshots":[{"event_id":"sha256:1335275a0859fefeaac2fcd7f430ac70bcf91d46d3d085c993b1166eb844ea57","target":"graph","created_at":"2026-07-05T09:15:13Z","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/2408.03560/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite advancements, fine-tuning Large Language Models (LLMs) remains costly due to the extensive parameter count and substantial data requirements for model generalization. Accessibility to computing resources remains a barrier for the open-source community. To address this challenge, we propose the In2Core algorithm, which selects a coreset by analyzing the correlation between training and evaluation samples with a trained model. Notably, we assess the model's internal gradients to estimate this relationship, aiming to rank the contribution of each training point. To enhance efficiency, we ","authors_text":"Ayrton San Joaquin, Bin Wang, Brian Lim, Nancy F. Chen, Nicholas Asher, Philippe Muller, Zhengyuan Liu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-07T05:48:05Z","title":"In2Core: Leveraging Influence Functions for Coreset Selection in Instruction Finetuning of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03560","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":"sha256:88563ec0066cc8afb9599f6840d4d8a9a1bdf30c50a864ebaca17d99cfdb013a","target":"record","created_at":"2026-07-05T09:15:13Z","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":"e9986fc43be1cb88ec17785e19209a22c8e983d2787a0456bee9c6634713cba8","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-07T05:48:05Z","title_canon_sha256":"eb9ad73cf01b09bf8b3db2e91be89c4785e985a5f8429a3b01b4208cc88959ec"},"schema_version":"1.0","source":{"id":"2408.03560","kind":"arxiv","version":2}},"canonical_sha256":"4b5652dd9b57c6b0513226924ca03bc5371048cc73e9cd9816dca7d692fef3f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b5652dd9b57c6b0513226924ca03bc5371048cc73e9cd9816dca7d692fef3f1","first_computed_at":"2026-07-05T09:15:13.822274Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:13.822274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rbXslx/T10Q31B8yePaXiRllkAWGixqZ/VinNCr3hOxcXZ4es05krtWdZlAIykXPM+MONB5MoFsnQ646H84eDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:13.822795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.03560","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88563ec0066cc8afb9599f6840d4d8a9a1bdf30c50a864ebaca17d99cfdb013a","sha256:1335275a0859fefeaac2fcd7f430ac70bcf91d46d3d085c993b1166eb844ea57"],"state_sha256":"84680c88938a9847a681c61e2253a2bbc8bfed54ad86ae19b5f419331fe9679a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mYVen9g9P5OhcPmEqTZmSnP7UIZZmziS38c5RwbcmN+vxTANdGHha62XF/5c6Sd7rDBSJbnEY3iwDlry9lajBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:15:26.052834Z","bundle_sha256":"da051ef08bbaf17f9e55aa8c7c1c681b3d9a27c12cc9bdb80069f20fa6aee2a9"}}