{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IND5BG7BSHJKAT5UIFTPXQ5SMI","short_pith_number":"pith:IND5BG7B","canonical_record":{"source":{"id":"2504.13835","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-18T17:59:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"35c3915f6d539e5da9bbf81cb26383b9880bc847a0e60f363ea13150c3609b8d","abstract_canon_sha256":"0f0250c98521ac30cb57bfeacd8634ee6c48fc195e3feb5cef56bda45d899524"},"schema_version":"1.0"},"canonical_sha256":"4347d09be191d2a04fb44166fbc3b26211a7178c044cdc75e95112592ea2188e","source":{"kind":"arxiv","id":"2504.13835","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13835","created_at":"2026-07-05T10:51:02Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13835v1","created_at":"2026-07-05T10:51:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13835","created_at":"2026-07-05T10:51:02Z"},{"alias_kind":"pith_short_12","alias_value":"IND5BG7BSHJK","created_at":"2026-07-05T10:51:02Z"},{"alias_kind":"pith_short_16","alias_value":"IND5BG7BSHJKAT5U","created_at":"2026-07-05T10:51:02Z"},{"alias_kind":"pith_short_8","alias_value":"IND5BG7B","created_at":"2026-07-05T10:51:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IND5BG7BSHJKAT5UIFTPXQ5SMI","target":"record","payload":{"canonical_record":{"source":{"id":"2504.13835","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-18T17:59:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"35c3915f6d539e5da9bbf81cb26383b9880bc847a0e60f363ea13150c3609b8d","abstract_canon_sha256":"0f0250c98521ac30cb57bfeacd8634ee6c48fc195e3feb5cef56bda45d899524"},"schema_version":"1.0"},"canonical_sha256":"4347d09be191d2a04fb44166fbc3b26211a7178c044cdc75e95112592ea2188e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:02.760800Z","signature_b64":"vBa5lbR//VGkVpA1PxkaHavYKaFlt840oCtVw8scSPIe2LdhcZFRebN4Fu01GZ5O0CAQonY8PmmODvdJpH3fBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4347d09be191d2a04fb44166fbc3b26211a7178c044cdc75e95112592ea2188e","last_reissued_at":"2026-07-05T10:51:02.760206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:02.760206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.13835","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":"2026-07-05T10:51:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dyooP9Y9G7CVIYVk6MjbMWIB4CeFctUOQYdXUH4n4YiNXODOlFMLcr9nYVJi9V1wLLZxulwfgQ5QckMX8mJ2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:16:27.867505Z"},"content_sha256":"75398f06fb296d6c2c11aa0d1ceffaa008bc4e817c395d80c1d9491edb28aee0","schema_version":"1.0","event_id":"sha256:75398f06fb296d6c2c11aa0d1ceffaa008bc4e817c395d80c1d9491edb28aee0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IND5BG7BSHJKAT5UIFTPXQ5SMI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haochen Ye, Kai Chen, Kai Hu, Yicheng Chen, Yining Li, Zerun Ma","submitted_at":"2025-04-18T17:59:46Z","abstract_excerpt":"Data quality and diversity are key to the construction of effective instruction-tuning datasets. %\nWith the increasing availability of open-source instruction-tuning datasets, it is advantageous to automatically select high-quality and diverse subsets from a vast amount of data. %\nExisting methods typically prioritize instance quality and use heuristic rules to maintain diversity. %\nHowever, this absence of a comprehensive view of the entire collection often leads to suboptimal results. %\nMoreover, heuristic rules generally focus on distance or clustering within the embedding space, which fail"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13835","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/2504.13835/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":"2026-07-05T10:51:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e5LQ56MSnngmFXEmnKz6KFe2CQ4wvEGsylyQLGco4gUB8mgMpkakSy7EwUCS6CyBRNgornGs/fdvZzuaUHlyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:16:27.868008Z"},"content_sha256":"72e9c6a1aa15d539e2c9db910234569a93477543057b47e0eef1535ebc7f6852","schema_version":"1.0","event_id":"sha256:72e9c6a1aa15d539e2c9db910234569a93477543057b47e0eef1535ebc7f6852"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IND5BG7BSHJKAT5UIFTPXQ5SMI/bundle.json","state_url":"https://pith.science/pith/IND5BG7BSHJKAT5UIFTPXQ5SMI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IND5BG7BSHJKAT5UIFTPXQ5SMI/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":"2026-08-09T15:16:27Z","links":{"resolver":"https://pith.science/pith/IND5BG7BSHJKAT5UIFTPXQ5SMI","bundle":"https://pith.science/pith/IND5BG7BSHJKAT5UIFTPXQ5SMI/bundle.json","state":"https://pith.science/pith/IND5BG7BSHJKAT5UIFTPXQ5SMI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IND5BG7BSHJKAT5UIFTPXQ5SMI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IND5BG7BSHJKAT5UIFTPXQ5SMI","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":"0f0250c98521ac30cb57bfeacd8634ee6c48fc195e3feb5cef56bda45d899524","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-18T17:59:46Z","title_canon_sha256":"35c3915f6d539e5da9bbf81cb26383b9880bc847a0e60f363ea13150c3609b8d"},"schema_version":"1.0","source":{"id":"2504.13835","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.13835","created_at":"2026-07-05T10:51:02Z"},{"alias_kind":"arxiv_version","alias_value":"2504.13835v1","created_at":"2026-07-05T10:51:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13835","created_at":"2026-07-05T10:51:02Z"},{"alias_kind":"pith_short_12","alias_value":"IND5BG7BSHJK","created_at":"2026-07-05T10:51:02Z"},{"alias_kind":"pith_short_16","alias_value":"IND5BG7BSHJKAT5U","created_at":"2026-07-05T10:51:02Z"},{"alias_kind":"pith_short_8","alias_value":"IND5BG7B","created_at":"2026-07-05T10:51:02Z"}],"graph_snapshots":[{"event_id":"sha256:72e9c6a1aa15d539e2c9db910234569a93477543057b47e0eef1535ebc7f6852","target":"graph","created_at":"2026-07-05T10:51:02Z","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/2504.13835/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data quality and diversity are key to the construction of effective instruction-tuning datasets. %\nWith the increasing availability of open-source instruction-tuning datasets, it is advantageous to automatically select high-quality and diverse subsets from a vast amount of data. %\nExisting methods typically prioritize instance quality and use heuristic rules to maintain diversity. %\nHowever, this absence of a comprehensive view of the entire collection often leads to suboptimal results. %\nMoreover, heuristic rules generally focus on distance or clustering within the embedding space, which fail","authors_text":"Haochen Ye, Kai Chen, Kai Hu, Yicheng Chen, Yining Li, Zerun Ma","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-18T17:59:46Z","title":"MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13835","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":"sha256:75398f06fb296d6c2c11aa0d1ceffaa008bc4e817c395d80c1d9491edb28aee0","target":"record","created_at":"2026-07-05T10:51:02Z","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":"0f0250c98521ac30cb57bfeacd8634ee6c48fc195e3feb5cef56bda45d899524","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-18T17:59:46Z","title_canon_sha256":"35c3915f6d539e5da9bbf81cb26383b9880bc847a0e60f363ea13150c3609b8d"},"schema_version":"1.0","source":{"id":"2504.13835","kind":"arxiv","version":1}},"canonical_sha256":"4347d09be191d2a04fb44166fbc3b26211a7178c044cdc75e95112592ea2188e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4347d09be191d2a04fb44166fbc3b26211a7178c044cdc75e95112592ea2188e","first_computed_at":"2026-07-05T10:51:02.760206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:02.760206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vBa5lbR//VGkVpA1PxkaHavYKaFlt840oCtVw8scSPIe2LdhcZFRebN4Fu01GZ5O0CAQonY8PmmODvdJpH3fBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:02.760800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.13835","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75398f06fb296d6c2c11aa0d1ceffaa008bc4e817c395d80c1d9491edb28aee0","sha256:72e9c6a1aa15d539e2c9db910234569a93477543057b47e0eef1535ebc7f6852"],"state_sha256":"3540113ab5168e1109504849bcf982f474f53da814d6e94d2d542e5650137c58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TqSWTrqt+zEtLwdsvV1PGSDs5p+rWV0yb+gWl1oxcdSd6kjsiqouRCI+2fRZB8wF7PEOOyY30N9Jaw0pxwflDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:16:27.871238Z","bundle_sha256":"8ac7ddd5faf3ecb8a302f3f9c0c7118dfe2b232a4004921d9a96911f8d4e509d"}}