{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UUHESACCHYYXASCIEHKDQSUZBA","short_pith_number":"pith:UUHESACC","canonical_record":{"source":{"id":"2608.10579","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-11T07:05:05Z","cross_cats_sorted":[],"title_canon_sha256":"92d247d101cd028daa41716d9f3333258c58b082115e7b452bdfde782a3fcbc2","abstract_canon_sha256":"abed3db11543b98d04a9300f8e99b880a820d5bd88134340afdd81fa9a1a3040"},"schema_version":"1.0"},"canonical_sha256":"a50e4900423e3170484821d4384a99083189261cbfb0e0c583b36ceadad874e4","source":{"kind":"arxiv","id":"2608.10579","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10579","created_at":"2026-08-12T01:22:47Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10579v1","created_at":"2026-08-12T01:22:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10579","created_at":"2026-08-12T01:22:47Z"},{"alias_kind":"pith_short_12","alias_value":"UUHESACCHYYX","created_at":"2026-08-12T01:22:47Z"},{"alias_kind":"pith_short_16","alias_value":"UUHESACCHYYXASCI","created_at":"2026-08-12T01:22:47Z"},{"alias_kind":"pith_short_8","alias_value":"UUHESACC","created_at":"2026-08-12T01:22:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UUHESACCHYYXASCIEHKDQSUZBA","target":"record","payload":{"canonical_record":{"source":{"id":"2608.10579","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-11T07:05:05Z","cross_cats_sorted":[],"title_canon_sha256":"92d247d101cd028daa41716d9f3333258c58b082115e7b452bdfde782a3fcbc2","abstract_canon_sha256":"abed3db11543b98d04a9300f8e99b880a820d5bd88134340afdd81fa9a1a3040"},"schema_version":"1.0"},"canonical_sha256":"a50e4900423e3170484821d4384a99083189261cbfb0e0c583b36ceadad874e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:22:47.937725Z","signature_b64":"AK1JCUpkNEdLjm+cBKJ/Az+cZKC54spas/Fot212C87IjYQeexZftBsQncJ4l+2XybUknKpX8hu+g278lTiGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a50e4900423e3170484821d4384a99083189261cbfb0e0c583b36ceadad874e4","last_reissued_at":"2026-08-12T01:22:47.935427Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:22:47.935427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.10579","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":"2026-08-12T01:22:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wTsAQ3UD9+r8KMWanNuS/Gk7XvpXTCDW2z03P5QMH248ypM9RRXE2QKJ9V+QbyfjNt2ptgGGkFQQpgWR+WccDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:04:08.570257Z"},"content_sha256":"a8a208d4d94c00b9631be544b72965e24959d1d515ecfb1a110791193f66a541","schema_version":"1.0","event_id":"sha256:a8a208d4d94c00b9631be544b72965e24959d1d515ecfb1a110791193f66a541"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UUHESACCHYYXASCIEHKDQSUZBA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Agentic Instruction Data Selection: Let DataMaster Interpret Your Intent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fanqi Zhou, Gong Cheng, Qiaosheng Chen, Zixian Huang","submitted_at":"2026-08-11T07:05:05Z","abstract_excerpt":"Although existing instruction data selection methods have introduced various metrics, the inherent complexity of real-world datasets makes it impractical for any single metric to generalize across all scenarios. Developers are thus often forced to manually inspect data and craft heuristic rules for each new application---a tedious and error-prone process. In this paper, we propose a paradigm shift from manual configuration to automated orchestration via the Instruction Data Selection Agent (DataMaster), which interprets user intent and autonomously composes optimal selection strategies. By all"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10579","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/2608.10579/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":"2026-08-12T01:22:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yx2aHmUVM/7wXGFpaC56CRj/ym3xSqowOeD9gmwWVKbQsfCpv1kS+Dfc3X0bfns7Yp8rrzGVCzUKQ48xJtt5Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T09:04:08.570579Z"},"content_sha256":"1e541c41561a2b233298da0f7d89007902c2f5ac4483e884ae0073e1eb7e3dea","schema_version":"1.0","event_id":"sha256:1e541c41561a2b233298da0f7d89007902c2f5ac4483e884ae0073e1eb7e3dea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UUHESACCHYYXASCIEHKDQSUZBA/bundle.json","state_url":"https://pith.science/pith/UUHESACCHYYXASCIEHKDQSUZBA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UUHESACCHYYXASCIEHKDQSUZBA/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":"2026-08-14T09:04:08Z","links":{"resolver":"https://pith.science/pith/UUHESACCHYYXASCIEHKDQSUZBA","bundle":"https://pith.science/pith/UUHESACCHYYXASCIEHKDQSUZBA/bundle.json","state":"https://pith.science/pith/UUHESACCHYYXASCIEHKDQSUZBA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UUHESACCHYYXASCIEHKDQSUZBA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UUHESACCHYYXASCIEHKDQSUZBA","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":"abed3db11543b98d04a9300f8e99b880a820d5bd88134340afdd81fa9a1a3040","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-11T07:05:05Z","title_canon_sha256":"92d247d101cd028daa41716d9f3333258c58b082115e7b452bdfde782a3fcbc2"},"schema_version":"1.0","source":{"id":"2608.10579","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10579","created_at":"2026-08-12T01:22:47Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10579v1","created_at":"2026-08-12T01:22:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10579","created_at":"2026-08-12T01:22:47Z"},{"alias_kind":"pith_short_12","alias_value":"UUHESACCHYYX","created_at":"2026-08-12T01:22:47Z"},{"alias_kind":"pith_short_16","alias_value":"UUHESACCHYYXASCI","created_at":"2026-08-12T01:22:47Z"},{"alias_kind":"pith_short_8","alias_value":"UUHESACC","created_at":"2026-08-12T01:22:47Z"}],"graph_snapshots":[{"event_id":"sha256:1e541c41561a2b233298da0f7d89007902c2f5ac4483e884ae0073e1eb7e3dea","target":"graph","created_at":"2026-08-12T01:22:47Z","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/2608.10579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although existing instruction data selection methods have introduced various metrics, the inherent complexity of real-world datasets makes it impractical for any single metric to generalize across all scenarios. Developers are thus often forced to manually inspect data and craft heuristic rules for each new application---a tedious and error-prone process. In this paper, we propose a paradigm shift from manual configuration to automated orchestration via the Instruction Data Selection Agent (DataMaster), which interprets user intent and autonomously composes optimal selection strategies. By all","authors_text":"Fanqi Zhou, Gong Cheng, Qiaosheng Chen, Zixian Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-11T07:05:05Z","title":"Agentic Instruction Data Selection: Let DataMaster Interpret Your Intent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10579","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:a8a208d4d94c00b9631be544b72965e24959d1d515ecfb1a110791193f66a541","target":"record","created_at":"2026-08-12T01:22:47Z","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":"abed3db11543b98d04a9300f8e99b880a820d5bd88134340afdd81fa9a1a3040","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-11T07:05:05Z","title_canon_sha256":"92d247d101cd028daa41716d9f3333258c58b082115e7b452bdfde782a3fcbc2"},"schema_version":"1.0","source":{"id":"2608.10579","kind":"arxiv","version":1}},"canonical_sha256":"a50e4900423e3170484821d4384a99083189261cbfb0e0c583b36ceadad874e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a50e4900423e3170484821d4384a99083189261cbfb0e0c583b36ceadad874e4","first_computed_at":"2026-08-12T01:22:47.935427Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T01:22:47.935427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AK1JCUpkNEdLjm+cBKJ/Az+cZKC54spas/Fot212C87IjYQeexZftBsQncJ4l+2XybUknKpX8hu+g278lTiGCQ==","signature_status":"signed_v1","signed_at":"2026-08-12T01:22:47.937725Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10579","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8a208d4d94c00b9631be544b72965e24959d1d515ecfb1a110791193f66a541","sha256:1e541c41561a2b233298da0f7d89007902c2f5ac4483e884ae0073e1eb7e3dea"],"state_sha256":"3de2a57938fe990418abe9ca210deac147da8ce360ee59592ce6ebdded2d18c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ECYZHR2dB/kBDxEecG22mkPH6X1T/IIru9embF0OCntNlL0o2Ciy4twHIwMHSsAiJbGG0dPRcEpm0ctlgCaTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T09:04:08.573047Z","bundle_sha256":"d97c48134984ae11cae37de88e2d5bdff86d571266c2e18c711b8c005be365a0"}}