{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:M2BSHJ2HZI7GE5FXA2IIYFYDCH","short_pith_number":"pith:M2BSHJ2H","canonical_record":{"source":{"id":"2605.30039","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T14:57:02Z","cross_cats_sorted":[],"title_canon_sha256":"cf581d4c56731511d241328cd332144eadd01b78593c43b86c51258f97673df2","abstract_canon_sha256":"7d938a4c3a8f1d76587d9564d5e37d17dc7498a99c8a9d26edeca15580807b84"},"schema_version":"1.0"},"canonical_sha256":"668323a747ca3e6274b706908c170311ec84ef310c0921d901c0fb0318dd605d","source":{"kind":"arxiv","id":"2605.30039","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30039","created_at":"2026-05-29T02:06:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30039v1","created_at":"2026-05-29T02:06:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30039","created_at":"2026-05-29T02:06:08Z"},{"alias_kind":"pith_short_12","alias_value":"M2BSHJ2HZI7G","created_at":"2026-05-29T02:06:08Z"},{"alias_kind":"pith_short_16","alias_value":"M2BSHJ2HZI7GE5FX","created_at":"2026-05-29T02:06:08Z"},{"alias_kind":"pith_short_8","alias_value":"M2BSHJ2H","created_at":"2026-05-29T02:06:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:M2BSHJ2HZI7GE5FXA2IIYFYDCH","target":"record","payload":{"canonical_record":{"source":{"id":"2605.30039","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T14:57:02Z","cross_cats_sorted":[],"title_canon_sha256":"cf581d4c56731511d241328cd332144eadd01b78593c43b86c51258f97673df2","abstract_canon_sha256":"7d938a4c3a8f1d76587d9564d5e37d17dc7498a99c8a9d26edeca15580807b84"},"schema_version":"1.0"},"canonical_sha256":"668323a747ca3e6274b706908c170311ec84ef310c0921d901c0fb0318dd605d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:08.071608Z","signature_b64":"saIGv+SalZjkjmD1+wcTb8o5wq9l7ca9C7AYmuBm7RAQZDQ7ttbvRorrIaKH3bJkbPx5RJifZFZZ3+NeuJk0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"668323a747ca3e6274b706908c170311ec84ef310c0921d901c0fb0318dd605d","last_reissued_at":"2026-05-29T02:06:08.071115Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:08.071115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.30039","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":"2026-05-29T02:06:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kf2ewZOVMt6VMJwHZ76u/bZrMPSzltjSBpE6w/U38LPhdOqoCYwTPnHE/hfzAIAYLHP7JGbJJvlEPxlK/OcnBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:34:52.672681Z"},"content_sha256":"940c40541442e979b5a61c224bdbb06ba760b78855a2f5c7f01f2644dca1b75a","schema_version":"1.0","event_id":"sha256:940c40541442e979b5a61c224bdbb06ba760b78855a2f5c7f01f2644dca1b75a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:M2BSHJ2HZI7GE5FXA2IIYFYDCH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hang Yu, Jianguo Li, Jianwei Yin, Peiyu Liu, Peng Di, Tengfei Ma, Tong Ye, Wenhai Wang, Xuhong Zhang","submitted_at":"2026-05-28T14:57:02Z","abstract_excerpt":"Large Language Models have demonstrated remarkable progress in general-purpose capabilities and can achieve strong performance in specific domains through fine-tuning on domain-specific data. However, acquiring high-quality data for target domains remains a significant challenge. Existing data synthesis approaches follow a deductive paradigm, heavily relying on explicit domain descriptions expressed in natural language and careful prompt engineering, limiting their applicability in real-world scenarios where domains are difficult to describe or formally articulate. In this work, we tackle the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30039","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/2605.30039/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":"2026-05-29T02:06:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y2nWrNvP3qVOLGdmnI4pLZnzBf7T4jv+xS6LDK+91CnqSxwWN9Zyr7tv0LsPiZe2NLpbC9zqaTE6ZBRE8wY/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:34:52.673536Z"},"content_sha256":"5957c6afb6a7d12b16cdc93ee42ff630ecdebc86e741c201d2d1eb436f52870b","schema_version":"1.0","event_id":"sha256:5957c6afb6a7d12b16cdc93ee42ff630ecdebc86e741c201d2d1eb436f52870b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M2BSHJ2HZI7GE5FXA2IIYFYDCH/bundle.json","state_url":"https://pith.science/pith/M2BSHJ2HZI7GE5FXA2IIYFYDCH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M2BSHJ2HZI7GE5FXA2IIYFYDCH/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":"2026-05-30T07:34:52Z","links":{"resolver":"https://pith.science/pith/M2BSHJ2HZI7GE5FXA2IIYFYDCH","bundle":"https://pith.science/pith/M2BSHJ2HZI7GE5FXA2IIYFYDCH/bundle.json","state":"https://pith.science/pith/M2BSHJ2HZI7GE5FXA2IIYFYDCH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M2BSHJ2HZI7GE5FXA2IIYFYDCH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M2BSHJ2HZI7GE5FXA2IIYFYDCH","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":"7d938a4c3a8f1d76587d9564d5e37d17dc7498a99c8a9d26edeca15580807b84","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T14:57:02Z","title_canon_sha256":"cf581d4c56731511d241328cd332144eadd01b78593c43b86c51258f97673df2"},"schema_version":"1.0","source":{"id":"2605.30039","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30039","created_at":"2026-05-29T02:06:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30039v1","created_at":"2026-05-29T02:06:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30039","created_at":"2026-05-29T02:06:08Z"},{"alias_kind":"pith_short_12","alias_value":"M2BSHJ2HZI7G","created_at":"2026-05-29T02:06:08Z"},{"alias_kind":"pith_short_16","alias_value":"M2BSHJ2HZI7GE5FX","created_at":"2026-05-29T02:06:08Z"},{"alias_kind":"pith_short_8","alias_value":"M2BSHJ2H","created_at":"2026-05-29T02:06:08Z"}],"graph_snapshots":[{"event_id":"sha256:5957c6afb6a7d12b16cdc93ee42ff630ecdebc86e741c201d2d1eb436f52870b","target":"graph","created_at":"2026-05-29T02:06:08Z","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/2605.30039/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models have demonstrated remarkable progress in general-purpose capabilities and can achieve strong performance in specific domains through fine-tuning on domain-specific data. However, acquiring high-quality data for target domains remains a significant challenge. Existing data synthesis approaches follow a deductive paradigm, heavily relying on explicit domain descriptions expressed in natural language and careful prompt engineering, limiting their applicability in real-world scenarios where domains are difficult to describe or formally articulate. In this work, we tackle the ","authors_text":"Hang Yu, Jianguo Li, Jianwei Yin, Peiyu Liu, Peng Di, Tengfei Ma, Tong Ye, Wenhai Wang, Xuhong Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T14:57:02Z","title":"Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30039","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":"sha256:940c40541442e979b5a61c224bdbb06ba760b78855a2f5c7f01f2644dca1b75a","target":"record","created_at":"2026-05-29T02:06:08Z","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":"7d938a4c3a8f1d76587d9564d5e37d17dc7498a99c8a9d26edeca15580807b84","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T14:57:02Z","title_canon_sha256":"cf581d4c56731511d241328cd332144eadd01b78593c43b86c51258f97673df2"},"schema_version":"1.0","source":{"id":"2605.30039","kind":"arxiv","version":1}},"canonical_sha256":"668323a747ca3e6274b706908c170311ec84ef310c0921d901c0fb0318dd605d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"668323a747ca3e6274b706908c170311ec84ef310c0921d901c0fb0318dd605d","first_computed_at":"2026-05-29T02:06:08.071115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:08.071115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"saIGv+SalZjkjmD1+wcTb8o5wq9l7ca9C7AYmuBm7RAQZDQ7ttbvRorrIaKH3bJkbPx5RJifZFZZ3+NeuJk0Aw==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:08.071608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30039","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:940c40541442e979b5a61c224bdbb06ba760b78855a2f5c7f01f2644dca1b75a","sha256:5957c6afb6a7d12b16cdc93ee42ff630ecdebc86e741c201d2d1eb436f52870b"],"state_sha256":"0f3c5865c230d07700eed89cfd4321a16dc9e86dae74d2bd23eff44411ae9eda"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8xp5gxW6T9CFyj8BZ/0DrnI5VB6eTuirfzYzTADm9fjcPE5/PqubunXeXIRng3DT1F2HmVZLg0FJ2H7lqweVDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T07:34:52.677661Z","bundle_sha256":"0318b89fc743b3b49e70d133686f119e3ecdb2aa402be100d7cf821ae3565163"}}