{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2Q73UB45NWBG4WGNCE34OYVIYM","short_pith_number":"pith:2Q73UB45","canonical_record":{"source":{"id":"2506.03968","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T14:00:47Z","cross_cats_sorted":[],"title_canon_sha256":"11a25e32d9ea2a009db68c628ba96d42eb0b74f1d766af9a8c5eab6b8ca96f8c","abstract_canon_sha256":"78952c13a6678d94ebea408560c4a464d64097d5ba25746476a9927d051de613"},"schema_version":"1.0"},"canonical_sha256":"d43fba079d6d826e58cd1137c762a8c315e138f01b70caa29d304c10dd0f3135","source":{"kind":"arxiv","id":"2506.03968","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03968","created_at":"2026-07-05T11:15:54Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03968v1","created_at":"2026-07-05T11:15:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03968","created_at":"2026-07-05T11:15:54Z"},{"alias_kind":"pith_short_12","alias_value":"2Q73UB45NWBG","created_at":"2026-07-05T11:15:54Z"},{"alias_kind":"pith_short_16","alias_value":"2Q73UB45NWBG4WGN","created_at":"2026-07-05T11:15:54Z"},{"alias_kind":"pith_short_8","alias_value":"2Q73UB45","created_at":"2026-07-05T11:15:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2Q73UB45NWBG4WGNCE34OYVIYM","target":"record","payload":{"canonical_record":{"source":{"id":"2506.03968","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T14:00:47Z","cross_cats_sorted":[],"title_canon_sha256":"11a25e32d9ea2a009db68c628ba96d42eb0b74f1d766af9a8c5eab6b8ca96f8c","abstract_canon_sha256":"78952c13a6678d94ebea408560c4a464d64097d5ba25746476a9927d051de613"},"schema_version":"1.0"},"canonical_sha256":"d43fba079d6d826e58cd1137c762a8c315e138f01b70caa29d304c10dd0f3135","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:54.673869Z","signature_b64":"gf+iyRlO7hJN9kq4ss5QwjYgRx1jrCPEKIQxJBfT4iJtyp6c3WZzpPI7svr7fXqW/qdKz7elNsmd0qKcqU4MBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d43fba079d6d826e58cd1137c762a8c315e138f01b70caa29d304c10dd0f3135","last_reissued_at":"2026-07-05T11:15:54.673407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:54.673407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.03968","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":"2026-07-05T11:15:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yKD+p2/UmNOyHYH0marY4bvAgIFn98UueUchXg5ZFkJ2yWRdyKmJOi6BD0m1ao8e1am8JGSueuVHjZOnHxotCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:23:50.953115Z"},"content_sha256":"73b33644216827b5e458179c9a4bffa96c28eb1831a901ead07cf401a0df7552","schema_version":"1.0","event_id":"sha256:73b33644216827b5e458179c9a4bffa96c28eb1831a901ead07cf401a0df7552"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2Q73UB45NWBG4WGNCE34OYVIYM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benfeng Xu, Chiwei Zhu, Xiaorui Wang, Zhendong Mao","submitted_at":"2025-06-04T14:00:47Z","abstract_excerpt":"The pursuit of diverse, complex, and large-scale instruction data is crucial for automatically aligning large language models (LLMs). While there are methods capable of generating synthetic instructions at scale, they either suffer from limited grounding sources, leading to a narrow distribution, or rely on trivial extensions that fail to produce meaningful trajectories in terms of complexity. In contrast, instructions that benefit efficient alignment are typically crafted with cognitive insights and grounded in real-world use cases. In this paper, we synthesize such instructions using attribu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03968","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/2506.03968/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":"2026-07-05T11:15:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nwO+d5G1aY6b6hFNv0cGn8WqUfQSVFEpIm8MriRaJIEL1uQ/b8vWUytYyCuyp0M0HF7UVrEHt3k9TU0gjUYTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:23:50.953777Z"},"content_sha256":"512f58b1dc837c4ced7277f8fbd5268f0a87bd07c080d4f8ac9a14b46dc690c3","schema_version":"1.0","event_id":"sha256:512f58b1dc837c4ced7277f8fbd5268f0a87bd07c080d4f8ac9a14b46dc690c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2Q73UB45NWBG4WGNCE34OYVIYM/bundle.json","state_url":"https://pith.science/pith/2Q73UB45NWBG4WGNCE34OYVIYM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2Q73UB45NWBG4WGNCE34OYVIYM/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":"2026-08-04T04:23:50Z","links":{"resolver":"https://pith.science/pith/2Q73UB45NWBG4WGNCE34OYVIYM","bundle":"https://pith.science/pith/2Q73UB45NWBG4WGNCE34OYVIYM/bundle.json","state":"https://pith.science/pith/2Q73UB45NWBG4WGNCE34OYVIYM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2Q73UB45NWBG4WGNCE34OYVIYM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2Q73UB45NWBG4WGNCE34OYVIYM","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":"78952c13a6678d94ebea408560c4a464d64097d5ba25746476a9927d051de613","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T14:00:47Z","title_canon_sha256":"11a25e32d9ea2a009db68c628ba96d42eb0b74f1d766af9a8c5eab6b8ca96f8c"},"schema_version":"1.0","source":{"id":"2506.03968","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03968","created_at":"2026-07-05T11:15:54Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03968v1","created_at":"2026-07-05T11:15:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03968","created_at":"2026-07-05T11:15:54Z"},{"alias_kind":"pith_short_12","alias_value":"2Q73UB45NWBG","created_at":"2026-07-05T11:15:54Z"},{"alias_kind":"pith_short_16","alias_value":"2Q73UB45NWBG4WGN","created_at":"2026-07-05T11:15:54Z"},{"alias_kind":"pith_short_8","alias_value":"2Q73UB45","created_at":"2026-07-05T11:15:54Z"}],"graph_snapshots":[{"event_id":"sha256:512f58b1dc837c4ced7277f8fbd5268f0a87bd07c080d4f8ac9a14b46dc690c3","target":"graph","created_at":"2026-07-05T11:15:54Z","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/2506.03968/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The pursuit of diverse, complex, and large-scale instruction data is crucial for automatically aligning large language models (LLMs). While there are methods capable of generating synthetic instructions at scale, they either suffer from limited grounding sources, leading to a narrow distribution, or rely on trivial extensions that fail to produce meaningful trajectories in terms of complexity. In contrast, instructions that benefit efficient alignment are typically crafted with cognitive insights and grounded in real-world use cases. In this paper, we synthesize such instructions using attribu","authors_text":"Benfeng Xu, Chiwei Zhu, Xiaorui Wang, Zhendong Mao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T14:00:47Z","title":"From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03968","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":"sha256:73b33644216827b5e458179c9a4bffa96c28eb1831a901ead07cf401a0df7552","target":"record","created_at":"2026-07-05T11:15:54Z","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":"78952c13a6678d94ebea408560c4a464d64097d5ba25746476a9927d051de613","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T14:00:47Z","title_canon_sha256":"11a25e32d9ea2a009db68c628ba96d42eb0b74f1d766af9a8c5eab6b8ca96f8c"},"schema_version":"1.0","source":{"id":"2506.03968","kind":"arxiv","version":1}},"canonical_sha256":"d43fba079d6d826e58cd1137c762a8c315e138f01b70caa29d304c10dd0f3135","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d43fba079d6d826e58cd1137c762a8c315e138f01b70caa29d304c10dd0f3135","first_computed_at":"2026-07-05T11:15:54.673407Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:54.673407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gf+iyRlO7hJN9kq4ss5QwjYgRx1jrCPEKIQxJBfT4iJtyp6c3WZzpPI7svr7fXqW/qdKz7elNsmd0qKcqU4MBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:54.673869Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03968","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73b33644216827b5e458179c9a4bffa96c28eb1831a901ead07cf401a0df7552","sha256:512f58b1dc837c4ced7277f8fbd5268f0a87bd07c080d4f8ac9a14b46dc690c3"],"state_sha256":"7bbaff07cad1dd7e72737cba6db5614e10242bc1f0111d86d585be720f2207df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"etslp8yBVf2LPb0BWC0XP9bwyErpwtYNGdvfKD658QXJC1WKvdYuV1t7+Qkibn5QmC1S6zUV14CggTq59KKPBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:23:50.964025Z","bundle_sha256":"67c870c52c40b5feb076336853fa8e73181148ba53d7d9745706d9adefcb437b"}}