{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3TILJDF3UTLXXX447Z5VZGW2F7","short_pith_number":"pith:3TILJDF3","canonical_record":{"source":{"id":"2410.15553","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T00:59:47Z","cross_cats_sorted":[],"title_canon_sha256":"cff093408af0fb3e084a34420e529e7675f97130dc708a75265f3fbcbe41cda8","abstract_canon_sha256":"1cebc88d6bc28ec8be5d5d44e06979224c92efa65d73ba3bdd3b6cb9de3f48c8"},"schema_version":"1.0"},"canonical_sha256":"dcd0b48cbba4d77bdf9cfe7b5c9ada2ff5a5619daf6adb449f353b1ec4ed902b","source":{"kind":"arxiv","id":"2410.15553","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15553","created_at":"2026-07-05T09:34:38Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15553v2","created_at":"2026-07-05T09:34:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15553","created_at":"2026-07-05T09:34:38Z"},{"alias_kind":"pith_short_12","alias_value":"3TILJDF3UTLX","created_at":"2026-07-05T09:34:38Z"},{"alias_kind":"pith_short_16","alias_value":"3TILJDF3UTLXXX44","created_at":"2026-07-05T09:34:38Z"},{"alias_kind":"pith_short_8","alias_value":"3TILJDF3","created_at":"2026-07-05T09:34:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3TILJDF3UTLXXX447Z5VZGW2F7","target":"record","payload":{"canonical_record":{"source":{"id":"2410.15553","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T00:59:47Z","cross_cats_sorted":[],"title_canon_sha256":"cff093408af0fb3e084a34420e529e7675f97130dc708a75265f3fbcbe41cda8","abstract_canon_sha256":"1cebc88d6bc28ec8be5d5d44e06979224c92efa65d73ba3bdd3b6cb9de3f48c8"},"schema_version":"1.0"},"canonical_sha256":"dcd0b48cbba4d77bdf9cfe7b5c9ada2ff5a5619daf6adb449f353b1ec4ed902b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:38.927837Z","signature_b64":"ktlAmT9V4FO4eOffGCBWWFU1tQi3/74/CzZXbFzTBMWeD+BdlWXCL8nqFp3bVLjFuXTwAyxBBN4HiB7fHBVSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcd0b48cbba4d77bdf9cfe7b5c9ada2ff5a5619daf6adb449f353b1ec4ed902b","last_reissued_at":"2026-07-05T09:34:38.927344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:38.927344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.15553","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":"2026-07-05T09:34:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GZu14NWuca7+Z3e2UV7bvRCX/ksRIdQXvmOGmB0qrm89VjFzN6qsr8t4ldLivHGmZWQzHHJRK6dTZbOSSh4iCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:14:22.645108Z"},"content_sha256":"2ac83d6b0fb266fcb9e396b0f026257b52d83728ffe188446b926df0c847690f","schema_version":"1.0","event_id":"sha256:2ac83d6b0fb266fcb9e396b0f026257b52d83728ffe188446b926df0c847690f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3TILJDF3UTLXXX447Z5VZGW2F7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditya Tayade, Chaoqi Wang, Chenguang Zhu, Chen Zhu, Chloe Bi, Di Jin, Eryk Helenowski, Han Fang, Hao Ma, Hejia Zhang, Hongjiang Lv, Karishma Mandyam, Karthik Abinav Sankararaman, Melanie Kambadur, Ning Li, Shruti Bhosale, Sinong Wang, Tengyu Xu, Yun He","submitted_at":"2024-10-21T00:59:47Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated impressive capabilities in various tasks, including instruction following, which is crucial for aligning model outputs with user expectations. However, evaluating LLMs' ability to follow instructions remains challenging due to the complexity and subjectivity of human language. Current benchmarks primarily focus on single-turn, monolingual instructions, which do not adequately reflect the complexities of real-world applications that require handling multi-turn and multilingual interactions. To address this gap, we introduce Multi-IF, a new benchmar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15553","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/2410.15553/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":"2026-07-05T09:34:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+x0XWmL1oMs5t69U7CrAU9vLGggdR+SV07OX64MDKh/7cKrsu3HRyGfWz4PBIkQNtDnyKhOGHa0p0ycKzJYDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T04:14:22.645498Z"},"content_sha256":"592c7df0f1ae97ea011bff5f918aa6a72767c862910520f299d60ebbc7b7ef36","schema_version":"1.0","event_id":"sha256:592c7df0f1ae97ea011bff5f918aa6a72767c862910520f299d60ebbc7b7ef36"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3TILJDF3UTLXXX447Z5VZGW2F7/bundle.json","state_url":"https://pith.science/pith/3TILJDF3UTLXXX447Z5VZGW2F7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3TILJDF3UTLXXX447Z5VZGW2F7/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":"2026-07-09T04:14:22Z","links":{"resolver":"https://pith.science/pith/3TILJDF3UTLXXX447Z5VZGW2F7","bundle":"https://pith.science/pith/3TILJDF3UTLXXX447Z5VZGW2F7/bundle.json","state":"https://pith.science/pith/3TILJDF3UTLXXX447Z5VZGW2F7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3TILJDF3UTLXXX447Z5VZGW2F7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3TILJDF3UTLXXX447Z5VZGW2F7","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":"1cebc88d6bc28ec8be5d5d44e06979224c92efa65d73ba3bdd3b6cb9de3f48c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T00:59:47Z","title_canon_sha256":"cff093408af0fb3e084a34420e529e7675f97130dc708a75265f3fbcbe41cda8"},"schema_version":"1.0","source":{"id":"2410.15553","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15553","created_at":"2026-07-05T09:34:38Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15553v2","created_at":"2026-07-05T09:34:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15553","created_at":"2026-07-05T09:34:38Z"},{"alias_kind":"pith_short_12","alias_value":"3TILJDF3UTLX","created_at":"2026-07-05T09:34:38Z"},{"alias_kind":"pith_short_16","alias_value":"3TILJDF3UTLXXX44","created_at":"2026-07-05T09:34:38Z"},{"alias_kind":"pith_short_8","alias_value":"3TILJDF3","created_at":"2026-07-05T09:34:38Z"}],"graph_snapshots":[{"event_id":"sha256:592c7df0f1ae97ea011bff5f918aa6a72767c862910520f299d60ebbc7b7ef36","target":"graph","created_at":"2026-07-05T09:34:38Z","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/2410.15553/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated impressive capabilities in various tasks, including instruction following, which is crucial for aligning model outputs with user expectations. However, evaluating LLMs' ability to follow instructions remains challenging due to the complexity and subjectivity of human language. Current benchmarks primarily focus on single-turn, monolingual instructions, which do not adequately reflect the complexities of real-world applications that require handling multi-turn and multilingual interactions. To address this gap, we introduce Multi-IF, a new benchmar","authors_text":"Aditya Tayade, Chaoqi Wang, Chenguang Zhu, Chen Zhu, Chloe Bi, Di Jin, Eryk Helenowski, Han Fang, Hao Ma, Hejia Zhang, Hongjiang Lv, Karishma Mandyam, Karthik Abinav Sankararaman, Melanie Kambadur, Ning Li, Shruti Bhosale, Sinong Wang, Tengyu Xu, Yun He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T00:59:47Z","title":"Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15553","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":"sha256:2ac83d6b0fb266fcb9e396b0f026257b52d83728ffe188446b926df0c847690f","target":"record","created_at":"2026-07-05T09:34:38Z","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":"1cebc88d6bc28ec8be5d5d44e06979224c92efa65d73ba3bdd3b6cb9de3f48c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T00:59:47Z","title_canon_sha256":"cff093408af0fb3e084a34420e529e7675f97130dc708a75265f3fbcbe41cda8"},"schema_version":"1.0","source":{"id":"2410.15553","kind":"arxiv","version":2}},"canonical_sha256":"dcd0b48cbba4d77bdf9cfe7b5c9ada2ff5a5619daf6adb449f353b1ec4ed902b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcd0b48cbba4d77bdf9cfe7b5c9ada2ff5a5619daf6adb449f353b1ec4ed902b","first_computed_at":"2026-07-05T09:34:38.927344Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:38.927344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ktlAmT9V4FO4eOffGCBWWFU1tQi3/74/CzZXbFzTBMWeD+BdlWXCL8nqFp3bVLjFuXTwAyxBBN4HiB7fHBVSDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:38.927837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.15553","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ac83d6b0fb266fcb9e396b0f026257b52d83728ffe188446b926df0c847690f","sha256:592c7df0f1ae97ea011bff5f918aa6a72767c862910520f299d60ebbc7b7ef36"],"state_sha256":"bd50f430a7be497793a4c3d241d4aea4c169592a6c0f88a466eed7244a29d9c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sYp2XONo+nHF5SwWp8IdaS2WqpQ4d+n2PPYPUGgiJ6HW9uyj/Kl82ITaB917N2Qy5mdUV2+t3HOUA6MYTvxSBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T04:14:22.647744Z","bundle_sha256":"a23a0804726f89df59543aba67a1e472030265d9b335573b571313c68bed3fce"}}