{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OIM3AUYMSTJCFSD4QMSDB24QVK","short_pith_number":"pith:OIM3AUYM","canonical_record":{"source":{"id":"2502.15147","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-21T02:03:08Z","cross_cats_sorted":[],"title_canon_sha256":"b7b15381263d781fab90326e5420e6cd555b59cede1aef79bb492fc908c6b983","abstract_canon_sha256":"bc4d4a250989f8284d359aaf57c8479872833569c24cb48dd7e242911a182ccf"},"schema_version":"1.0"},"canonical_sha256":"7219b0530c94d222c87c832430eb90aa91552f5933b0acd5135cc23ca8753769","source":{"kind":"arxiv","id":"2502.15147","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15147","created_at":"2026-07-05T10:54:43Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15147v2","created_at":"2026-07-05T10:54:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15147","created_at":"2026-07-05T10:54:43Z"},{"alias_kind":"pith_short_12","alias_value":"OIM3AUYMSTJC","created_at":"2026-07-05T10:54:43Z"},{"alias_kind":"pith_short_16","alias_value":"OIM3AUYMSTJCFSD4","created_at":"2026-07-05T10:54:43Z"},{"alias_kind":"pith_short_8","alias_value":"OIM3AUYM","created_at":"2026-07-05T10:54:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OIM3AUYMSTJCFSD4QMSDB24QVK","target":"record","payload":{"canonical_record":{"source":{"id":"2502.15147","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-21T02:03:08Z","cross_cats_sorted":[],"title_canon_sha256":"b7b15381263d781fab90326e5420e6cd555b59cede1aef79bb492fc908c6b983","abstract_canon_sha256":"bc4d4a250989f8284d359aaf57c8479872833569c24cb48dd7e242911a182ccf"},"schema_version":"1.0"},"canonical_sha256":"7219b0530c94d222c87c832430eb90aa91552f5933b0acd5135cc23ca8753769","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:43.762978Z","signature_b64":"pCMBX67NoS+/Fq1gplOZ3VaZxbG/0u9koSCeDHFAYZMIAAXTxNy0JC5GCQzd/qCcb/V4bzpa4TgCpV+EAMbjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7219b0530c94d222c87c832430eb90aa91552f5933b0acd5135cc23ca8753769","last_reissued_at":"2026-07-05T10:54:43.762499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:43.762499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.15147","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":"2026-07-05T10:54:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mTM36bvBzjl2Sb2FnarHvQQ0gAWbSC30ijcxZxXryfwHeLUsyOntj0MJsymnnC2uanFgPv/c7Y/o1SbDHnyfDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:53:02.757717Z"},"content_sha256":"a94e28550e8224e6c5002e726534316516a677a804dd794851593c9ffa77a4f9","schema_version":"1.0","event_id":"sha256:a94e28550e8224e6c5002e726534316516a677a804dd794851593c9ffa77a4f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OIM3AUYMSTJCFSD4QMSDB24QVK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bhavana Dalvi Mishra, Bodhisattwa Prasad Majumder, Harshit Surana, Julian McAuley, Peter Clark, Tushar Khot, Zhouhang Xie","submitted_at":"2025-02-21T02:03:08Z","abstract_excerpt":"Instruction-following LLMs have recently allowed systems to discover hidden concepts from a collection of unstructured documents based on a natural language description of the purpose of the discovery (i.e., goal). Still, the quality of the discovered concepts remains mixed, as it depends heavily on LLM's reasoning ability and drops when the data is noisy or beyond LLM's knowledge. We present Instruct-LF, a goal-oriented latent factor discovery system that integrates LLM's instruction-following ability with statistical models to handle large, noisy datasets where LLM reasoning alone falls shor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15147","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/2502.15147/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":"2026-07-05T10:54:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MQtGsxU9WeCHzxJBcZTGMTcswpsUPuS6FtbRvyCIwWz43o/wqUeCngxlQ+p74T6rNxP75nKJVAi/cU+0DTDICA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:53:02.758338Z"},"content_sha256":"6f82c3a6d64d8507a18cdf096b717e1d04ea9351178280432cec4398a1de2963","schema_version":"1.0","event_id":"sha256:6f82c3a6d64d8507a18cdf096b717e1d04ea9351178280432cec4398a1de2963"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OIM3AUYMSTJCFSD4QMSDB24QVK/bundle.json","state_url":"https://pith.science/pith/OIM3AUYMSTJCFSD4QMSDB24QVK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OIM3AUYMSTJCFSD4QMSDB24QVK/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":"2026-07-07T04:53:02Z","links":{"resolver":"https://pith.science/pith/OIM3AUYMSTJCFSD4QMSDB24QVK","bundle":"https://pith.science/pith/OIM3AUYMSTJCFSD4QMSDB24QVK/bundle.json","state":"https://pith.science/pith/OIM3AUYMSTJCFSD4QMSDB24QVK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OIM3AUYMSTJCFSD4QMSDB24QVK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OIM3AUYMSTJCFSD4QMSDB24QVK","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":"bc4d4a250989f8284d359aaf57c8479872833569c24cb48dd7e242911a182ccf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-21T02:03:08Z","title_canon_sha256":"b7b15381263d781fab90326e5420e6cd555b59cede1aef79bb492fc908c6b983"},"schema_version":"1.0","source":{"id":"2502.15147","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15147","created_at":"2026-07-05T10:54:43Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15147v2","created_at":"2026-07-05T10:54:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15147","created_at":"2026-07-05T10:54:43Z"},{"alias_kind":"pith_short_12","alias_value":"OIM3AUYMSTJC","created_at":"2026-07-05T10:54:43Z"},{"alias_kind":"pith_short_16","alias_value":"OIM3AUYMSTJCFSD4","created_at":"2026-07-05T10:54:43Z"},{"alias_kind":"pith_short_8","alias_value":"OIM3AUYM","created_at":"2026-07-05T10:54:43Z"}],"graph_snapshots":[{"event_id":"sha256:6f82c3a6d64d8507a18cdf096b717e1d04ea9351178280432cec4398a1de2963","target":"graph","created_at":"2026-07-05T10:54:43Z","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/2502.15147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction-following LLMs have recently allowed systems to discover hidden concepts from a collection of unstructured documents based on a natural language description of the purpose of the discovery (i.e., goal). Still, the quality of the discovered concepts remains mixed, as it depends heavily on LLM's reasoning ability and drops when the data is noisy or beyond LLM's knowledge. We present Instruct-LF, a goal-oriented latent factor discovery system that integrates LLM's instruction-following ability with statistical models to handle large, noisy datasets where LLM reasoning alone falls shor","authors_text":"Bhavana Dalvi Mishra, Bodhisattwa Prasad Majumder, Harshit Surana, Julian McAuley, Peter Clark, Tushar Khot, Zhouhang Xie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-21T02:03:08Z","title":"Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15147","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:a94e28550e8224e6c5002e726534316516a677a804dd794851593c9ffa77a4f9","target":"record","created_at":"2026-07-05T10:54:43Z","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":"bc4d4a250989f8284d359aaf57c8479872833569c24cb48dd7e242911a182ccf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-21T02:03:08Z","title_canon_sha256":"b7b15381263d781fab90326e5420e6cd555b59cede1aef79bb492fc908c6b983"},"schema_version":"1.0","source":{"id":"2502.15147","kind":"arxiv","version":2}},"canonical_sha256":"7219b0530c94d222c87c832430eb90aa91552f5933b0acd5135cc23ca8753769","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7219b0530c94d222c87c832430eb90aa91552f5933b0acd5135cc23ca8753769","first_computed_at":"2026-07-05T10:54:43.762499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:43.762499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pCMBX67NoS+/Fq1gplOZ3VaZxbG/0u9koSCeDHFAYZMIAAXTxNy0JC5GCQzd/qCcb/V4bzpa4TgCpV+EAMbjBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:43.762978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.15147","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a94e28550e8224e6c5002e726534316516a677a804dd794851593c9ffa77a4f9","sha256:6f82c3a6d64d8507a18cdf096b717e1d04ea9351178280432cec4398a1de2963"],"state_sha256":"78649e9e5f531c2569fb7c9456ef76e9cfbd8249c84577ebb9cf710227c68e69"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Dov+L4NZmdkTCpTJUKXzTqT0E2onuQFgMCLtc7Q3SCKtV1hlZsasTemexonYLdwMASn02A6VoJaaxc37XWVAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:53:02.762422Z","bundle_sha256":"beda0a278279e5468e627e2ece338d6f133ab14642da67e02c81074ec48a6ef9"}}