{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M27ZMKCCKPZK5N4O5PDTI7PDKT","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":"99b48e628adb38411339ebeee7e03e77472d4de5b1b48ac7af3faa6aaf7e3d10","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T17:14:37Z","title_canon_sha256":"0e55598c44e4a2e33feec164f59cdd3952905e4920927efbdfae463a26e96892"},"schema_version":"1.0","source":{"id":"2505.21439","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21439","created_at":"2026-07-05T11:10:41Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21439v1","created_at":"2026-07-05T11:10:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21439","created_at":"2026-07-05T11:10:41Z"},{"alias_kind":"pith_short_12","alias_value":"M27ZMKCCKPZK","created_at":"2026-07-05T11:10:41Z"},{"alias_kind":"pith_short_16","alias_value":"M27ZMKCCKPZK5N4O","created_at":"2026-07-05T11:10:41Z"},{"alias_kind":"pith_short_8","alias_value":"M27ZMKCC","created_at":"2026-07-05T11:10:41Z"}],"graph_snapshots":[{"event_id":"sha256:3057744b154e74ddf4dd197ee3e14a267de60b362473e7c17a38ac786181a960","target":"graph","created_at":"2026-07-05T11:10:41Z","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/2505.21439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern information retrieval (IR) models, trained exclusively on standard <query, passage> pairs, struggle to effectively interpret and follow explicit user instructions. We introduce InF-IR, a large-scale, high-quality training corpus tailored for enhancing retrieval models in Instruction-Following IR. InF-IR expands traditional training pairs into over 38,000 expressive <instruction, query, passage> triplets as positive samples. In particular, for each positive triplet, we generate two additional hard negative examples by poisoning both instructions and queries, then rigorously validated by ","authors_text":"Aaron Trinh, Bo Dai, Chao Zhang, Hanjun Dai, Haotian Sun, Rushi Qiang, Yuchen Zhuang","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T17:14:37Z","title":"Towards Better Instruction Following Retrieval Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21439","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":"sha256:2fadeffe50d19c8d31bf9f2a0b3a7797581c098aa3f20bf43435b717017819d0","target":"record","created_at":"2026-07-05T11:10:41Z","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":"99b48e628adb38411339ebeee7e03e77472d4de5b1b48ac7af3faa6aaf7e3d10","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T17:14:37Z","title_canon_sha256":"0e55598c44e4a2e33feec164f59cdd3952905e4920927efbdfae463a26e96892"},"schema_version":"1.0","source":{"id":"2505.21439","kind":"arxiv","version":1}},"canonical_sha256":"66bf96284253f2aeb78eebc7347de354f9671316bfd808ca686f62dee877ab7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66bf96284253f2aeb78eebc7347de354f9671316bfd808ca686f62dee877ab7a","first_computed_at":"2026-07-05T11:10:41.927556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:41.927556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XPFGh/Z3sXJcSO5G0jjb7HPbwmjBQO7pVkqxrYXo2b6EUZZY3+XY9F4i+TAMU4KJtC8SW8UnH0d4bmZIk1NZBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:41.928058Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21439","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fadeffe50d19c8d31bf9f2a0b3a7797581c098aa3f20bf43435b717017819d0","sha256:3057744b154e74ddf4dd197ee3e14a267de60b362473e7c17a38ac786181a960"],"state_sha256":"3b185ec726151f9dec9b116c18f476a5bb369c0a34954cd44f24c4f647f7f279"}