{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VY5ATNVME7IU7SHFV52NYJLK3E","short_pith_number":"pith:VY5ATNVM","canonical_record":{"source":{"id":"2505.17736","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-23T10:58:22Z","cross_cats_sorted":[],"title_canon_sha256":"074b6188a9014f75487377466dc144ce023b0814909c8ee0b5ce4923ae03a424","abstract_canon_sha256":"e2c66bbcf878aa12ad2e9fff33876e5a61e3ef303e177bebda66c4c48507e001"},"schema_version":"1.0"},"canonical_sha256":"ae3a09b6ac27d14fc8e5af74dc256ad9341169593cf7def1a1b99258092a9938","source":{"kind":"arxiv","id":"2505.17736","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17736","created_at":"2026-07-05T11:08:31Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17736v1","created_at":"2026-07-05T11:08:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17736","created_at":"2026-07-05T11:08:31Z"},{"alias_kind":"pith_short_12","alias_value":"VY5ATNVME7IU","created_at":"2026-07-05T11:08:31Z"},{"alias_kind":"pith_short_16","alias_value":"VY5ATNVME7IU7SHF","created_at":"2026-07-05T11:08:31Z"},{"alias_kind":"pith_short_8","alias_value":"VY5ATNVM","created_at":"2026-07-05T11:08:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VY5ATNVME7IU7SHFV52NYJLK3E","target":"record","payload":{"canonical_record":{"source":{"id":"2505.17736","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-23T10:58:22Z","cross_cats_sorted":[],"title_canon_sha256":"074b6188a9014f75487377466dc144ce023b0814909c8ee0b5ce4923ae03a424","abstract_canon_sha256":"e2c66bbcf878aa12ad2e9fff33876e5a61e3ef303e177bebda66c4c48507e001"},"schema_version":"1.0"},"canonical_sha256":"ae3a09b6ac27d14fc8e5af74dc256ad9341169593cf7def1a1b99258092a9938","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:31.028137Z","signature_b64":"2w+MGI5IgDP9XgDhklu6mSbv/VvoMeC94uPWwBkl/3uaqRszkoqX72M6+scwJJWQaxOura4Bvpk+H479IwdoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae3a09b6ac27d14fc8e5af74dc256ad9341169593cf7def1a1b99258092a9938","last_reissued_at":"2026-07-05T11:08:31.027702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:31.027702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.17736","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":"2026-07-05T11:08:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BUT9nwtm0OTN+OgjQ5VSJtRjIqzFKdtYUC1b4Gt/Zj7/B2PdsuXlkT2IrHJOtWkM5phlHC4xNWtt4Zt/sUQLCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:12:20.950885Z"},"content_sha256":"fddac623a2f86dfdbfa2fc90a7d63996ad3fb3799a679f7279d540f1705571e5","schema_version":"1.0","event_id":"sha256:fddac623a2f86dfdbfa2fc90a7d63996ad3fb3799a679f7279d540f1705571e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VY5ATNVME7IU7SHFV52NYJLK3E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modeling Ranking Properties with In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Andrew Parry, Debasis Ganguly, Nilanjan Sinhababu, Pabitra Mitra","submitted_at":"2025-05-23T10:58:22Z","abstract_excerpt":"While standard IR models are mainly designed to optimize relevance, real-world search often needs to balance additional objectives such as diversity and fairness. These objectives depend on inter-document interactions and are commonly addressed using post-hoc heuristics or supervised learning methods, which require task-specific training for each ranking scenario and dataset. In this work, we propose an in-context learning (ICL) approach that eliminates the need for such training. Instead, our method relies on a small number of example rankings that demonstrate the desired trade-offs between o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17736","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/2505.17736/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":"2026-07-05T11:08:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SZ8iN244243iMpQq+7Qgksfm8CpW7uEmO2NJD272AFc/oKWbQvP/Wj550NldRXwhRaGlGcNqHP4etIR4SCDiDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:12:20.951516Z"},"content_sha256":"9e7cc06c48154185c555157847d6ac365c38dce2ae08de0e2fd0aacca0034c80","schema_version":"1.0","event_id":"sha256:9e7cc06c48154185c555157847d6ac365c38dce2ae08de0e2fd0aacca0034c80"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VY5ATNVME7IU7SHFV52NYJLK3E/bundle.json","state_url":"https://pith.science/pith/VY5ATNVME7IU7SHFV52NYJLK3E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VY5ATNVME7IU7SHFV52NYJLK3E/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":"2026-08-12T14:12:20Z","links":{"resolver":"https://pith.science/pith/VY5ATNVME7IU7SHFV52NYJLK3E","bundle":"https://pith.science/pith/VY5ATNVME7IU7SHFV52NYJLK3E/bundle.json","state":"https://pith.science/pith/VY5ATNVME7IU7SHFV52NYJLK3E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VY5ATNVME7IU7SHFV52NYJLK3E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VY5ATNVME7IU7SHFV52NYJLK3E","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":"e2c66bbcf878aa12ad2e9fff33876e5a61e3ef303e177bebda66c4c48507e001","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-23T10:58:22Z","title_canon_sha256":"074b6188a9014f75487377466dc144ce023b0814909c8ee0b5ce4923ae03a424"},"schema_version":"1.0","source":{"id":"2505.17736","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17736","created_at":"2026-07-05T11:08:31Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17736v1","created_at":"2026-07-05T11:08:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17736","created_at":"2026-07-05T11:08:31Z"},{"alias_kind":"pith_short_12","alias_value":"VY5ATNVME7IU","created_at":"2026-07-05T11:08:31Z"},{"alias_kind":"pith_short_16","alias_value":"VY5ATNVME7IU7SHF","created_at":"2026-07-05T11:08:31Z"},{"alias_kind":"pith_short_8","alias_value":"VY5ATNVM","created_at":"2026-07-05T11:08:31Z"}],"graph_snapshots":[{"event_id":"sha256:9e7cc06c48154185c555157847d6ac365c38dce2ae08de0e2fd0aacca0034c80","target":"graph","created_at":"2026-07-05T11:08:31Z","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/2505.17736/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While standard IR models are mainly designed to optimize relevance, real-world search often needs to balance additional objectives such as diversity and fairness. These objectives depend on inter-document interactions and are commonly addressed using post-hoc heuristics or supervised learning methods, which require task-specific training for each ranking scenario and dataset. In this work, we propose an in-context learning (ICL) approach that eliminates the need for such training. Instead, our method relies on a small number of example rankings that demonstrate the desired trade-offs between o","authors_text":"Andrew Parry, Debasis Ganguly, Nilanjan Sinhababu, Pabitra Mitra","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-23T10:58:22Z","title":"Modeling Ranking Properties with In-Context Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17736","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:fddac623a2f86dfdbfa2fc90a7d63996ad3fb3799a679f7279d540f1705571e5","target":"record","created_at":"2026-07-05T11:08:31Z","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":"e2c66bbcf878aa12ad2e9fff33876e5a61e3ef303e177bebda66c4c48507e001","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-23T10:58:22Z","title_canon_sha256":"074b6188a9014f75487377466dc144ce023b0814909c8ee0b5ce4923ae03a424"},"schema_version":"1.0","source":{"id":"2505.17736","kind":"arxiv","version":1}},"canonical_sha256":"ae3a09b6ac27d14fc8e5af74dc256ad9341169593cf7def1a1b99258092a9938","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae3a09b6ac27d14fc8e5af74dc256ad9341169593cf7def1a1b99258092a9938","first_computed_at":"2026-07-05T11:08:31.027702Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:31.027702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2w+MGI5IgDP9XgDhklu6mSbv/VvoMeC94uPWwBkl/3uaqRszkoqX72M6+scwJJWQaxOura4Bvpk+H479IwdoDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:31.028137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17736","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fddac623a2f86dfdbfa2fc90a7d63996ad3fb3799a679f7279d540f1705571e5","sha256:9e7cc06c48154185c555157847d6ac365c38dce2ae08de0e2fd0aacca0034c80"],"state_sha256":"c36de706fe38f700485e5a7fa08be67d19b48a45e258297cb6835919f316f5ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3VnAyA024e18w2xoQGuqpxi7lQMjZIyntmcLMny2ULq6u3r2hTkSXOJsrnUFSK1MWKl/tqYy4RFJ8H+jEogBAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T14:12:20.955505Z","bundle_sha256":"d7aec44a03a853be9e6e8861bd9395acb9df5d61a5572a0d713f259f8db79cc3"}}