{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NBC32NZGCJFGABFKHYR27PW5CW","short_pith_number":"pith:NBC32NZG","canonical_record":{"source":{"id":"2507.06622","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T07:49:55Z","cross_cats_sorted":[],"title_canon_sha256":"8b71a508ea5d80440d005b108f8f2128585055b3712bd310317cc67343c76aac","abstract_canon_sha256":"821aebcfbba9a217a29bfedae16696d4bb854389715f3d48d618fefaebb21210"},"schema_version":"1.0"},"canonical_sha256":"6845bd3726124a6004aa3e23afbedd15a5debc8595d220c6908b0f11d6a3d941","source":{"kind":"arxiv","id":"2507.06622","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06622","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06622v1","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06622","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"pith_short_12","alias_value":"NBC32NZGCJFG","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"pith_short_16","alias_value":"NBC32NZGCJFGABFK","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"pith_short_8","alias_value":"NBC32NZG","created_at":"2026-07-05T11:34:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NBC32NZGCJFGABFKHYR27PW5CW","target":"record","payload":{"canonical_record":{"source":{"id":"2507.06622","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T07:49:55Z","cross_cats_sorted":[],"title_canon_sha256":"8b71a508ea5d80440d005b108f8f2128585055b3712bd310317cc67343c76aac","abstract_canon_sha256":"821aebcfbba9a217a29bfedae16696d4bb854389715f3d48d618fefaebb21210"},"schema_version":"1.0"},"canonical_sha256":"6845bd3726124a6004aa3e23afbedd15a5debc8595d220c6908b0f11d6a3d941","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:19.600467Z","signature_b64":"KwjVqLZYS296x+XQ69qrV1t/S4MHsIsmu8SlXFzafmTDehJAsWptNfKo+xUtAn3CkUSIhNSr1BbRz1QOT7nqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6845bd3726124a6004aa3e23afbedd15a5debc8595d220c6908b0f11d6a3d941","last_reissued_at":"2026-07-05T11:34:19.599735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:19.599735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.06622","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":"2026-07-05T11:34:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7IC/+VDVl+PNY/ys6ujovQt9/2UFwqX+izxBYZ9pnVYalH0Wz70cPvQHP0G1vy6wuvIN7dxpg5Jwg5XrlczSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:03:53.946832Z"},"content_sha256":"fb72302a854398ebdc36a641d466ffe60b63ebbca05122f9adc1954daea836a4","schema_version":"1.0","event_id":"sha256:fb72302a854398ebdc36a641d466ffe60b63ebbca05122f9adc1954daea836a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NBC32NZGCJFGABFKHYR27PW5CW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FuDoBa: Fusing Document and Knowledge Graph-based Representations with Bayesian Optimisation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bla\\v{z} \\v{S}krlj, Boshko Koloski, Roberto Navigli, Senja Pollak","submitted_at":"2025-07-09T07:49:55Z","abstract_excerpt":"Building on the success of Large Language Models (LLMs), LLM-based representations have dominated the document representation landscape, achieving great performance on the document embedding benchmarks. However, the high-dimensional, computationally expensive embeddings from LLMs tend to be either too generic or inefficient for domain-specific applications. To address these limitations, we introduce FuDoBa a Bayesian optimisation-based method that integrates LLM-based embeddings with domain-specific structured knowledge, sourced both locally and from external repositories like WikiData. This f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06622","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/2507.06622/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":"2026-07-05T11:34:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/YLEtB3PEXI35H2ufJWbgmA/h7d8Hv5qsvmiQY2AauLMw3PxqQOpNoXuatTcv6gRupmzNVLwBxBAEMzbA24vAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:03:53.947338Z"},"content_sha256":"57de64256edc2c83c97fd4704a0b39885f7ed71a644fb5f56e6823ae8541db3b","schema_version":"1.0","event_id":"sha256:57de64256edc2c83c97fd4704a0b39885f7ed71a644fb5f56e6823ae8541db3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NBC32NZGCJFGABFKHYR27PW5CW/bundle.json","state_url":"https://pith.science/pith/NBC32NZGCJFGABFKHYR27PW5CW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NBC32NZGCJFGABFKHYR27PW5CW/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":"2026-08-08T04:03:53Z","links":{"resolver":"https://pith.science/pith/NBC32NZGCJFGABFKHYR27PW5CW","bundle":"https://pith.science/pith/NBC32NZGCJFGABFKHYR27PW5CW/bundle.json","state":"https://pith.science/pith/NBC32NZGCJFGABFKHYR27PW5CW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NBC32NZGCJFGABFKHYR27PW5CW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NBC32NZGCJFGABFKHYR27PW5CW","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":"821aebcfbba9a217a29bfedae16696d4bb854389715f3d48d618fefaebb21210","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T07:49:55Z","title_canon_sha256":"8b71a508ea5d80440d005b108f8f2128585055b3712bd310317cc67343c76aac"},"schema_version":"1.0","source":{"id":"2507.06622","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06622","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06622v1","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06622","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"pith_short_12","alias_value":"NBC32NZGCJFG","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"pith_short_16","alias_value":"NBC32NZGCJFGABFK","created_at":"2026-07-05T11:34:19Z"},{"alias_kind":"pith_short_8","alias_value":"NBC32NZG","created_at":"2026-07-05T11:34:19Z"}],"graph_snapshots":[{"event_id":"sha256:57de64256edc2c83c97fd4704a0b39885f7ed71a644fb5f56e6823ae8541db3b","target":"graph","created_at":"2026-07-05T11:34:19Z","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/2507.06622/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building on the success of Large Language Models (LLMs), LLM-based representations have dominated the document representation landscape, achieving great performance on the document embedding benchmarks. However, the high-dimensional, computationally expensive embeddings from LLMs tend to be either too generic or inefficient for domain-specific applications. To address these limitations, we introduce FuDoBa a Bayesian optimisation-based method that integrates LLM-based embeddings with domain-specific structured knowledge, sourced both locally and from external repositories like WikiData. This f","authors_text":"Bla\\v{z} \\v{S}krlj, Boshko Koloski, Roberto Navigli, Senja Pollak","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T07:49:55Z","title":"FuDoBa: Fusing Document and Knowledge Graph-based Representations with Bayesian Optimisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06622","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:fb72302a854398ebdc36a641d466ffe60b63ebbca05122f9adc1954daea836a4","target":"record","created_at":"2026-07-05T11:34:19Z","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":"821aebcfbba9a217a29bfedae16696d4bb854389715f3d48d618fefaebb21210","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-09T07:49:55Z","title_canon_sha256":"8b71a508ea5d80440d005b108f8f2128585055b3712bd310317cc67343c76aac"},"schema_version":"1.0","source":{"id":"2507.06622","kind":"arxiv","version":1}},"canonical_sha256":"6845bd3726124a6004aa3e23afbedd15a5debc8595d220c6908b0f11d6a3d941","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6845bd3726124a6004aa3e23afbedd15a5debc8595d220c6908b0f11d6a3d941","first_computed_at":"2026-07-05T11:34:19.599735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:19.599735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KwjVqLZYS296x+XQ69qrV1t/S4MHsIsmu8SlXFzafmTDehJAsWptNfKo+xUtAn3CkUSIhNSr1BbRz1QOT7nqCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:19.600467Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06622","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb72302a854398ebdc36a641d466ffe60b63ebbca05122f9adc1954daea836a4","sha256:57de64256edc2c83c97fd4704a0b39885f7ed71a644fb5f56e6823ae8541db3b"],"state_sha256":"9fef3f271f5a1d03d44ee12b482e4abbb7cfada7c8ce973f9ba0e5a000c0d19e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Oz8LKr5/PFYDrGkfBM4//XvEW4As5oJTTXPvlZu+g8/Y8EWrd1oGq1sh3agLy2tMooS7CRk3vzNYxDrRtDLECQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:03:53.952297Z","bundle_sha256":"10950c15a1ee5b9b02482e984da3cd3fe838918c64c7fda55dace419e121b7b8"}}