{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LPRDPQ2T2SVLAJDA2YZJOZRF4M","short_pith_number":"pith:LPRDPQ2T","canonical_record":{"source":{"id":"2605.18410","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2026-05-18T13:48:58Z","cross_cats_sorted":[],"title_canon_sha256":"f37eaa24c0d138982c7c9e9ca38bad50bef5aec81aa9c6f80a24dc404292649b","abstract_canon_sha256":"b59dc24f3b7d5fa91faa1d83431ab5b3442f61fd6d8bb509f7d43ac679039990"},"schema_version":"1.0"},"canonical_sha256":"5be237c353d4aab02460d632976625e3285982c2d5453351574a1ff00bdd9bf3","source":{"kind":"arxiv","id":"2605.18410","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18410","created_at":"2026-05-20T00:05:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18410v1","created_at":"2026-05-20T00:05:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18410","created_at":"2026-05-20T00:05:59Z"},{"alias_kind":"pith_short_12","alias_value":"LPRDPQ2T2SVL","created_at":"2026-05-20T00:05:59Z"},{"alias_kind":"pith_short_16","alias_value":"LPRDPQ2T2SVLAJDA","created_at":"2026-05-20T00:05:59Z"},{"alias_kind":"pith_short_8","alias_value":"LPRDPQ2T","created_at":"2026-05-20T00:05:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LPRDPQ2T2SVLAJDA2YZJOZRF4M","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18410","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2026-05-18T13:48:58Z","cross_cats_sorted":[],"title_canon_sha256":"f37eaa24c0d138982c7c9e9ca38bad50bef5aec81aa9c6f80a24dc404292649b","abstract_canon_sha256":"b59dc24f3b7d5fa91faa1d83431ab5b3442f61fd6d8bb509f7d43ac679039990"},"schema_version":"1.0"},"canonical_sha256":"5be237c353d4aab02460d632976625e3285982c2d5453351574a1ff00bdd9bf3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:59.385295Z","signature_b64":"XJlM9923n1Uc2BNWg12EVEhkJ1LBGv/u4c8Bah6N0T6nd4TqBFYAGCUuemfMhDwGpBwQSjEPUb2MWzo/gasbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5be237c353d4aab02460d632976625e3285982c2d5453351574a1ff00bdd9bf3","last_reissued_at":"2026-05-20T00:05:59.384559Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:59.384559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18410","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":"2026-05-20T00:05:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TuDgy8sh2iYkoIKPWGtAmDLD65r4EG9kC2tkX8MHSymoUWB9iyqJ54wCGeM0PHnJHfWgrODbCZA1h9poDvyuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T14:58:08.856630Z"},"content_sha256":"814024ac104448957a2991a7e8e65ff4524a4dece91ca76ad385ab1e1444911b","schema_version":"1.0","event_id":"sha256:814024ac104448957a2991a7e8e65ff4524a4dece91ca76ad385ab1e1444911b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LPRDPQ2T2SVLAJDA2YZJOZRF4M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Node2Vec to GPT-based GraphRAG: scientific impact prediction across graph and language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Directed citation graphs combined with textual embeddings predict scientific impact with 0.84-0.85 AUC, while GPT prompts without retrieval often match GraphRAG performance at 0.87.","cross_cats":[],"primary_cat":"cs.DL","authors_text":"Adilson Vital Jr., Diego R. Amancio, Filipi N. Silva","submitted_at":"2026-05-18T13:48:58Z","abstract_excerpt":"Identifying which newly published scientific papers are likely to become highly cited is important for prioritizing research attention, supporting editorial decisions, and guiding the allocation of scientific resources, particularly under cold-start conditions where little direct evidence is available at publication time. In this work, we formulate impact prediction as a cohort-normalized top-P% classification task and compare graph-based and LLM-based approaches under a unified framework. We construct citation and textual-similarity graphs under temporal constraints and generate Node2Vec repr"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The best supervised configuration combines directed citation graphs with textual embeddings, reaching approximately 0.84-0.85 AUC. [...] target-only prompts often perform as well as or better than GraphRAG prompts achieving the 0.87 mark.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That cohort-normalized top-P% citation rank measured years later is a stable and unbiased proxy for scientific impact that can be meaningfully predicted from information available at publication time under temporal graph constraints.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Directed citation graphs plus textual embeddings reach 0.84-0.85 AUC for top-P% impact classification while GPT-5.5/5.4 Nano prompts hit 0.87 but show no consistent gain from retrieved graph neighborhoods over target-only baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Directed citation graphs combined with textual embeddings predict scientific impact with 0.84-0.85 AUC, while GPT prompts without retrieval often match GraphRAG performance at 0.87.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"db61ce579af1a3445e790a317758fb5139f4d61a58099c9e3ff25df5d7d045a4"},"source":{"id":"2605.18410","kind":"arxiv","version":1},"verdict":{"id":"443a19c5-afb6-43b7-83bc-aea9d39f0d27","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T23:29:39.693665Z","strongest_claim":"The best supervised configuration combines directed citation graphs with textual embeddings, reaching approximately 0.84-0.85 AUC. [...] target-only prompts often perform as well as or better than GraphRAG prompts achieving the 0.87 mark.","one_line_summary":"Directed citation graphs plus textual embeddings reach 0.84-0.85 AUC for top-P% impact classification while GPT-5.5/5.4 Nano prompts hit 0.87 but show no consistent gain from retrieved graph neighborhoods over target-only baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That cohort-normalized top-P% citation rank measured years later is a stable and unbiased proxy for scientific impact that can be meaningfully predicted from information available at publication time under temporal graph constraints.","pith_extraction_headline":"Directed citation graphs combined with textual embeddings predict scientific impact with 0.84-0.85 AUC, while GPT prompts without retrieval often match GraphRAG performance at 0.87."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.18410/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-20T00:01:20.293918Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T23:51:58.273520Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T23:49:59.512686Z","status":"completed","version":"0.1.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T23:40:55.444477Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:29.258436Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"external_links","ran_at":"2026-05-19T23:31:38.560226Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T23:21:58.704620Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"244c8ea9ec92d328b441fc040be2b6ad647d9a4b3086ddf02b525455a99c8bb5"},"references":{"count":57,"sample":[{"doi":"","year":2009,"title":"The number of papers published yearly is shown in Figure 2","work_id":"8b567498-d922-4a16-81da-1cb625cf383e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2009,"title":"For both graph types we created four variations based on (i) edge direction (directed vs","work_id":"440a6ebe-7ae3-49ce-8dd5-315277db8b7b","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Each graph family is further expanded by two edge direction types (directed vs","work_id":"80f56783-6e7e-41d6-831b-72c05e989b1e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2048,"title":"Impact classification In the final phase, we use the embeddings from the previous phase as inputs to a su- pervised classification model that predicts whether each paper will be a “top paper” un- der ","work_id":"2bf0032e-236b-4f1c-ae38-5ebdeed91d77","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2050,"title":"We retain the 13 FIG","work_id":"be5759a5-4bea-428b-a0eb-9c9454618d35","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":57,"snapshot_sha256":"8f99577121bb48edaedf5ec1c791746545fe1b65495e7ac6b7a4cc4ca7dd47b8","internal_anchors":3},"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":"443a19c5-afb6-43b7-83bc-aea9d39f0d27"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DfcgxuBlCLmElgGBhwiD8LficJ0ukxggFfZ1+xc981lUemMNpCgg/ILDQxit5DICHealuGqnvhllJILXLVOPDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T14:58:08.857788Z"},"content_sha256":"6f274436667427ab19720a7f325ef347899918e785417c702e6667e29f3d62c1","schema_version":"1.0","event_id":"sha256:6f274436667427ab19720a7f325ef347899918e785417c702e6667e29f3d62c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LPRDPQ2T2SVLAJDA2YZJOZRF4M/bundle.json","state_url":"https://pith.science/pith/LPRDPQ2T2SVLAJDA2YZJOZRF4M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LPRDPQ2T2SVLAJDA2YZJOZRF4M/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":"2026-05-25T14:58:08Z","links":{"resolver":"https://pith.science/pith/LPRDPQ2T2SVLAJDA2YZJOZRF4M","bundle":"https://pith.science/pith/LPRDPQ2T2SVLAJDA2YZJOZRF4M/bundle.json","state":"https://pith.science/pith/LPRDPQ2T2SVLAJDA2YZJOZRF4M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LPRDPQ2T2SVLAJDA2YZJOZRF4M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LPRDPQ2T2SVLAJDA2YZJOZRF4M","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":"b59dc24f3b7d5fa91faa1d83431ab5b3442f61fd6d8bb509f7d43ac679039990","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2026-05-18T13:48:58Z","title_canon_sha256":"f37eaa24c0d138982c7c9e9ca38bad50bef5aec81aa9c6f80a24dc404292649b"},"schema_version":"1.0","source":{"id":"2605.18410","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18410","created_at":"2026-05-20T00:05:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18410v1","created_at":"2026-05-20T00:05:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18410","created_at":"2026-05-20T00:05:59Z"},{"alias_kind":"pith_short_12","alias_value":"LPRDPQ2T2SVL","created_at":"2026-05-20T00:05:59Z"},{"alias_kind":"pith_short_16","alias_value":"LPRDPQ2T2SVLAJDA","created_at":"2026-05-20T00:05:59Z"},{"alias_kind":"pith_short_8","alias_value":"LPRDPQ2T","created_at":"2026-05-20T00:05:59Z"}],"graph_snapshots":[{"event_id":"sha256:6f274436667427ab19720a7f325ef347899918e785417c702e6667e29f3d62c1","target":"graph","created_at":"2026-05-20T00:05:59Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The best supervised configuration combines directed citation graphs with textual embeddings, reaching approximately 0.84-0.85 AUC. [...] target-only prompts often perform as well as or better than GraphRAG prompts achieving the 0.87 mark."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That cohort-normalized top-P% citation rank measured years later is a stable and unbiased proxy for scientific impact that can be meaningfully predicted from information available at publication time under temporal graph constraints."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Directed citation graphs plus textual embeddings reach 0.84-0.85 AUC for top-P% impact classification while GPT-5.5/5.4 Nano prompts hit 0.87 but show no consistent gain from retrieved graph neighborhoods over target-only baselines."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Directed citation graphs combined with textual embeddings predict scientific impact with 0.84-0.85 AUC, while GPT prompts without retrieval often match GraphRAG performance at 0.87."}],"snapshot_sha256":"db61ce579af1a3445e790a317758fb5139f4d61a58099c9e3ff25df5d7d045a4"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-20T00:01:20.293918Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T23:51:58.273520Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T23:49:59.512686Z","status":"completed","version":"0.1.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T23:40:55.444477Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:29.258436Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"external_links","ran_at":"2026-05-19T23:31:38.560226Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T23:21:58.704620Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18410/integrity.json","findings":[],"snapshot_sha256":"244c8ea9ec92d328b441fc040be2b6ad647d9a4b3086ddf02b525455a99c8bb5","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Identifying which newly published scientific papers are likely to become highly cited is important for prioritizing research attention, supporting editorial decisions, and guiding the allocation of scientific resources, particularly under cold-start conditions where little direct evidence is available at publication time. In this work, we formulate impact prediction as a cohort-normalized top-P% classification task and compare graph-based and LLM-based approaches under a unified framework. We construct citation and textual-similarity graphs under temporal constraints and generate Node2Vec repr","authors_text":"Adilson Vital Jr., Diego R. Amancio, Filipi N. Silva","cross_cats":[],"headline":"Directed citation graphs combined with textual embeddings predict scientific impact with 0.84-0.85 AUC, while GPT prompts without retrieval often match GraphRAG performance at 0.87.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2026-05-18T13:48:58Z","title":"From Node2Vec to GPT-based GraphRAG: scientific impact prediction across graph and language models"},"references":{"count":57,"internal_anchors":3,"resolved_work":57,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"The number of papers published yearly is shown in Figure 2","work_id":"8b567498-d922-4a16-81da-1cb625cf383e","year":2009},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"For both graph types we created four variations based on (i) edge direction (directed vs","work_id":"440a6ebe-7ae3-49ce-8dd5-315277db8b7b","year":2009},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Each graph family is further expanded by two edge direction types (directed vs","work_id":"80f56783-6e7e-41d6-831b-72c05e989b1e","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Impact classification In the final phase, we use the embeddings from the previous phase as inputs to a su- pervised classification model that predicts whether each paper will be a “top paper” un- der ","work_id":"2bf0032e-236b-4f1c-ae38-5ebdeed91d77","year":2048},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"We retain the 13 FIG","work_id":"be5759a5-4bea-428b-a0eb-9c9454618d35","year":2050}],"snapshot_sha256":"8f99577121bb48edaedf5ec1c791746545fe1b65495e7ac6b7a4cc4ca7dd47b8"},"source":{"id":"2605.18410","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T23:29:39.693665Z","id":"443a19c5-afb6-43b7-83bc-aea9d39f0d27","model_set":{"reader":"grok-4.3"},"one_line_summary":"Directed citation graphs plus textual embeddings reach 0.84-0.85 AUC for top-P% impact classification while GPT-5.5/5.4 Nano prompts hit 0.87 but show no consistent gain from retrieved graph neighborhoods over target-only baselines.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Directed citation graphs combined with textual embeddings predict scientific impact with 0.84-0.85 AUC, while GPT prompts without retrieval often match GraphRAG performance at 0.87.","strongest_claim":"The best supervised configuration combines directed citation graphs with textual embeddings, reaching approximately 0.84-0.85 AUC. [...] target-only prompts often perform as well as or better than GraphRAG prompts achieving the 0.87 mark.","weakest_assumption":"That cohort-normalized top-P% citation rank measured years later is a stable and unbiased proxy for scientific impact that can be meaningfully predicted from information available at publication time under temporal graph constraints."}},"verdict_id":"443a19c5-afb6-43b7-83bc-aea9d39f0d27"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:814024ac104448957a2991a7e8e65ff4524a4dece91ca76ad385ab1e1444911b","target":"record","created_at":"2026-05-20T00:05:59Z","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":"b59dc24f3b7d5fa91faa1d83431ab5b3442f61fd6d8bb509f7d43ac679039990","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2026-05-18T13:48:58Z","title_canon_sha256":"f37eaa24c0d138982c7c9e9ca38bad50bef5aec81aa9c6f80a24dc404292649b"},"schema_version":"1.0","source":{"id":"2605.18410","kind":"arxiv","version":1}},"canonical_sha256":"5be237c353d4aab02460d632976625e3285982c2d5453351574a1ff00bdd9bf3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5be237c353d4aab02460d632976625e3285982c2d5453351574a1ff00bdd9bf3","first_computed_at":"2026-05-20T00:05:59.384559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:59.384559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XJlM9923n1Uc2BNWg12EVEhkJ1LBGv/u4c8Bah6N0T6nd4TqBFYAGCUuemfMhDwGpBwQSjEPUb2MWzo/gasbDQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:59.385295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18410","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:814024ac104448957a2991a7e8e65ff4524a4dece91ca76ad385ab1e1444911b","sha256:6f274436667427ab19720a7f325ef347899918e785417c702e6667e29f3d62c1"],"state_sha256":"60b51f49cabc79357021f4570a72ddb532293c69f72eea59c8d6df711edf9559"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yg3G9I5VrGOq/oY/rTStoTv8YexDh+KkbluAMGYcOGbaTHUIHpTHNYfNtNOeNccLf7+vT8lxJ5mLEq4g4Gy3AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T14:58:08.862506Z","bundle_sha256":"a64529a7d56bb5ee19be41626ea7489e316937d12af9aa7002aa935cf08be449"}}