{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2UDX2LKAEVUTBJDC2BJVLAMX22","short_pith_number":"pith:2UDX2LKA","canonical_record":{"source":{"id":"2507.10726","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-14T18:47:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"860f360d724d0be2b92de09301ea73694636c4988c8c969318b36ed5a5ed6be8","abstract_canon_sha256":"e817e3ef34df3d0e25dd3560947f4f0892b6d7f828a674a31edb826a2ca03753"},"schema_version":"1.0"},"canonical_sha256":"d5077d2d40256930a462d053558197d6b62277336f7c7e5af586626c9342a9cf","source":{"kind":"arxiv","id":"2507.10726","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10726","created_at":"2026-07-05T11:36:59Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10726v1","created_at":"2026-07-05T11:36:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10726","created_at":"2026-07-05T11:36:59Z"},{"alias_kind":"pith_short_12","alias_value":"2UDX2LKAEVUT","created_at":"2026-07-05T11:36:59Z"},{"alias_kind":"pith_short_16","alias_value":"2UDX2LKAEVUTBJDC","created_at":"2026-07-05T11:36:59Z"},{"alias_kind":"pith_short_8","alias_value":"2UDX2LKA","created_at":"2026-07-05T11:36:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2UDX2LKAEVUTBJDC2BJVLAMX22","target":"record","payload":{"canonical_record":{"source":{"id":"2507.10726","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-14T18:47:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"860f360d724d0be2b92de09301ea73694636c4988c8c969318b36ed5a5ed6be8","abstract_canon_sha256":"e817e3ef34df3d0e25dd3560947f4f0892b6d7f828a674a31edb826a2ca03753"},"schema_version":"1.0"},"canonical_sha256":"d5077d2d40256930a462d053558197d6b62277336f7c7e5af586626c9342a9cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:59.014880Z","signature_b64":"jn7EuT5CLtYGnYiP3Ui+kFcMsq6bPzQyu4FaZ0SSjBCu6Qtft7o/QLq40qfiJ3obxaxodzFIeUZcAIde5uGmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5077d2d40256930a462d053558197d6b62277336f7c7e5af586626c9342a9cf","last_reissued_at":"2026-07-05T11:36:59.014496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:59.014496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.10726","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":"2026-07-05T11:36:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y4PWT9aqZZAXPYhJ4LXKeKPYypSzPOlZW/PlWeBflVmq5rGao8fGdgvKLOmcVGXWzFnRSlIH2Uy/GhF6LriADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:47:47.306752Z"},"content_sha256":"b2612f19c06e7f7d4184068aa09d89e3aa49dc7c2f7a65c3b40249ab7ace4e73","schema_version":"1.0","event_id":"sha256:b2612f19c06e7f7d4184068aa09d89e3aa49dc7c2f7a65c3b40249ab7ace4e73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2UDX2LKAEVUTBJDC2BJVLAMX22","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extracting Document Relations from Search Corpus by Marginalizing over User Queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Kaoru Tsunoda, Ken Kaneiwa, Yuki Iwamoto","submitted_at":"2025-07-14T18:47:13Z","abstract_excerpt":"Understanding relationships between documents in large-scale corpora is essential for knowledge discovery and information organization. However, existing approaches rely heavily on manual annotation or predefined relationship taxonomies. We propose EDR-MQ (Extracting Document Relations by Marginalizing over User Queries), a novel framework that discovers document relationships through query marginalization. EDR-MQ is based on the insight that strongly related documents often co-occur in results across diverse user queries, enabling us to estimate joint probabilities between document pairs by m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10726","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/2507.10726/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":"2026-07-05T11:36:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zJWnZFmvWSnM5CEaJ5YRFL87rHhu6Qm1wV3QJO1Es9CkhFg8eqtsBWKBMXipXTlzfwgsDFMEpIPr0XDKAGWBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:47:47.307281Z"},"content_sha256":"2f1880b83417b6399a5cf34c117e66d1a7ca335dc870d391b8538ef117c77603","schema_version":"1.0","event_id":"sha256:2f1880b83417b6399a5cf34c117e66d1a7ca335dc870d391b8538ef117c77603"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2UDX2LKAEVUTBJDC2BJVLAMX22/bundle.json","state_url":"https://pith.science/pith/2UDX2LKAEVUTBJDC2BJVLAMX22/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2UDX2LKAEVUTBJDC2BJVLAMX22/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":"2026-08-08T15:47:47Z","links":{"resolver":"https://pith.science/pith/2UDX2LKAEVUTBJDC2BJVLAMX22","bundle":"https://pith.science/pith/2UDX2LKAEVUTBJDC2BJVLAMX22/bundle.json","state":"https://pith.science/pith/2UDX2LKAEVUTBJDC2BJVLAMX22/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2UDX2LKAEVUTBJDC2BJVLAMX22/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2UDX2LKAEVUTBJDC2BJVLAMX22","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":"e817e3ef34df3d0e25dd3560947f4f0892b6d7f828a674a31edb826a2ca03753","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-14T18:47:13Z","title_canon_sha256":"860f360d724d0be2b92de09301ea73694636c4988c8c969318b36ed5a5ed6be8"},"schema_version":"1.0","source":{"id":"2507.10726","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10726","created_at":"2026-07-05T11:36:59Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10726v1","created_at":"2026-07-05T11:36:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10726","created_at":"2026-07-05T11:36:59Z"},{"alias_kind":"pith_short_12","alias_value":"2UDX2LKAEVUT","created_at":"2026-07-05T11:36:59Z"},{"alias_kind":"pith_short_16","alias_value":"2UDX2LKAEVUTBJDC","created_at":"2026-07-05T11:36:59Z"},{"alias_kind":"pith_short_8","alias_value":"2UDX2LKA","created_at":"2026-07-05T11:36:59Z"}],"graph_snapshots":[{"event_id":"sha256:2f1880b83417b6399a5cf34c117e66d1a7ca335dc870d391b8538ef117c77603","target":"graph","created_at":"2026-07-05T11:36:59Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.10726/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding relationships between documents in large-scale corpora is essential for knowledge discovery and information organization. However, existing approaches rely heavily on manual annotation or predefined relationship taxonomies. We propose EDR-MQ (Extracting Document Relations by Marginalizing over User Queries), a novel framework that discovers document relationships through query marginalization. EDR-MQ is based on the insight that strongly related documents often co-occur in results across diverse user queries, enabling us to estimate joint probabilities between document pairs by m","authors_text":"Kaoru Tsunoda, Ken Kaneiwa, Yuki Iwamoto","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-14T18:47:13Z","title":"Extracting Document Relations from Search Corpus by Marginalizing over User Queries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10726","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:b2612f19c06e7f7d4184068aa09d89e3aa49dc7c2f7a65c3b40249ab7ace4e73","target":"record","created_at":"2026-07-05T11:36:59Z","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":"e817e3ef34df3d0e25dd3560947f4f0892b6d7f828a674a31edb826a2ca03753","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-14T18:47:13Z","title_canon_sha256":"860f360d724d0be2b92de09301ea73694636c4988c8c969318b36ed5a5ed6be8"},"schema_version":"1.0","source":{"id":"2507.10726","kind":"arxiv","version":1}},"canonical_sha256":"d5077d2d40256930a462d053558197d6b62277336f7c7e5af586626c9342a9cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5077d2d40256930a462d053558197d6b62277336f7c7e5af586626c9342a9cf","first_computed_at":"2026-07-05T11:36:59.014496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:59.014496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jn7EuT5CLtYGnYiP3Ui+kFcMsq6bPzQyu4FaZ0SSjBCu6Qtft7o/QLq40qfiJ3obxaxodzFIeUZcAIde5uGmBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:59.014880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.10726","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2612f19c06e7f7d4184068aa09d89e3aa49dc7c2f7a65c3b40249ab7ace4e73","sha256:2f1880b83417b6399a5cf34c117e66d1a7ca335dc870d391b8538ef117c77603"],"state_sha256":"de8f82ec8ca552a0b12cbe079951dcd3f0083ce97a0857059025e26467585740"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fIA4HCtW5ht03Nh9A5sPW9xUPfJDIVYtJVIBnhoV/WaXLPfHIjSlY/eQJfcuLfl1+IddNjc1b2RZsOz6gXNaAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:47:47.311412Z","bundle_sha256":"6d83a2f2fdcada6b8f5326215a124cbb8c33e4cde8536ba304e07d085ecbc614"}}