{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LRVROURXK2GNYMGZ6UK4DMOUC3","short_pith_number":"pith:LRVROURX","canonical_record":{"source":{"id":"2603.19250","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-25T06:20:36Z","cross_cats_sorted":[],"title_canon_sha256":"9349504ad81f6947ed17a4c7ef62e184389b61b14ff526e9b5b4850b71b57efa","abstract_canon_sha256":"6a931c419a4666655097c418d56fbd63b34d2761948621cc24993e920ceb88d1"},"schema_version":"1.0"},"canonical_sha256":"5c6b175237568cdc30d9f515c1b1d416d64d25dc12c0f735b45d70e6e9ee7325","source":{"kind":"arxiv","id":"2603.19250","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.19250","created_at":"2026-06-03T01:05:11Z"},{"alias_kind":"arxiv_version","alias_value":"2603.19250v2","created_at":"2026-06-03T01:05:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.19250","created_at":"2026-06-03T01:05:11Z"},{"alias_kind":"pith_short_12","alias_value":"LRVROURXK2GN","created_at":"2026-06-03T01:05:11Z"},{"alias_kind":"pith_short_16","alias_value":"LRVROURXK2GNYMGZ","created_at":"2026-06-03T01:05:11Z"},{"alias_kind":"pith_short_8","alias_value":"LRVROURX","created_at":"2026-06-03T01:05:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LRVROURXK2GNYMGZ6UK4DMOUC3","target":"record","payload":{"canonical_record":{"source":{"id":"2603.19250","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-25T06:20:36Z","cross_cats_sorted":[],"title_canon_sha256":"9349504ad81f6947ed17a4c7ef62e184389b61b14ff526e9b5b4850b71b57efa","abstract_canon_sha256":"6a931c419a4666655097c418d56fbd63b34d2761948621cc24993e920ceb88d1"},"schema_version":"1.0"},"canonical_sha256":"5c6b175237568cdc30d9f515c1b1d416d64d25dc12c0f735b45d70e6e9ee7325","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:11.939386Z","signature_b64":"pGTTdHxGYyxk60wZP03NMUF0Be/Rn6NB1nwXzEnk9fcobq1iOsDFsWd0G3tmExCRm/sYdezz57go0a6stcbzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c6b175237568cdc30d9f515c1b1d416d64d25dc12c0f735b45d70e6e9ee7325","last_reissued_at":"2026-06-03T01:05:11.938831Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:11.938831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.19250","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DZQw71JPXTcbbno28JMRmIgLslTkNtaC6EGburFPZ3Gs+EUGbx1kg4QSw4wDez4WbQCTEVYJnsyNxR8hyBQgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T17:59:05.420664Z"},"content_sha256":"e5788b25140832c96ffa0da2f77924bcbd0d77a136840493aad6886783b91e0f","schema_version":"1.0","event_id":"sha256:e5788b25140832c96ffa0da2f77924bcbd0d77a136840493aad6886783b91e0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LRVROURXK2GNYMGZ6UK4DMOUC3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Structural Cues Save LLMs? Evaluating Language Models in Massive Document Streams","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Susik Yoon, Wonjun Choi, Woojun Jung, Yebin Lim, Yukyung Lee","submitted_at":"2026-02-25T06:20:36Z","abstract_excerpt":"Evaluating language models in streaming environments is critical, yet underexplored. Existing benchmarks either focus on single complex events or provide curated inputs for each query, and do not evaluate models under the conflicts that arise when multiple concurrent events are mixed within the same document stream. We introduce StreamBench, a benchmark built from major news stories in 2016 and 2025, comprising 605 events and 15,354 documents across three tasks: Topic Clustering, Temporal Question Answering, and Summarization. To diagnose how models fail, we compare performance with and withou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.19250","kind":"arxiv","version":2},"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/2603.19250/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":"2026-06-03T01:05:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"45O+mebXI2R10+GSqvGEmEdnqM95ALPaGKXzLAaS2npF1phgO3XemyOO+beiu0dQpZ+dTcdNfXtNglhvuOiDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T17:59:05.421040Z"},"content_sha256":"e8e61762035fe42cae513947a6c7e1984147689760213717cdf26765f4761264","schema_version":"1.0","event_id":"sha256:e8e61762035fe42cae513947a6c7e1984147689760213717cdf26765f4761264"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LRVROURXK2GNYMGZ6UK4DMOUC3/bundle.json","state_url":"https://pith.science/pith/LRVROURXK2GNYMGZ6UK4DMOUC3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LRVROURXK2GNYMGZ6UK4DMOUC3/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":"2026-06-04T17:59:05Z","links":{"resolver":"https://pith.science/pith/LRVROURXK2GNYMGZ6UK4DMOUC3","bundle":"https://pith.science/pith/LRVROURXK2GNYMGZ6UK4DMOUC3/bundle.json","state":"https://pith.science/pith/LRVROURXK2GNYMGZ6UK4DMOUC3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LRVROURXK2GNYMGZ6UK4DMOUC3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LRVROURXK2GNYMGZ6UK4DMOUC3","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":"6a931c419a4666655097c418d56fbd63b34d2761948621cc24993e920ceb88d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-25T06:20:36Z","title_canon_sha256":"9349504ad81f6947ed17a4c7ef62e184389b61b14ff526e9b5b4850b71b57efa"},"schema_version":"1.0","source":{"id":"2603.19250","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.19250","created_at":"2026-06-03T01:05:11Z"},{"alias_kind":"arxiv_version","alias_value":"2603.19250v2","created_at":"2026-06-03T01:05:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.19250","created_at":"2026-06-03T01:05:11Z"},{"alias_kind":"pith_short_12","alias_value":"LRVROURXK2GN","created_at":"2026-06-03T01:05:11Z"},{"alias_kind":"pith_short_16","alias_value":"LRVROURXK2GNYMGZ","created_at":"2026-06-03T01:05:11Z"},{"alias_kind":"pith_short_8","alias_value":"LRVROURX","created_at":"2026-06-03T01:05:11Z"}],"graph_snapshots":[{"event_id":"sha256:e8e61762035fe42cae513947a6c7e1984147689760213717cdf26765f4761264","target":"graph","created_at":"2026-06-03T01:05:11Z","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/2603.19250/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating language models in streaming environments is critical, yet underexplored. Existing benchmarks either focus on single complex events or provide curated inputs for each query, and do not evaluate models under the conflicts that arise when multiple concurrent events are mixed within the same document stream. We introduce StreamBench, a benchmark built from major news stories in 2016 and 2025, comprising 605 events and 15,354 documents across three tasks: Topic Clustering, Temporal Question Answering, and Summarization. To diagnose how models fail, we compare performance with and withou","authors_text":"Susik Yoon, Wonjun Choi, Woojun Jung, Yebin Lim, Yukyung Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-25T06:20:36Z","title":"Can Structural Cues Save LLMs? Evaluating Language Models in Massive Document Streams"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.19250","kind":"arxiv","version":2},"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:e5788b25140832c96ffa0da2f77924bcbd0d77a136840493aad6886783b91e0f","target":"record","created_at":"2026-06-03T01:05:11Z","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":"6a931c419a4666655097c418d56fbd63b34d2761948621cc24993e920ceb88d1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-25T06:20:36Z","title_canon_sha256":"9349504ad81f6947ed17a4c7ef62e184389b61b14ff526e9b5b4850b71b57efa"},"schema_version":"1.0","source":{"id":"2603.19250","kind":"arxiv","version":2}},"canonical_sha256":"5c6b175237568cdc30d9f515c1b1d416d64d25dc12c0f735b45d70e6e9ee7325","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c6b175237568cdc30d9f515c1b1d416d64d25dc12c0f735b45d70e6e9ee7325","first_computed_at":"2026-06-03T01:05:11.938831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:11.938831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pGTTdHxGYyxk60wZP03NMUF0Be/Rn6NB1nwXzEnk9fcobq1iOsDFsWd0G3tmExCRm/sYdezz57go0a6stcbzBA==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:11.939386Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.19250","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5788b25140832c96ffa0da2f77924bcbd0d77a136840493aad6886783b91e0f","sha256:e8e61762035fe42cae513947a6c7e1984147689760213717cdf26765f4761264"],"state_sha256":"d26b0965408c3314dc3776dbcb095e45aa4292f042bb2ed27111b42ca9f98b00"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eT1NCI95E3bsRg9Wi8nh0KkgScp00iDFX8fhmFvsaFHTMGSabLaAjjoTSY9DTnIxEfnZ+5E+R+TXW2l7hxx0CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T17:59:05.423016Z","bundle_sha256":"44cca1f3f12c3d0c9deaf850d811f2c50b04700a6c5ab8063de4e805ff533920"}}