{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ONZNUBPN2KBNEUEI3F6PTVUCFG","short_pith_number":"pith:ONZNUBPN","canonical_record":{"source":{"id":"2305.15387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:48:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9e59a86663cce4853081b921fa54d25990cc74b56f7a246dbd51942b9b8fcafc","abstract_canon_sha256":"976f24641bd98fb851b7ed70fc1de3da078db5f2cd0c9ae305f1c6c0130a80b3"},"schema_version":"1.0"},"canonical_sha256":"7372da05edd282d25088d97cf9d68229b7af1502da0f686f983d9f367ad94858","source":{"kind":"arxiv","id":"2305.15387","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15387","created_at":"2026-07-05T06:13:34Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15387v1","created_at":"2026-07-05T06:13:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15387","created_at":"2026-07-05T06:13:34Z"},{"alias_kind":"pith_short_12","alias_value":"ONZNUBPN2KBN","created_at":"2026-07-05T06:13:34Z"},{"alias_kind":"pith_short_16","alias_value":"ONZNUBPN2KBNEUEI","created_at":"2026-07-05T06:13:34Z"},{"alias_kind":"pith_short_8","alias_value":"ONZNUBPN","created_at":"2026-07-05T06:13:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ONZNUBPN2KBNEUEI3F6PTVUCFG","target":"record","payload":{"canonical_record":{"source":{"id":"2305.15387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:48:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9e59a86663cce4853081b921fa54d25990cc74b56f7a246dbd51942b9b8fcafc","abstract_canon_sha256":"976f24641bd98fb851b7ed70fc1de3da078db5f2cd0c9ae305f1c6c0130a80b3"},"schema_version":"1.0"},"canonical_sha256":"7372da05edd282d25088d97cf9d68229b7af1502da0f686f983d9f367ad94858","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:34.648213Z","signature_b64":"qSZ3THsUU8xVI0PxGuwRvG/oJVYa7Sx3bG93F2P+XAKvhwaK/Ndn+hcqoqzc1gq0C3S/sQ6EkhiJ9Gmq685sDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7372da05edd282d25088d97cf9d68229b7af1502da0f686f983d9f367ad94858","last_reissued_at":"2026-07-05T06:13:34.647860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:34.647860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.15387","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":"2026-07-05T06:13:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fqpv0HNZF13nSdOr10zXAoRnzwNIX+nyC90keXU0vHY6YYeu3nUB4sSFN2wIsFdZK9zVroODTIf1f/NZgmDSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:58:57.548161Z"},"content_sha256":"12ca8dcb2a6f7d441dda369777803504f93f5b52b30121a20ac30a318ed9303e","schema_version":"1.0","event_id":"sha256:12ca8dcb2a6f7d441dda369777803504f93f5b52b30121a20ac30a318ed9303e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ONZNUBPN2KBNEUEI3F6PTVUCFG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Avi Caciularu, Ido Dagan, Jacob Goldberger, Matthew E. Peters","submitted_at":"2023-05-24T17:48:40Z","abstract_excerpt":"The integration of multi-document pre-training objectives into language models has resulted in remarkable improvements in multi-document downstream tasks. In this work, we propose extending this idea by pre-training a generic multi-document model from a novel cross-document question answering pre-training objective. To that end, given a set (or cluster) of topically-related documents, we systematically generate semantically-oriented questions from a salient sentence in one document and challenge the model, during pre-training, to answer these questions while \"peeking\" into other topically-rela"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15387","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/2305.15387/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":"2026-07-05T06:13:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aOiA32RgtSBqbklA/oj0qwmxIR+6O+cptonc4Tn3LyErKnrU8uzKoPcVZWNxbctP1CvKQ8rBuu7YLY9BD+BqDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:58:57.548656Z"},"content_sha256":"5963e5caae9e25dea74b5086d142d0655f97f89d05482b8b56b1f8544ab11a32","schema_version":"1.0","event_id":"sha256:5963e5caae9e25dea74b5086d142d0655f97f89d05482b8b56b1f8544ab11a32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ONZNUBPN2KBNEUEI3F6PTVUCFG/bundle.json","state_url":"https://pith.science/pith/ONZNUBPN2KBNEUEI3F6PTVUCFG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ONZNUBPN2KBNEUEI3F6PTVUCFG/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":"2026-08-06T09:58:57Z","links":{"resolver":"https://pith.science/pith/ONZNUBPN2KBNEUEI3F6PTVUCFG","bundle":"https://pith.science/pith/ONZNUBPN2KBNEUEI3F6PTVUCFG/bundle.json","state":"https://pith.science/pith/ONZNUBPN2KBNEUEI3F6PTVUCFG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ONZNUBPN2KBNEUEI3F6PTVUCFG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ONZNUBPN2KBNEUEI3F6PTVUCFG","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":"976f24641bd98fb851b7ed70fc1de3da078db5f2cd0c9ae305f1c6c0130a80b3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:48:40Z","title_canon_sha256":"9e59a86663cce4853081b921fa54d25990cc74b56f7a246dbd51942b9b8fcafc"},"schema_version":"1.0","source":{"id":"2305.15387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15387","created_at":"2026-07-05T06:13:34Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15387v1","created_at":"2026-07-05T06:13:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15387","created_at":"2026-07-05T06:13:34Z"},{"alias_kind":"pith_short_12","alias_value":"ONZNUBPN2KBN","created_at":"2026-07-05T06:13:34Z"},{"alias_kind":"pith_short_16","alias_value":"ONZNUBPN2KBNEUEI","created_at":"2026-07-05T06:13:34Z"},{"alias_kind":"pith_short_8","alias_value":"ONZNUBPN","created_at":"2026-07-05T06:13:34Z"}],"graph_snapshots":[{"event_id":"sha256:5963e5caae9e25dea74b5086d142d0655f97f89d05482b8b56b1f8544ab11a32","target":"graph","created_at":"2026-07-05T06:13:34Z","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/2305.15387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The integration of multi-document pre-training objectives into language models has resulted in remarkable improvements in multi-document downstream tasks. In this work, we propose extending this idea by pre-training a generic multi-document model from a novel cross-document question answering pre-training objective. To that end, given a set (or cluster) of topically-related documents, we systematically generate semantically-oriented questions from a salient sentence in one document and challenge the model, during pre-training, to answer these questions while \"peeking\" into other topically-rela","authors_text":"Arman Cohan, Avi Caciularu, Ido Dagan, Jacob Goldberger, Matthew E. Peters","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:48:40Z","title":"Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15387","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":"sha256:12ca8dcb2a6f7d441dda369777803504f93f5b52b30121a20ac30a318ed9303e","target":"record","created_at":"2026-07-05T06:13:34Z","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":"976f24641bd98fb851b7ed70fc1de3da078db5f2cd0c9ae305f1c6c0130a80b3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:48:40Z","title_canon_sha256":"9e59a86663cce4853081b921fa54d25990cc74b56f7a246dbd51942b9b8fcafc"},"schema_version":"1.0","source":{"id":"2305.15387","kind":"arxiv","version":1}},"canonical_sha256":"7372da05edd282d25088d97cf9d68229b7af1502da0f686f983d9f367ad94858","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7372da05edd282d25088d97cf9d68229b7af1502da0f686f983d9f367ad94858","first_computed_at":"2026-07-05T06:13:34.647860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:34.647860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qSZ3THsUU8xVI0PxGuwRvG/oJVYa7Sx3bG93F2P+XAKvhwaK/Ndn+hcqoqzc1gq0C3S/sQ6EkhiJ9Gmq685sDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:34.648213Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.15387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12ca8dcb2a6f7d441dda369777803504f93f5b52b30121a20ac30a318ed9303e","sha256:5963e5caae9e25dea74b5086d142d0655f97f89d05482b8b56b1f8544ab11a32"],"state_sha256":"fec5ed4bee8c0ef66374042a506fe427bcadb64b6289703c180f94712bbfc6b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Asg+qhL9i1vxH00nT4C+Bkingdg+94N3+fhoTURSyQeyUtuiaMJwAWmaHXsakohPHpRiLRVadiU8BE6BnUEWCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:58:57.552560Z","bundle_sha256":"c54bf301703422ca01f317e6d9fbf729cd1dc0015e6497bb4b258264ad5cadaf"}}