{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7YPZSVJ7N73F63HDW72DXQ5ZBG","short_pith_number":"pith:7YPZSVJ7","canonical_record":{"source":{"id":"2403.01061","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-02T01:52:14Z","cross_cats_sorted":[],"title_canon_sha256":"f5544f81c1f5456b47d1bb57c3c46a32421c3ee3f4573155300825de871da6a2","abstract_canon_sha256":"c5948d9fdaef4533abd98f45c82bf808d1c6a960b699e258ca96d041b836f9c6"},"schema_version":"1.0"},"canonical_sha256":"fe1f99553f6ff65f6ce3b7f43bc3b909a243a498f08b7618f86243fbcde81224","source":{"kind":"arxiv","id":"2403.01061","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01061","created_at":"2026-07-05T08:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01061v3","created_at":"2026-07-05T08:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01061","created_at":"2026-07-05T08:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"7YPZSVJ7N73F","created_at":"2026-07-05T08:42:53Z"},{"alias_kind":"pith_short_16","alias_value":"7YPZSVJ7N73F63HD","created_at":"2026-07-05T08:42:53Z"},{"alias_kind":"pith_short_8","alias_value":"7YPZSVJ7","created_at":"2026-07-05T08:42:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7YPZSVJ7N73F63HDW72DXQ5ZBG","target":"record","payload":{"canonical_record":{"source":{"id":"2403.01061","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-02T01:52:14Z","cross_cats_sorted":[],"title_canon_sha256":"f5544f81c1f5456b47d1bb57c3c46a32421c3ee3f4573155300825de871da6a2","abstract_canon_sha256":"c5948d9fdaef4533abd98f45c82bf808d1c6a960b699e258ca96d041b836f9c6"},"schema_version":"1.0"},"canonical_sha256":"fe1f99553f6ff65f6ce3b7f43bc3b909a243a498f08b7618f86243fbcde81224","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:53.722601Z","signature_b64":"6ypI5m5PLSqSZXOWURSIAa4ES4EnEvZaPvu3wNSQK5rA5SF4S0vkfifiyEQ3SpCCcb+t5INFAqgJJwV4U2dsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe1f99553f6ff65f6ce3b7f43bc3b909a243a498f08b7618f86243fbcde81224","last_reissued_at":"2026-07-05T08:42:53.722160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:53.722160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.01061","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:42:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O6oChVOwRm5LGnq9Lpz8JoRfT3UPgeA34d8opx2e7lEPVOfjaucDpQPyJJBfPUCML8qVAMLubuLGMt5AoJmgDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:08:08.716047Z"},"content_sha256":"0d2276ba0c4d3a632b00a15fb98d1ac7fa1f91b8c9b1f0091b5e2792d3e23921","schema_version":"1.0","event_id":"sha256:0d2276ba0c4d3a632b00a15fb98d1ac7fa1f91b8c9b1f0091b5e2792d3e23921"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7YPZSVJ7N73F63HDW72DXQ5ZBG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reading Subtext: Evaluating Large Language Models on Short Story Summarization with Writers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kathleen McKeown, Lydia B. Chilton, Melanie Subbiah, Sean Zhang","submitted_at":"2024-03-02T01:52:14Z","abstract_excerpt":"We evaluate recent Large Language Models (LLMs) on the challenging task of summarizing short stories, which can be lengthy, and include nuanced subtext or scrambled timelines. Importantly, we work directly with authors to ensure that the stories have not been shared online (and therefore are unseen by the models), and to obtain informed evaluations of summary quality using judgments from the authors themselves. Through quantitative and qualitative analysis grounded in narrative theory, we compare GPT-4, Claude-2.1, and LLama-2-70B. We find that all three models make faithfulness mistakes in ov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01061","kind":"arxiv","version":3},"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/2403.01061/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":"2026-07-05T08:42:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o/v3WWGc8/JzF60dsbHEhCRn4k1Y1K80vaKi0sM7d3aYy5SUxuusDrmve7S44k63qtrZH/YzIpr+skB/eg3TCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:08:08.716565Z"},"content_sha256":"5486af99ded4ebb5776549f6684b0981a6eb8844e6969ee6b296f5b7aadf65c7","schema_version":"1.0","event_id":"sha256:5486af99ded4ebb5776549f6684b0981a6eb8844e6969ee6b296f5b7aadf65c7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7YPZSVJ7N73F63HDW72DXQ5ZBG/bundle.json","state_url":"https://pith.science/pith/7YPZSVJ7N73F63HDW72DXQ5ZBG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7YPZSVJ7N73F63HDW72DXQ5ZBG/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":"2026-08-12T13:08:08Z","links":{"resolver":"https://pith.science/pith/7YPZSVJ7N73F63HDW72DXQ5ZBG","bundle":"https://pith.science/pith/7YPZSVJ7N73F63HDW72DXQ5ZBG/bundle.json","state":"https://pith.science/pith/7YPZSVJ7N73F63HDW72DXQ5ZBG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7YPZSVJ7N73F63HDW72DXQ5ZBG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7YPZSVJ7N73F63HDW72DXQ5ZBG","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":"c5948d9fdaef4533abd98f45c82bf808d1c6a960b699e258ca96d041b836f9c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-02T01:52:14Z","title_canon_sha256":"f5544f81c1f5456b47d1bb57c3c46a32421c3ee3f4573155300825de871da6a2"},"schema_version":"1.0","source":{"id":"2403.01061","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01061","created_at":"2026-07-05T08:42:53Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01061v3","created_at":"2026-07-05T08:42:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01061","created_at":"2026-07-05T08:42:53Z"},{"alias_kind":"pith_short_12","alias_value":"7YPZSVJ7N73F","created_at":"2026-07-05T08:42:53Z"},{"alias_kind":"pith_short_16","alias_value":"7YPZSVJ7N73F63HD","created_at":"2026-07-05T08:42:53Z"},{"alias_kind":"pith_short_8","alias_value":"7YPZSVJ7","created_at":"2026-07-05T08:42:53Z"}],"graph_snapshots":[{"event_id":"sha256:5486af99ded4ebb5776549f6684b0981a6eb8844e6969ee6b296f5b7aadf65c7","target":"graph","created_at":"2026-07-05T08:42:53Z","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/2403.01061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We evaluate recent Large Language Models (LLMs) on the challenging task of summarizing short stories, which can be lengthy, and include nuanced subtext or scrambled timelines. Importantly, we work directly with authors to ensure that the stories have not been shared online (and therefore are unseen by the models), and to obtain informed evaluations of summary quality using judgments from the authors themselves. Through quantitative and qualitative analysis grounded in narrative theory, we compare GPT-4, Claude-2.1, and LLama-2-70B. We find that all three models make faithfulness mistakes in ov","authors_text":"Kathleen McKeown, Lydia B. Chilton, Melanie Subbiah, Sean Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-02T01:52:14Z","title":"Reading Subtext: Evaluating Large Language Models on Short Story Summarization with Writers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01061","kind":"arxiv","version":3},"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":"sha256:0d2276ba0c4d3a632b00a15fb98d1ac7fa1f91b8c9b1f0091b5e2792d3e23921","target":"record","created_at":"2026-07-05T08:42:53Z","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":"c5948d9fdaef4533abd98f45c82bf808d1c6a960b699e258ca96d041b836f9c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-02T01:52:14Z","title_canon_sha256":"f5544f81c1f5456b47d1bb57c3c46a32421c3ee3f4573155300825de871da6a2"},"schema_version":"1.0","source":{"id":"2403.01061","kind":"arxiv","version":3}},"canonical_sha256":"fe1f99553f6ff65f6ce3b7f43bc3b909a243a498f08b7618f86243fbcde81224","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe1f99553f6ff65f6ce3b7f43bc3b909a243a498f08b7618f86243fbcde81224","first_computed_at":"2026-07-05T08:42:53.722160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:53.722160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6ypI5m5PLSqSZXOWURSIAa4ES4EnEvZaPvu3wNSQK5rA5SF4S0vkfifiyEQ3SpCCcb+t5INFAqgJJwV4U2dsDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:53.722601Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.01061","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d2276ba0c4d3a632b00a15fb98d1ac7fa1f91b8c9b1f0091b5e2792d3e23921","sha256:5486af99ded4ebb5776549f6684b0981a6eb8844e6969ee6b296f5b7aadf65c7"],"state_sha256":"38a0389e895e78d050de309cc7d4afcb873d8717e9d8b54fa89a11c97cebec8c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pmFUNFsFJg/IlVs4JrYdWG01p6b1uYqIhT2CXDkwF+fE6cL7L2VXWrhmrZSf3BtUJYNuFhZ7qkY/8Vqg8lERBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T13:08:08.720607Z","bundle_sha256":"fd21ff35eef3095c881f3ba69de36ad38eabfdf0a9c805a3ccfc3400eaad939b"}}