{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7GPCTATKU6KAA22HC4D2G6LJWM","short_pith_number":"pith:7GPCTATK","canonical_record":{"source":{"id":"2502.14854","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T18:58:03Z","cross_cats_sorted":[],"title_canon_sha256":"2e212aa439f70df2ea17f6854a7056d3251f9ffdeb6390bb37a40b90b7ce3ce8","abstract_canon_sha256":"b9bb28e709fd519334723fb795a846bd5ee14f22b15a629554556e146dc9bbc2"},"schema_version":"1.0"},"canonical_sha256":"f99e29826aa794006b471707a37969b31be198a126640b3db0ccf6ba02ad8fe1","source":{"kind":"arxiv","id":"2502.14854","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14854","created_at":"2026-07-05T11:48:23Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14854v2","created_at":"2026-07-05T11:48:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14854","created_at":"2026-07-05T11:48:23Z"},{"alias_kind":"pith_short_12","alias_value":"7GPCTATKU6KA","created_at":"2026-07-05T11:48:23Z"},{"alias_kind":"pith_short_16","alias_value":"7GPCTATKU6KAA22H","created_at":"2026-07-05T11:48:23Z"},{"alias_kind":"pith_short_8","alias_value":"7GPCTATK","created_at":"2026-07-05T11:48:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7GPCTATKU6KAA22HC4D2G6LJWM","target":"record","payload":{"canonical_record":{"source":{"id":"2502.14854","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T18:58:03Z","cross_cats_sorted":[],"title_canon_sha256":"2e212aa439f70df2ea17f6854a7056d3251f9ffdeb6390bb37a40b90b7ce3ce8","abstract_canon_sha256":"b9bb28e709fd519334723fb795a846bd5ee14f22b15a629554556e146dc9bbc2"},"schema_version":"1.0"},"canonical_sha256":"f99e29826aa794006b471707a37969b31be198a126640b3db0ccf6ba02ad8fe1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:23.221093Z","signature_b64":"Oz4IYdZoHLxBlFO1TKuR8S4MEvK2z9wzH1F9tWkEXjT6ZmGCnIWI08FNTx17xRLssd1pUl456wejz1cklRu3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f99e29826aa794006b471707a37969b31be198a126640b3db0ccf6ba02ad8fe1","last_reissued_at":"2026-07-05T11:48:23.220554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:23.220554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.14854","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":"2026-07-05T11:48:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DC+nZ8hED8DQXRju6oYZYfhgR/M+dxgd/kKY+1j/YPqIlooaShOqX8mu2vqSnKEPpia0jwmOk35J6nPUtlLsBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:29:01.786632Z"},"content_sha256":"e4b2721a1348bee60c401ac51e5e6da12f9ceffd5559eaefcba44bca1ccb8db5","schema_version":"1.0","event_id":"sha256:e4b2721a1348bee60c401ac51e5e6da12f9ceffd5559eaefcba44bca1ccb8db5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7GPCTATKU6KAA22HC4D2G6LJWM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLIPPER: Compression enables long-context synthetic data generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chau Minh Pham, Mohit Iyyer, Yapei Chang","submitted_at":"2025-02-20T18:58:03Z","abstract_excerpt":"LLM developers are increasingly reliant on synthetic data, but generating high-quality data for complex long-context reasoning tasks remains challenging. We introduce CLIPPER, a compression-based approach for generating synthetic data tailored to narrative claim verification - a task that requires reasoning over a book to verify a given claim. Instead of generating claims directly from the raw text of the book, which results in artifact-riddled claims, CLIPPER first compresses the book into chapter outlines and book summaries and then uses these intermediate representations to generate complex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14854","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/2502.14854/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":"2026-07-05T11:48:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8+7o1s5mg7yTiTU9NCHeLOwu7VoXdCI4mcxICr6LRNUTiuVOVZ+/i2EySWMz9jDMCh0lzTXqmlwj3jytwwvHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:29:01.787557Z"},"content_sha256":"743106beb7c21a138b4e006b58f5ec0a96506a5f94e5e941c3eb8054051a9190","schema_version":"1.0","event_id":"sha256:743106beb7c21a138b4e006b58f5ec0a96506a5f94e5e941c3eb8054051a9190"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7GPCTATKU6KAA22HC4D2G6LJWM/bundle.json","state_url":"https://pith.science/pith/7GPCTATKU6KAA22HC4D2G6LJWM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7GPCTATKU6KAA22HC4D2G6LJWM/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":"2026-08-10T20:29:01Z","links":{"resolver":"https://pith.science/pith/7GPCTATKU6KAA22HC4D2G6LJWM","bundle":"https://pith.science/pith/7GPCTATKU6KAA22HC4D2G6LJWM/bundle.json","state":"https://pith.science/pith/7GPCTATKU6KAA22HC4D2G6LJWM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7GPCTATKU6KAA22HC4D2G6LJWM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7GPCTATKU6KAA22HC4D2G6LJWM","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":"b9bb28e709fd519334723fb795a846bd5ee14f22b15a629554556e146dc9bbc2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T18:58:03Z","title_canon_sha256":"2e212aa439f70df2ea17f6854a7056d3251f9ffdeb6390bb37a40b90b7ce3ce8"},"schema_version":"1.0","source":{"id":"2502.14854","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14854","created_at":"2026-07-05T11:48:23Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14854v2","created_at":"2026-07-05T11:48:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14854","created_at":"2026-07-05T11:48:23Z"},{"alias_kind":"pith_short_12","alias_value":"7GPCTATKU6KA","created_at":"2026-07-05T11:48:23Z"},{"alias_kind":"pith_short_16","alias_value":"7GPCTATKU6KAA22H","created_at":"2026-07-05T11:48:23Z"},{"alias_kind":"pith_short_8","alias_value":"7GPCTATK","created_at":"2026-07-05T11:48:23Z"}],"graph_snapshots":[{"event_id":"sha256:743106beb7c21a138b4e006b58f5ec0a96506a5f94e5e941c3eb8054051a9190","target":"graph","created_at":"2026-07-05T11:48:23Z","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/2502.14854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM developers are increasingly reliant on synthetic data, but generating high-quality data for complex long-context reasoning tasks remains challenging. We introduce CLIPPER, a compression-based approach for generating synthetic data tailored to narrative claim verification - a task that requires reasoning over a book to verify a given claim. Instead of generating claims directly from the raw text of the book, which results in artifact-riddled claims, CLIPPER first compresses the book into chapter outlines and book summaries and then uses these intermediate representations to generate complex","authors_text":"Chau Minh Pham, Mohit Iyyer, Yapei Chang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T18:58:03Z","title":"CLIPPER: Compression enables long-context synthetic data generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14854","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:e4b2721a1348bee60c401ac51e5e6da12f9ceffd5559eaefcba44bca1ccb8db5","target":"record","created_at":"2026-07-05T11:48:23Z","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":"b9bb28e709fd519334723fb795a846bd5ee14f22b15a629554556e146dc9bbc2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T18:58:03Z","title_canon_sha256":"2e212aa439f70df2ea17f6854a7056d3251f9ffdeb6390bb37a40b90b7ce3ce8"},"schema_version":"1.0","source":{"id":"2502.14854","kind":"arxiv","version":2}},"canonical_sha256":"f99e29826aa794006b471707a37969b31be198a126640b3db0ccf6ba02ad8fe1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f99e29826aa794006b471707a37969b31be198a126640b3db0ccf6ba02ad8fe1","first_computed_at":"2026-07-05T11:48:23.220554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:23.220554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Oz4IYdZoHLxBlFO1TKuR8S4MEvK2z9wzH1F9tWkEXjT6ZmGCnIWI08FNTx17xRLssd1pUl456wejz1cklRu3Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:23.221093Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14854","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4b2721a1348bee60c401ac51e5e6da12f9ceffd5559eaefcba44bca1ccb8db5","sha256:743106beb7c21a138b4e006b58f5ec0a96506a5f94e5e941c3eb8054051a9190"],"state_sha256":"c7847cfaff8928690a36d4fbce7bf56acd7b2ed3bbab4b6f185a20d3997f9ee8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OmneJp5dv5vRwImI9nVvGIVZGQf9jQjc66DymWZtHt9XDpcCRszT2ml284OCDdML2CBV/Pt5PwwDTbPc9yH5AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T20:29:01.818433Z","bundle_sha256":"59f9a41e63406d48e5642f5c851b1015ac462058ec46af155213cf5c47923745"}}