{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GTM6CRTZ3SU6IVBETG5VWBJROE","short_pith_number":"pith:GTM6CRTZ","canonical_record":{"source":{"id":"2512.02240","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-01T22:07:32Z","cross_cats_sorted":[],"title_canon_sha256":"b302fc01ae4177b051b17a94953393e4ddd0ee8b52b0bb7f830fb027da26aaa2","abstract_canon_sha256":"832c36d0600e4f3c0e0d2519b173f1c390a8afd066d72f1eec1ae633e28e0849"},"schema_version":"1.0"},"canonical_sha256":"34d9e14679dca9e4542499bb5b0531713d29693d6ca7ce893e3e8391bf6c9b85","source":{"kind":"arxiv","id":"2512.02240","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.02240","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"arxiv_version","alias_value":"2512.02240v2","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.02240","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"pith_short_12","alias_value":"GTM6CRTZ3SU6","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"pith_short_16","alias_value":"GTM6CRTZ3SU6IVBE","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"pith_short_8","alias_value":"GTM6CRTZ","created_at":"2026-06-10T01:09:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GTM6CRTZ3SU6IVBETG5VWBJROE","target":"record","payload":{"canonical_record":{"source":{"id":"2512.02240","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-01T22:07:32Z","cross_cats_sorted":[],"title_canon_sha256":"b302fc01ae4177b051b17a94953393e4ddd0ee8b52b0bb7f830fb027da26aaa2","abstract_canon_sha256":"832c36d0600e4f3c0e0d2519b173f1c390a8afd066d72f1eec1ae633e28e0849"},"schema_version":"1.0"},"canonical_sha256":"34d9e14679dca9e4542499bb5b0531713d29693d6ca7ce893e3e8391bf6c9b85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:09:48.267096Z","signature_b64":"GJrzGwHZLvPacqwZ65eJKJE5hCtw5IApsoLLuGtLHy2eBsUhH/We3CQmZAhBMkQtTiZQKRIRFJT4PzBxZ6EzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34d9e14679dca9e4542499bb5b0531713d29693d6ca7ce893e3e8391bf6c9b85","last_reissued_at":"2026-06-10T01:09:48.266242Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:09:48.266242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.02240","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":"2026-06-10T01:09:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/DkIjUlq83noUBYbw7GyztB3vn45i5ohlsDsMTOjVdvGxzGThdakV9tzie/Y7RUlFmG/AmBhc2PXVSJQwuwHCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T22:26:51.304543Z"},"content_sha256":"9394fa712a17e10d280aff54d8e287494ce2785ce5937319df03d0e875ef3862","schema_version":"1.0","event_id":"sha256:9394fa712a17e10d280aff54d8e287494ce2785ce5937319df03d0e875ef3862"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GTM6CRTZ3SU6IVBETG5VWBJROE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lightweight Latent Reasoning for Narrative Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Gurung, Esmeralda S. Whitammer, Mirella Lapata","submitted_at":"2025-12-01T22:07:32Z","abstract_excerpt":"Large language models (LLMs) tackle complex tasks by generating long chains of thought or \"reasoning traces\" that act as latent variables in the generation of an output given a query. A model's ability to generate such traces can be optimized with reinforcement learning (RL) to improve their utility in predicting an answer. This optimization comes at a high computational cost, especially for narrative-related tasks that involve retrieving and processing many tokens. To this end, we propose LiteReason, a latent reasoning method that can be interleaved with standard token sampling and easily com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.02240","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/2512.02240/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":"2026-06-10T01:09:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BDXTdu3xqapbrJnHlaSefDh2NIae9r0QMXMPjvigED/UoCFVxH7yqxpEk3Wf59etr7PFqZeE1Jn13DhLXVbEDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T22:26:51.304916Z"},"content_sha256":"fbde8541f4205f383ae8b4b07bf6891ac8386fe12fe6539976d36049d6c5c7a5","schema_version":"1.0","event_id":"sha256:fbde8541f4205f383ae8b4b07bf6891ac8386fe12fe6539976d36049d6c5c7a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GTM6CRTZ3SU6IVBETG5VWBJROE/bundle.json","state_url":"https://pith.science/pith/GTM6CRTZ3SU6IVBETG5VWBJROE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GTM6CRTZ3SU6IVBETG5VWBJROE/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":"2026-07-01T22:26:51Z","links":{"resolver":"https://pith.science/pith/GTM6CRTZ3SU6IVBETG5VWBJROE","bundle":"https://pith.science/pith/GTM6CRTZ3SU6IVBETG5VWBJROE/bundle.json","state":"https://pith.science/pith/GTM6CRTZ3SU6IVBETG5VWBJROE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GTM6CRTZ3SU6IVBETG5VWBJROE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GTM6CRTZ3SU6IVBETG5VWBJROE","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":"832c36d0600e4f3c0e0d2519b173f1c390a8afd066d72f1eec1ae633e28e0849","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-01T22:07:32Z","title_canon_sha256":"b302fc01ae4177b051b17a94953393e4ddd0ee8b52b0bb7f830fb027da26aaa2"},"schema_version":"1.0","source":{"id":"2512.02240","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.02240","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"arxiv_version","alias_value":"2512.02240v2","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.02240","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"pith_short_12","alias_value":"GTM6CRTZ3SU6","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"pith_short_16","alias_value":"GTM6CRTZ3SU6IVBE","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"pith_short_8","alias_value":"GTM6CRTZ","created_at":"2026-06-10T01:09:48Z"}],"graph_snapshots":[{"event_id":"sha256:fbde8541f4205f383ae8b4b07bf6891ac8386fe12fe6539976d36049d6c5c7a5","target":"graph","created_at":"2026-06-10T01:09:48Z","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/2512.02240/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) tackle complex tasks by generating long chains of thought or \"reasoning traces\" that act as latent variables in the generation of an output given a query. A model's ability to generate such traces can be optimized with reinforcement learning (RL) to improve their utility in predicting an answer. This optimization comes at a high computational cost, especially for narrative-related tasks that involve retrieving and processing many tokens. To this end, we propose LiteReason, a latent reasoning method that can be interleaved with standard token sampling and easily com","authors_text":"Alexander Gurung, Esmeralda S. Whitammer, Mirella Lapata","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-01T22:07:32Z","title":"Lightweight Latent Reasoning for Narrative Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.02240","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":"sha256:9394fa712a17e10d280aff54d8e287494ce2785ce5937319df03d0e875ef3862","target":"record","created_at":"2026-06-10T01:09:48Z","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":"832c36d0600e4f3c0e0d2519b173f1c390a8afd066d72f1eec1ae633e28e0849","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-01T22:07:32Z","title_canon_sha256":"b302fc01ae4177b051b17a94953393e4ddd0ee8b52b0bb7f830fb027da26aaa2"},"schema_version":"1.0","source":{"id":"2512.02240","kind":"arxiv","version":2}},"canonical_sha256":"34d9e14679dca9e4542499bb5b0531713d29693d6ca7ce893e3e8391bf6c9b85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34d9e14679dca9e4542499bb5b0531713d29693d6ca7ce893e3e8391bf6c9b85","first_computed_at":"2026-06-10T01:09:48.266242Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:09:48.266242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GJrzGwHZLvPacqwZ65eJKJE5hCtw5IApsoLLuGtLHy2eBsUhH/We3CQmZAhBMkQtTiZQKRIRFJT4PzBxZ6EzBg==","signature_status":"signed_v1","signed_at":"2026-06-10T01:09:48.267096Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.02240","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9394fa712a17e10d280aff54d8e287494ce2785ce5937319df03d0e875ef3862","sha256:fbde8541f4205f383ae8b4b07bf6891ac8386fe12fe6539976d36049d6c5c7a5"],"state_sha256":"6e36d0d3071d7609bf9f30b20035c0c4efbc27084111dc1ed88906245171888b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ys2wQjPlrckd2bMFNvX7NV1c3tw9zO0R5gKbLVmbSAcVM9rpDQfMmytD8qDI5g9jwDctbPBOemEwChnd+5R5DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T22:26:51.307072Z","bundle_sha256":"ca38956fcaade8ca666c917bfa5e7c16e282f417dfa16e0f6d8cfdda094c6899"}}