{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:P3BLKF4T6MHV6L2E3BFNUIKQAL","short_pith_number":"pith:P3BLKF4T","canonical_record":{"source":{"id":"2510.03595","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-04T00:52:48Z","cross_cats_sorted":[],"title_canon_sha256":"9c30d226c56b909e62c48be740c5e444ef733601e8bd24f63e51273d5e573470","abstract_canon_sha256":"c945f17915a08516972b50f2f8a993a0e5411c506b279a31ec1137a786c86560"},"schema_version":"1.0"},"canonical_sha256":"7ec2b51793f30f5f2f44d84ada215002dd72594524a282114fddacbba08844b1","source":{"kind":"arxiv","id":"2510.03595","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.03595","created_at":"2026-07-13T01:17:47Z"},{"alias_kind":"arxiv_version","alias_value":"2510.03595v2","created_at":"2026-07-13T01:17:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.03595","created_at":"2026-07-13T01:17:47Z"},{"alias_kind":"pith_short_12","alias_value":"P3BLKF4T6MHV","created_at":"2026-07-13T01:17:47Z"},{"alias_kind":"pith_short_16","alias_value":"P3BLKF4T6MHV6L2E","created_at":"2026-07-13T01:17:47Z"},{"alias_kind":"pith_short_8","alias_value":"P3BLKF4T","created_at":"2026-07-13T01:17:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:P3BLKF4T6MHV6L2E3BFNUIKQAL","target":"record","payload":{"canonical_record":{"source":{"id":"2510.03595","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-04T00:52:48Z","cross_cats_sorted":[],"title_canon_sha256":"9c30d226c56b909e62c48be740c5e444ef733601e8bd24f63e51273d5e573470","abstract_canon_sha256":"c945f17915a08516972b50f2f8a993a0e5411c506b279a31ec1137a786c86560"},"schema_version":"1.0"},"canonical_sha256":"7ec2b51793f30f5f2f44d84ada215002dd72594524a282114fddacbba08844b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:17:47.849361Z","signature_b64":"CA243Pbuvcp3zucnxJh/vd0BaaU8gbXt5IqvOVQpTIvLy4dzdF25L5jIbT5evlN2UuNfDofi1ApKwRfykEWNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ec2b51793f30f5f2f44d84ada215002dd72594524a282114fddacbba08844b1","last_reissued_at":"2026-07-13T01:17:47.847340Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:17:47.847340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.03595","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":"2026-07-13T01:17:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w2+BZfsIeEFPBSNgFvk3idfdaEok6KeLmyVjDK0XOFRhMLAL3QP5oHRvtVr141r7Kaa14F4ZU0hyNr+T4RsfBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:14:47.608650Z"},"content_sha256":"f385583ba5454f7697fb7e0589a21f77aa355197736437220c013e58adb51ee7","schema_version":"1.0","event_id":"sha256:f385583ba5454f7697fb7e0589a21f77aa355197736437220c013e58adb51ee7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:P3BLKF4T6MHV6L2E3BFNUIKQAL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decoupling Task-Solving and Output Formatting in LLM Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haikang Deng, Nanyun Peng, Po-Nien Kung","submitted_at":"2025-10-04T00:52:48Z","abstract_excerpt":"Large language models (LLMs) are increasingly adept at solving complex problems, such as mathematical reasoning and automatic evaluation. However, performance often degrades when prompts intertwine task instructions with rigid formatting requirements. This entanglement creates competing goals for the model, hindering its reasoning capabilities. To address this, we introduce Deco-G, a decoding framework that explicitly decouples format adherence from problem solving. Deco-G delegates format adherence to a separate Format Estimation Module (FEM), which performs probabilistic lookahead to estimat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.03595","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/2510.03595/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":"2026-07-13T01:17:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XJGi77/pOG9/WAw9ZZeMWEJ5HXzuzvlMSnJx3chHHWPvLu1uKDasQwyWfcoO4hkt2NqnwEKwNraPnxLWqIlQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:14:47.609571Z"},"content_sha256":"2175adf22f1b712150f2222a2700a01079fb2ccd13dc6b9cf180a0b275ad19e3","schema_version":"1.0","event_id":"sha256:2175adf22f1b712150f2222a2700a01079fb2ccd13dc6b9cf180a0b275ad19e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P3BLKF4T6MHV6L2E3BFNUIKQAL/bundle.json","state_url":"https://pith.science/pith/P3BLKF4T6MHV6L2E3BFNUIKQAL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P3BLKF4T6MHV6L2E3BFNUIKQAL/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":"2026-08-05T15:14:47Z","links":{"resolver":"https://pith.science/pith/P3BLKF4T6MHV6L2E3BFNUIKQAL","bundle":"https://pith.science/pith/P3BLKF4T6MHV6L2E3BFNUIKQAL/bundle.json","state":"https://pith.science/pith/P3BLKF4T6MHV6L2E3BFNUIKQAL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P3BLKF4T6MHV6L2E3BFNUIKQAL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P3BLKF4T6MHV6L2E3BFNUIKQAL","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":"c945f17915a08516972b50f2f8a993a0e5411c506b279a31ec1137a786c86560","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-04T00:52:48Z","title_canon_sha256":"9c30d226c56b909e62c48be740c5e444ef733601e8bd24f63e51273d5e573470"},"schema_version":"1.0","source":{"id":"2510.03595","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.03595","created_at":"2026-07-13T01:17:47Z"},{"alias_kind":"arxiv_version","alias_value":"2510.03595v2","created_at":"2026-07-13T01:17:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.03595","created_at":"2026-07-13T01:17:47Z"},{"alias_kind":"pith_short_12","alias_value":"P3BLKF4T6MHV","created_at":"2026-07-13T01:17:47Z"},{"alias_kind":"pith_short_16","alias_value":"P3BLKF4T6MHV6L2E","created_at":"2026-07-13T01:17:47Z"},{"alias_kind":"pith_short_8","alias_value":"P3BLKF4T","created_at":"2026-07-13T01:17:47Z"}],"graph_snapshots":[{"event_id":"sha256:2175adf22f1b712150f2222a2700a01079fb2ccd13dc6b9cf180a0b275ad19e3","target":"graph","created_at":"2026-07-13T01:17:47Z","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/2510.03595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly adept at solving complex problems, such as mathematical reasoning and automatic evaluation. However, performance often degrades when prompts intertwine task instructions with rigid formatting requirements. This entanglement creates competing goals for the model, hindering its reasoning capabilities. To address this, we introduce Deco-G, a decoding framework that explicitly decouples format adherence from problem solving. Deco-G delegates format adherence to a separate Format Estimation Module (FEM), which performs probabilistic lookahead to estimat","authors_text":"Haikang Deng, Nanyun Peng, Po-Nien Kung","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-04T00:52:48Z","title":"Decoupling Task-Solving and Output Formatting in LLM Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.03595","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:f385583ba5454f7697fb7e0589a21f77aa355197736437220c013e58adb51ee7","target":"record","created_at":"2026-07-13T01:17:47Z","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":"c945f17915a08516972b50f2f8a993a0e5411c506b279a31ec1137a786c86560","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-04T00:52:48Z","title_canon_sha256":"9c30d226c56b909e62c48be740c5e444ef733601e8bd24f63e51273d5e573470"},"schema_version":"1.0","source":{"id":"2510.03595","kind":"arxiv","version":2}},"canonical_sha256":"7ec2b51793f30f5f2f44d84ada215002dd72594524a282114fddacbba08844b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ec2b51793f30f5f2f44d84ada215002dd72594524a282114fddacbba08844b1","first_computed_at":"2026-07-13T01:17:47.847340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T01:17:47.847340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CA243Pbuvcp3zucnxJh/vd0BaaU8gbXt5IqvOVQpTIvLy4dzdF25L5jIbT5evlN2UuNfDofi1ApKwRfykEWNCA==","signature_status":"signed_v1","signed_at":"2026-07-13T01:17:47.849361Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.03595","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f385583ba5454f7697fb7e0589a21f77aa355197736437220c013e58adb51ee7","sha256:2175adf22f1b712150f2222a2700a01079fb2ccd13dc6b9cf180a0b275ad19e3"],"state_sha256":"04ffe27d182989ba7bdd69b6e373e33d0fb747e4df8f346bbca9a9a234c43038"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1QcMcoE5lg2EBOXBjVngkjlEF3/FWtjdQCmQZdiAl74Bj7AcQBFeBdI1m5jHvE4+YHhTHUnPGYeB5kWgFtOjAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:14:47.615005Z","bundle_sha256":"30d5140825c1a8fa956c27fad56b9e324bef46831865466f00954e781c0e8421"}}