{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FSXNB7NY6S35RR5BHTVNB4IMFQ","short_pith_number":"pith:FSXNB7NY","canonical_record":{"source":{"id":"2405.17402","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T17:51:24Z","cross_cats_sorted":[],"title_canon_sha256":"351e750453636b501a0b57feba9dfdc254b3ec810f1fe5c7eb8621c9a1b3b518","abstract_canon_sha256":"4c95684a7b3ad4de6f27e642ae957a4f5913f6df1ac204fa23d21bae7de79d52"},"schema_version":"1.0"},"canonical_sha256":"2caed0fdb8f4b7d8c7a13cead0f10c2c01b9176edac300cb490f9573f47f1bf3","source":{"kind":"arxiv","id":"2405.17402","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17402","created_at":"2026-07-05T11:47:11Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17402v2","created_at":"2026-07-05T11:47:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17402","created_at":"2026-07-05T11:47:11Z"},{"alias_kind":"pith_short_12","alias_value":"FSXNB7NY6S35","created_at":"2026-07-05T11:47:11Z"},{"alias_kind":"pith_short_16","alias_value":"FSXNB7NY6S35RR5B","created_at":"2026-07-05T11:47:11Z"},{"alias_kind":"pith_short_8","alias_value":"FSXNB7NY","created_at":"2026-07-05T11:47:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FSXNB7NY6S35RR5BHTVNB4IMFQ","target":"record","payload":{"canonical_record":{"source":{"id":"2405.17402","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T17:51:24Z","cross_cats_sorted":[],"title_canon_sha256":"351e750453636b501a0b57feba9dfdc254b3ec810f1fe5c7eb8621c9a1b3b518","abstract_canon_sha256":"4c95684a7b3ad4de6f27e642ae957a4f5913f6df1ac204fa23d21bae7de79d52"},"schema_version":"1.0"},"canonical_sha256":"2caed0fdb8f4b7d8c7a13cead0f10c2c01b9176edac300cb490f9573f47f1bf3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:11.813304Z","signature_b64":"7mtLleHpXqBFyz6PT/tGNa1erC5hTB1hXCZtjYo3K00MouqqQG1f7tGF1w3+urLGWwRGiDZXPA6gexy2wSm7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2caed0fdb8f4b7d8c7a13cead0f10c2c01b9176edac300cb490f9573f47f1bf3","last_reissued_at":"2026-07-05T11:47:11.812801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:11.812801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.17402","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":"2026-07-05T11:47:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jqFfwCR7iQwRQHMXMQei03lJagsMDWGOviuziSOwh5jfPo6NAZKRI54LQ2JmfPk+omqygvSGcR8foqD8suooAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:10:46.145071Z"},"content_sha256":"959af12ff8d531916a952784c0bc033696b5346ac56e6afced9d18400693d8c6","schema_version":"1.0","event_id":"sha256:959af12ff8d531916a952784c0bc033696b5346ac56e6afced9d18400693d8c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FSXNB7NY6S35RR5BHTVNB4IMFQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"THREAD: Thinking Deeper with Recursive Spawning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongyin Luo, James Glass, Nathaniel Morgan, Philip Schroeder","submitted_at":"2024-05-27T17:51:24Z","abstract_excerpt":"Large language models (LLMs) have shown impressive capabilities across diverse settings, but still struggle as the length and complexity of the context increases. To address this challenge, we propose Thinking Recursively and Dynamically (ThReaD). THREAD frames model generation as a thread of execution that, based on the context, can run to completion or dynamically spawn new threads. By spawning, threads can offload work (e.g., thinking, retrieving information) to child threads, which only return tokens needed for the parent thread to do its work. In effect, this enables the model to adapt, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17402","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/2405.17402/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":"2026-07-05T11:47:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uJd2Ld8zcaOYRO2AzvV2/px75/L7V5AkbBvqYFP6vLxBCZ9XglK/lV2DBlGCKe7Y/d65yKr09ryJ20asqbjmCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:10:46.145621Z"},"content_sha256":"9d9355576c148f4e0c4a1235a2cb38eac23c366140b380ce465a6f6d2f7d10e1","schema_version":"1.0","event_id":"sha256:9d9355576c148f4e0c4a1235a2cb38eac23c366140b380ce465a6f6d2f7d10e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FSXNB7NY6S35RR5BHTVNB4IMFQ/bundle.json","state_url":"https://pith.science/pith/FSXNB7NY6S35RR5BHTVNB4IMFQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FSXNB7NY6S35RR5BHTVNB4IMFQ/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":"2026-08-17T06:10:46Z","links":{"resolver":"https://pith.science/pith/FSXNB7NY6S35RR5BHTVNB4IMFQ","bundle":"https://pith.science/pith/FSXNB7NY6S35RR5BHTVNB4IMFQ/bundle.json","state":"https://pith.science/pith/FSXNB7NY6S35RR5BHTVNB4IMFQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FSXNB7NY6S35RR5BHTVNB4IMFQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FSXNB7NY6S35RR5BHTVNB4IMFQ","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":"4c95684a7b3ad4de6f27e642ae957a4f5913f6df1ac204fa23d21bae7de79d52","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T17:51:24Z","title_canon_sha256":"351e750453636b501a0b57feba9dfdc254b3ec810f1fe5c7eb8621c9a1b3b518"},"schema_version":"1.0","source":{"id":"2405.17402","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17402","created_at":"2026-07-05T11:47:11Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17402v2","created_at":"2026-07-05T11:47:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17402","created_at":"2026-07-05T11:47:11Z"},{"alias_kind":"pith_short_12","alias_value":"FSXNB7NY6S35","created_at":"2026-07-05T11:47:11Z"},{"alias_kind":"pith_short_16","alias_value":"FSXNB7NY6S35RR5B","created_at":"2026-07-05T11:47:11Z"},{"alias_kind":"pith_short_8","alias_value":"FSXNB7NY","created_at":"2026-07-05T11:47:11Z"}],"graph_snapshots":[{"event_id":"sha256:9d9355576c148f4e0c4a1235a2cb38eac23c366140b380ce465a6f6d2f7d10e1","target":"graph","created_at":"2026-07-05T11:47:11Z","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/2405.17402/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown impressive capabilities across diverse settings, but still struggle as the length and complexity of the context increases. To address this challenge, we propose Thinking Recursively and Dynamically (ThReaD). THREAD frames model generation as a thread of execution that, based on the context, can run to completion or dynamically spawn new threads. By spawning, threads can offload work (e.g., thinking, retrieving information) to child threads, which only return tokens needed for the parent thread to do its work. In effect, this enables the model to adapt, a","authors_text":"Hongyin Luo, James Glass, Nathaniel Morgan, Philip Schroeder","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T17:51:24Z","title":"THREAD: Thinking Deeper with Recursive Spawning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17402","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":"sha256:959af12ff8d531916a952784c0bc033696b5346ac56e6afced9d18400693d8c6","target":"record","created_at":"2026-07-05T11:47:11Z","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":"4c95684a7b3ad4de6f27e642ae957a4f5913f6df1ac204fa23d21bae7de79d52","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T17:51:24Z","title_canon_sha256":"351e750453636b501a0b57feba9dfdc254b3ec810f1fe5c7eb8621c9a1b3b518"},"schema_version":"1.0","source":{"id":"2405.17402","kind":"arxiv","version":2}},"canonical_sha256":"2caed0fdb8f4b7d8c7a13cead0f10c2c01b9176edac300cb490f9573f47f1bf3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2caed0fdb8f4b7d8c7a13cead0f10c2c01b9176edac300cb490f9573f47f1bf3","first_computed_at":"2026-07-05T11:47:11.812801Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:11.812801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7mtLleHpXqBFyz6PT/tGNa1erC5hTB1hXCZtjYo3K00MouqqQG1f7tGF1w3+urLGWwRGiDZXPA6gexy2wSm7CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:11.813304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17402","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:959af12ff8d531916a952784c0bc033696b5346ac56e6afced9d18400693d8c6","sha256:9d9355576c148f4e0c4a1235a2cb38eac23c366140b380ce465a6f6d2f7d10e1"],"state_sha256":"7e00c4e2d6f0fa5a6f85dbde2ec2f09c20e5753e27758e7200178a4814ea76c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2QwZdJZ4e97xsikBjyZAKx8HBgY4ivPuFpacI0fYLj49o31UjJR1m/2hiSOhouKmDvWtn0Y1UbkeYZtUpLE2CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T06:10:46.149498Z","bundle_sha256":"a562bb159460a2b94c510c4b513f68875ddf3288900ae539c89c0760d7a36645"}}