{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QMZQ7JO65NSKD43PWHV2SATIJJ","short_pith_number":"pith:QMZQ7JO6","canonical_record":{"source":{"id":"2506.11274","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T20:28:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dbc1164693ad61a4e369d94b91902fa86475815f06cd4e5d864550001845016d","abstract_canon_sha256":"8e1f3235ff71e4f21336e7c775834a0d6963edfb0f8f226886ab05de284a0070"},"schema_version":"1.0"},"canonical_sha256":"83330fa5deeb64a1f36fb1eba902684a48bb2f850d3cbda4686dc1c17f5d5e9c","source":{"kind":"arxiv","id":"2506.11274","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11274","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11274v2","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11274","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"pith_short_12","alias_value":"QMZQ7JO65NSK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QMZQ7JO65NSKD43P","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QMZQ7JO6","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QMZQ7JO65NSKD43PWHV2SATIJJ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.11274","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T20:28:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dbc1164693ad61a4e369d94b91902fa86475815f06cd4e5d864550001845016d","abstract_canon_sha256":"8e1f3235ff71e4f21336e7c775834a0d6963edfb0f8f226886ab05de284a0070"},"schema_version":"1.0"},"canonical_sha256":"83330fa5deeb64a1f36fb1eba902684a48bb2f850d3cbda4686dc1c17f5d5e9c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:12.579242Z","signature_b64":"D8gPjtnZSM3cvgcsJnhS7TrIOqUSWJGGkXqijC4w3L+fO2MB1h2phTkISRudOwviXQk85gQE0XYXk8STmcn/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83330fa5deeb64a1f36fb1eba902684a48bb2f850d3cbda4686dc1c17f5d5e9c","last_reissued_at":"2026-05-18T03:10:12.578778Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:12.578778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.11274","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":"2026-05-18T03:10:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F9dFknmhY0XpFjZB9AzSusKyx6g0M9Z7KKa3UM5QcnqC9Rk+gdfj5Rnc8iI8CNecE0f7ekdCYiO/q34QauWvCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T22:23:22.405827Z"},"content_sha256":"3908d78a8011d9d08dd1f3c5182f19cb0e92f61a246a49794c20c62138c019a5","schema_version":"1.0","event_id":"sha256:3908d78a8011d9d08dd1f3c5182f19cb0e92f61a246a49794c20c62138c019a5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QMZQ7JO65NSKD43PWHV2SATIJJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning a Continue-Thinking Token for Enhanced Test-Time Scaling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Elad Tolochinsky, Liran Ringel, Yaniv Romano","submitted_at":"2025-06-12T20:28:54Z","abstract_excerpt":"Test-time scaling has emerged as an effective approach for improving language model performance by utilizing additional compute at inference time. Recent studies have shown that overriding end-of-thinking tokens (e.g., replacing \"</think>\" with \"Wait\") can extend reasoning steps and improve accuracy. In this work, we explore whether a dedicated continue-thinking token can be learned to trigger extended reasoning. We augment a distilled version of DeepSeek-R1 with a single learned \"<|continue-thinking|>\" token, training only its embedding via reinforcement learning while keeping the model weigh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11274","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":""},"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":"2026-05-18T03:10:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KHSCNF0qG8SWKJQppopC/uoFx7kYlG2M2wAPKPXaRjcEp7jwt0nKbwev1YNe7AAzWgiLJh3HEKGKeNS3eqsECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T22:23:22.406174Z"},"content_sha256":"b7e462cd2e363c62cd258d7cd6a25e77afce3455c2d76e62fdca650db2f1ff45","schema_version":"1.0","event_id":"sha256:b7e462cd2e363c62cd258d7cd6a25e77afce3455c2d76e62fdca650db2f1ff45"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QMZQ7JO65NSKD43PWHV2SATIJJ/bundle.json","state_url":"https://pith.science/pith/QMZQ7JO65NSKD43PWHV2SATIJJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QMZQ7JO65NSKD43PWHV2SATIJJ/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":"2026-05-21T22:23:22Z","links":{"resolver":"https://pith.science/pith/QMZQ7JO65NSKD43PWHV2SATIJJ","bundle":"https://pith.science/pith/QMZQ7JO65NSKD43PWHV2SATIJJ/bundle.json","state":"https://pith.science/pith/QMZQ7JO65NSKD43PWHV2SATIJJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QMZQ7JO65NSKD43PWHV2SATIJJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QMZQ7JO65NSKD43PWHV2SATIJJ","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":"8e1f3235ff71e4f21336e7c775834a0d6963edfb0f8f226886ab05de284a0070","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T20:28:54Z","title_canon_sha256":"dbc1164693ad61a4e369d94b91902fa86475815f06cd4e5d864550001845016d"},"schema_version":"1.0","source":{"id":"2506.11274","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.11274","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.11274v2","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11274","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"pith_short_12","alias_value":"QMZQ7JO65NSK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QMZQ7JO65NSKD43P","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QMZQ7JO6","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:b7e462cd2e363c62cd258d7cd6a25e77afce3455c2d76e62fdca650db2f1ff45","target":"graph","created_at":"2026-05-18T03:10:12Z","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"},"paper":{"abstract_excerpt":"Test-time scaling has emerged as an effective approach for improving language model performance by utilizing additional compute at inference time. Recent studies have shown that overriding end-of-thinking tokens (e.g., replacing \"</think>\" with \"Wait\") can extend reasoning steps and improve accuracy. In this work, we explore whether a dedicated continue-thinking token can be learned to trigger extended reasoning. We augment a distilled version of DeepSeek-R1 with a single learned \"<|continue-thinking|>\" token, training only its embedding via reinforcement learning while keeping the model weigh","authors_text":"Elad Tolochinsky, Liran Ringel, Yaniv Romano","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T20:28:54Z","title":"Learning a Continue-Thinking Token for Enhanced Test-Time Scaling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11274","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":"sha256:3908d78a8011d9d08dd1f3c5182f19cb0e92f61a246a49794c20c62138c019a5","target":"record","created_at":"2026-05-18T03:10:12Z","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":"8e1f3235ff71e4f21336e7c775834a0d6963edfb0f8f226886ab05de284a0070","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T20:28:54Z","title_canon_sha256":"dbc1164693ad61a4e369d94b91902fa86475815f06cd4e5d864550001845016d"},"schema_version":"1.0","source":{"id":"2506.11274","kind":"arxiv","version":2}},"canonical_sha256":"83330fa5deeb64a1f36fb1eba902684a48bb2f850d3cbda4686dc1c17f5d5e9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83330fa5deeb64a1f36fb1eba902684a48bb2f850d3cbda4686dc1c17f5d5e9c","first_computed_at":"2026-05-18T03:10:12.578778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:10:12.578778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D8gPjtnZSM3cvgcsJnhS7TrIOqUSWJGGkXqijC4w3L+fO2MB1h2phTkISRudOwviXQk85gQE0XYXk8STmcn/Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:10:12.579242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.11274","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3908d78a8011d9d08dd1f3c5182f19cb0e92f61a246a49794c20c62138c019a5","sha256:b7e462cd2e363c62cd258d7cd6a25e77afce3455c2d76e62fdca650db2f1ff45"],"state_sha256":"13b5ba692e7d8a0dafe39aa807237795756ee8dfdacefd4a0d7ba50e3d1f49d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DE1hEpLFaImp2JVXDaV0Hy+esQY2B6AssiaATZiC83Qlwd4QjLUzCw5bwbiQj1kRm28w5i9kUJKfyh8+unGxCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T22:23:22.408447Z","bundle_sha256":"c938f3a01d34665f775e348e058a1b9b6ef32a4261b8bf6dc4e99e2013e2d3ab"}}