{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DXXU2YCBJV3YF4CKFMUARV5KIT","short_pith_number":"pith:DXXU2YCB","canonical_record":{"source":{"id":"2504.04718","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T04:01:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b247e6be5ae6f0ddbed0bac473e803bd26e2e51b054cbddb91da941a0d7c7e28","abstract_canon_sha256":"98c57b69a8e7c20b9aebdcd7f8c1d71189b8892329ce2fc60b96fea1e72c368e"},"schema_version":"1.0"},"canonical_sha256":"1def4d60414d7782f04a2b2808d7aa44eafb9c9828c6ad8dd3c4130a62dee6c8","source":{"kind":"arxiv","id":"2504.04718","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04718","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04718v2","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04718","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"pith_short_12","alias_value":"DXXU2YCBJV3Y","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"pith_short_16","alias_value":"DXXU2YCBJV3YF4CK","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"pith_short_8","alias_value":"DXXU2YCB","created_at":"2026-06-02T02:04:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DXXU2YCBJV3YF4CKFMUARV5KIT","target":"record","payload":{"canonical_record":{"source":{"id":"2504.04718","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T04:01:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b247e6be5ae6f0ddbed0bac473e803bd26e2e51b054cbddb91da941a0d7c7e28","abstract_canon_sha256":"98c57b69a8e7c20b9aebdcd7f8c1d71189b8892329ce2fc60b96fea1e72c368e"},"schema_version":"1.0"},"canonical_sha256":"1def4d60414d7782f04a2b2808d7aa44eafb9c9828c6ad8dd3c4130a62dee6c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:46.615231Z","signature_b64":"gnp2+gPsFBDI/PBK6Prtd+NqQia3b3C3OkRQDoJULFzXZ7FNh10T90mxYiF1yJfmJ5GvX2E+IS/6BRuQijI9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1def4d60414d7782f04a2b2808d7aa44eafb9c9828c6ad8dd3c4130a62dee6c8","last_reissued_at":"2026-06-02T02:04:46.614658Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:46.614658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.04718","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":"2026-06-02T02:04:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6wCYAMD027K6AhgQ+1SzAFcFEtm4Off7iOrpw428JjXnoWOkHlzA3pXP2CYTncNZntgp7jzKNx6J/qYXU9XGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T12:24:49.598131Z"},"content_sha256":"7a580e06172d1a7ec86081f1f9fc48466b706fc40e75d9e8c47f0b947afeb599","schema_version":"1.0","event_id":"sha256:7a580e06172d1a7ec86081f1f9fc48466b706fc40e75d9e8c47f0b947afeb599"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DXXU2YCBJV3YF4CKFMUARV5KIT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jaewoong Cho, Jongwon Jeong, Minki Kang","submitted_at":"2025-04-07T04:01:17Z","abstract_excerpt":"Recent studies have demonstrated that test-time compute scaling effectively improves the performance of small language models (sLMs). However, prior research has mainly examined test-time compute scaling with an additional larger model as a verifier, leaving verification by sLMs underexplored. In this work, we investigate whether sLMs can reliably verify the output candidates under test-time scaling. We find that even with knowledge distillation from larger verifiers, sLMs struggle with verification tasks requiring memorization, such as numerical calculations and fact-checking. To address this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04718","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/2504.04718/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":"2026-06-02T02:04:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gdvScQ/t8UiKsSaTqAs5xJDdDTcff3u56uPrrmWs6ZmuPY1f4/wKyHkN/Ub4kqVBwngeANBHQWNbYNcYpK4jAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T12:24:49.598521Z"},"content_sha256":"a2837723c1976f38ce20748de9cfefebf329ae03854684c22fff1352ee4adfa1","schema_version":"1.0","event_id":"sha256:a2837723c1976f38ce20748de9cfefebf329ae03854684c22fff1352ee4adfa1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DXXU2YCBJV3YF4CKFMUARV5KIT/bundle.json","state_url":"https://pith.science/pith/DXXU2YCBJV3YF4CKFMUARV5KIT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DXXU2YCBJV3YF4CKFMUARV5KIT/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":"2026-06-09T12:24:49Z","links":{"resolver":"https://pith.science/pith/DXXU2YCBJV3YF4CKFMUARV5KIT","bundle":"https://pith.science/pith/DXXU2YCBJV3YF4CKFMUARV5KIT/bundle.json","state":"https://pith.science/pith/DXXU2YCBJV3YF4CKFMUARV5KIT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DXXU2YCBJV3YF4CKFMUARV5KIT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DXXU2YCBJV3YF4CKFMUARV5KIT","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":"98c57b69a8e7c20b9aebdcd7f8c1d71189b8892329ce2fc60b96fea1e72c368e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T04:01:17Z","title_canon_sha256":"b247e6be5ae6f0ddbed0bac473e803bd26e2e51b054cbddb91da941a0d7c7e28"},"schema_version":"1.0","source":{"id":"2504.04718","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04718","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04718v2","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04718","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"pith_short_12","alias_value":"DXXU2YCBJV3Y","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"pith_short_16","alias_value":"DXXU2YCBJV3YF4CK","created_at":"2026-06-02T02:04:46Z"},{"alias_kind":"pith_short_8","alias_value":"DXXU2YCB","created_at":"2026-06-02T02:04:46Z"}],"graph_snapshots":[{"event_id":"sha256:a2837723c1976f38ce20748de9cfefebf329ae03854684c22fff1352ee4adfa1","target":"graph","created_at":"2026-06-02T02:04:46Z","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/2504.04718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have demonstrated that test-time compute scaling effectively improves the performance of small language models (sLMs). However, prior research has mainly examined test-time compute scaling with an additional larger model as a verifier, leaving verification by sLMs underexplored. In this work, we investigate whether sLMs can reliably verify the output candidates under test-time scaling. We find that even with knowledge distillation from larger verifiers, sLMs struggle with verification tasks requiring memorization, such as numerical calculations and fact-checking. To address this","authors_text":"Jaewoong Cho, Jongwon Jeong, Minki Kang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T04:01:17Z","title":"T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04718","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":"sha256:7a580e06172d1a7ec86081f1f9fc48466b706fc40e75d9e8c47f0b947afeb599","target":"record","created_at":"2026-06-02T02:04:46Z","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":"98c57b69a8e7c20b9aebdcd7f8c1d71189b8892329ce2fc60b96fea1e72c368e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T04:01:17Z","title_canon_sha256":"b247e6be5ae6f0ddbed0bac473e803bd26e2e51b054cbddb91da941a0d7c7e28"},"schema_version":"1.0","source":{"id":"2504.04718","kind":"arxiv","version":2}},"canonical_sha256":"1def4d60414d7782f04a2b2808d7aa44eafb9c9828c6ad8dd3c4130a62dee6c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1def4d60414d7782f04a2b2808d7aa44eafb9c9828c6ad8dd3c4130a62dee6c8","first_computed_at":"2026-06-02T02:04:46.614658Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:46.614658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gnp2+gPsFBDI/PBK6Prtd+NqQia3b3C3OkRQDoJULFzXZ7FNh10T90mxYiF1yJfmJ5GvX2E+IS/6BRuQijI9Cg==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:46.615231Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.04718","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a580e06172d1a7ec86081f1f9fc48466b706fc40e75d9e8c47f0b947afeb599","sha256:a2837723c1976f38ce20748de9cfefebf329ae03854684c22fff1352ee4adfa1"],"state_sha256":"7ec10db46d63d151ff8a943f4dfa68376344a15f14ca02a65d30490d71e26f0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Eu9fSiBtDmSlT+YhRoZZ/JTkapMCtwMzfBZNdEk4R7Q3qVD3GgDGu8cWc/9hqC3mNi+sOiRfRqFdRSUkPvGCCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T12:24:49.600589Z","bundle_sha256":"e403e3d01160d136c89dccc81649872e3e91203d9f9cd6e7416f5240764403f9"}}