{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GZBZ4ZYMWDHJN4IHLMJ2YTR6LD","short_pith_number":"pith:GZBZ4ZYM","canonical_record":{"source":{"id":"2507.05065","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T14:49:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"65e15fcb4a14e3c21cbec38dcaa85d7cf6cbed5a5b34bf321561ebb0f228840e","abstract_canon_sha256":"6032e4babf18b9468b5408f79e560756796d5992d0cdd8b5e9bb66351a2f412c"},"schema_version":"1.0"},"canonical_sha256":"36439e670cb0ce96f1075b13ac4e3e58de8c209adc57e6bc3b3b7313e4d67987","source":{"kind":"arxiv","id":"2507.05065","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05065","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05065v1","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05065","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_12","alias_value":"GZBZ4ZYMWDHJ","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_16","alias_value":"GZBZ4ZYMWDHJN4IH","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_8","alias_value":"GZBZ4ZYM","created_at":"2026-07-05T11:33:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GZBZ4ZYMWDHJN4IHLMJ2YTR6LD","target":"record","payload":{"canonical_record":{"source":{"id":"2507.05065","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T14:49:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"65e15fcb4a14e3c21cbec38dcaa85d7cf6cbed5a5b34bf321561ebb0f228840e","abstract_canon_sha256":"6032e4babf18b9468b5408f79e560756796d5992d0cdd8b5e9bb66351a2f412c"},"schema_version":"1.0"},"canonical_sha256":"36439e670cb0ce96f1075b13ac4e3e58de8c209adc57e6bc3b3b7313e4d67987","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:08.495464Z","signature_b64":"DYzARbZKoclPzOI82fx5zcIXMTJUTWQ8VLxdx4gVc6zOj1oqkUykGnp65qcD2E8O+ISjTj01LMPHwfu+lH0xCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36439e670cb0ce96f1075b13ac4e3e58de8c209adc57e6bc3b3b7313e4d67987","last_reissued_at":"2026-07-05T11:33:08.495072Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:08.495072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.05065","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ix2uQ/KPA40MaVal3IV540a9Vpq/ExEOp20g/0R3+UUkZ6Wrtk5aVEZFs7MxgCecSyXIHQjhyBN1GfYtSYqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T18:22:48.442327Z"},"content_sha256":"44903411e9c74c84d7deafa02c2ff3a0cbfa57c8eb51102f64c08b9b857b0692","schema_version":"1.0","event_id":"sha256:44903411e9c74c84d7deafa02c2ff3a0cbfa57c8eb51102f64c08b9b857b0692"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GZBZ4ZYMWDHJN4IHLMJ2YTR6LD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Replacing thinking with tool usage enables reasoning in small language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Corrado Rainone, Roland Memisevic, Tim Bakker","submitted_at":"2025-07-07T14:49:18Z","abstract_excerpt":"Recent advances have established a new machine learning paradigm based on scaling up compute at inference time as well as at training time. In that line of work, a combination of Supervised Fine-Tuning (SFT) on synthetic demonstrations and Reinforcement Learning with Verifiable Rewards (RLVR) is used for training Large Language Models to expend extra compute during inference in the form of \"thoughts\" expressed in natural language. In this paper, we propose to instead format these tokens as a multi-turn interaction trace with a stateful tool. At each turn, the new state of the tool is appended "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05065","kind":"arxiv","version":1},"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/2507.05065/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":"2026-07-05T11:33:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"onlDPFUvwaEF1oJ1B7zzpfGTRPaed7H3+MXqDWk+N/ayXT3ddpEUjZUJokH6QpjuB47J+H0I0BzWCTh/AdkJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T18:22:48.443476Z"},"content_sha256":"38f4b1f9171d168123907abcb6c060129f4b86717dd04d331ec179a197db1596","schema_version":"1.0","event_id":"sha256:38f4b1f9171d168123907abcb6c060129f4b86717dd04d331ec179a197db1596"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GZBZ4ZYMWDHJN4IHLMJ2YTR6LD/bundle.json","state_url":"https://pith.science/pith/GZBZ4ZYMWDHJN4IHLMJ2YTR6LD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GZBZ4ZYMWDHJN4IHLMJ2YTR6LD/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":"2026-08-13T18:22:48Z","links":{"resolver":"https://pith.science/pith/GZBZ4ZYMWDHJN4IHLMJ2YTR6LD","bundle":"https://pith.science/pith/GZBZ4ZYMWDHJN4IHLMJ2YTR6LD/bundle.json","state":"https://pith.science/pith/GZBZ4ZYMWDHJN4IHLMJ2YTR6LD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GZBZ4ZYMWDHJN4IHLMJ2YTR6LD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GZBZ4ZYMWDHJN4IHLMJ2YTR6LD","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":"6032e4babf18b9468b5408f79e560756796d5992d0cdd8b5e9bb66351a2f412c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T14:49:18Z","title_canon_sha256":"65e15fcb4a14e3c21cbec38dcaa85d7cf6cbed5a5b34bf321561ebb0f228840e"},"schema_version":"1.0","source":{"id":"2507.05065","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05065","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05065v1","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05065","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_12","alias_value":"GZBZ4ZYMWDHJ","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_16","alias_value":"GZBZ4ZYMWDHJN4IH","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_8","alias_value":"GZBZ4ZYM","created_at":"2026-07-05T11:33:08Z"}],"graph_snapshots":[{"event_id":"sha256:38f4b1f9171d168123907abcb6c060129f4b86717dd04d331ec179a197db1596","target":"graph","created_at":"2026-07-05T11:33:08Z","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/2507.05065/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances have established a new machine learning paradigm based on scaling up compute at inference time as well as at training time. In that line of work, a combination of Supervised Fine-Tuning (SFT) on synthetic demonstrations and Reinforcement Learning with Verifiable Rewards (RLVR) is used for training Large Language Models to expend extra compute during inference in the form of \"thoughts\" expressed in natural language. In this paper, we propose to instead format these tokens as a multi-turn interaction trace with a stateful tool. At each turn, the new state of the tool is appended ","authors_text":"Corrado Rainone, Roland Memisevic, Tim Bakker","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T14:49:18Z","title":"Replacing thinking with tool usage enables reasoning in small language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05065","kind":"arxiv","version":1},"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":"sha256:44903411e9c74c84d7deafa02c2ff3a0cbfa57c8eb51102f64c08b9b857b0692","target":"record","created_at":"2026-07-05T11:33:08Z","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":"6032e4babf18b9468b5408f79e560756796d5992d0cdd8b5e9bb66351a2f412c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T14:49:18Z","title_canon_sha256":"65e15fcb4a14e3c21cbec38dcaa85d7cf6cbed5a5b34bf321561ebb0f228840e"},"schema_version":"1.0","source":{"id":"2507.05065","kind":"arxiv","version":1}},"canonical_sha256":"36439e670cb0ce96f1075b13ac4e3e58de8c209adc57e6bc3b3b7313e4d67987","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36439e670cb0ce96f1075b13ac4e3e58de8c209adc57e6bc3b3b7313e4d67987","first_computed_at":"2026-07-05T11:33:08.495072Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:08.495072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DYzARbZKoclPzOI82fx5zcIXMTJUTWQ8VLxdx4gVc6zOj1oqkUykGnp65qcD2E8O+ISjTj01LMPHwfu+lH0xCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:08.495464Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05065","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44903411e9c74c84d7deafa02c2ff3a0cbfa57c8eb51102f64c08b9b857b0692","sha256:38f4b1f9171d168123907abcb6c060129f4b86717dd04d331ec179a197db1596"],"state_sha256":"eda9337a6c2737dfbe169dd1b805db48ab3c95d5b98864973c2c1fffbf8a0eff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uBjBXzRBr2YcFkzV0auFzxzP4G+5WO5bJ3EiIZjKRHzQij5FHQV+FK3H/hZcNkyGOtZ+Y2quLDBfPZ03G+8MDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T18:22:48.453066Z","bundle_sha256":"489d74bc17cfaaa94632e254adba6f85dbfaccea53747fcb0efe61f184613252"}}