{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:46SGLAQSENW6R6MUVU45LDY4FR","short_pith_number":"pith:46SGLAQS","canonical_record":{"source":{"id":"2607.14149","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-14T13:07:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"febe249d3906881ab15ec7b6ce96852d132bd0a52ad8bb20ada5419e2a9009e2","abstract_canon_sha256":"4c4661eef31d4dbcac66eb526973332287cb7395f63200d2a632d48bae45ba7a"},"schema_version":"1.0"},"canonical_sha256":"e7a4658212236de8f994ad39d58f1c2c6527145e51a96f4fbb378a7aa8b5c7fd","source":{"kind":"arxiv","id":"2607.14149","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14149","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14149v1","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14149","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_12","alias_value":"46SGLAQSENW6","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_16","alias_value":"46SGLAQSENW6R6MU","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_8","alias_value":"46SGLAQS","created_at":"2026-07-17T00:20:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:46SGLAQSENW6R6MUVU45LDY4FR","target":"record","payload":{"canonical_record":{"source":{"id":"2607.14149","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-14T13:07:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"febe249d3906881ab15ec7b6ce96852d132bd0a52ad8bb20ada5419e2a9009e2","abstract_canon_sha256":"4c4661eef31d4dbcac66eb526973332287cb7395f63200d2a632d48bae45ba7a"},"schema_version":"1.0"},"canonical_sha256":"e7a4658212236de8f994ad39d58f1c2c6527145e51a96f4fbb378a7aa8b5c7fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:20:54.065384Z","signature_b64":"P6VIxSNeYbPoWXRkP4JKN2bOHUeIsywYvfowwX8vUzp6SxrbQtNorpo/2lDQ9CZUW2yWL7O8SHSZB7JcNiLfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7a4658212236de8f994ad39d58f1c2c6527145e51a96f4fbb378a7aa8b5c7fd","last_reissued_at":"2026-07-17T00:20:54.064547Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:20:54.064547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.14149","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":"2026-07-17T00:20:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9HTYDOu/yEn2vbFzksQO6RurS+FfKrDo7pXw18w6O987FRbD3pLjMy4xY8rdBG0HZ6SFMH7gtmhTKrO4IIjgBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:00:28.766999Z"},"content_sha256":"9421ae77d055c2e0bf0b6f44afa895460cc74977e77a1b5165cdafb536b58989","schema_version":"1.0","event_id":"sha256:9421ae77d055c2e0bf0b6f44afa895460cc74977e77a1b5165cdafb536b58989"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:46SGLAQSENW6R6MUVU45LDY4FR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Small Language Models Reasoning through Knowledge Graph Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Dimitrios Kelesis, Georgios Paliouras, Konstantinos Bougiatiotis","submitted_at":"2026-07-14T13:07:46Z","abstract_excerpt":"Although large language models (LLMs) have set benchmarks for zero-shot reasoning, their deployment remains cost-prohibitive and environmentally taxing. Small Language Models (SLMs) offer a sustainable alternative, but prone to errors, on tasks requiring complex, multi-hop logical grounding. We investigate a neuro-symbolic agentic framework to enhance the reasoning capabilities of SLMs, specifically Gemma 3 (1B, 4B) and Llama 3.2 (3B), using the CLUTRR kinship benchmark. Our approach transforms the SLM into a minimalist agent utilizing two specialized tool calls: extract_facts for symbolic tri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14149","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/2607.14149/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":"2026-07-17T00:20:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"os5NzQW3pcqDFwRAd+dcIOPuJ/FAqXuvyAop8aQKdcvnZG9KwXbhmFndx4JRReQyQi1RHaJ7L1W10kv8o9DcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:00:28.767525Z"},"content_sha256":"0ddc3f8d3f6541be22d014cbf1f9aa24c8da178cc627494ca36416c280734c47","schema_version":"1.0","event_id":"sha256:0ddc3f8d3f6541be22d014cbf1f9aa24c8da178cc627494ca36416c280734c47"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:46SGLAQSENW6R6MUVU45LDY4FR","target":"integrity","payload":{"note":"DOI is split by whitespace or line breaks in the printed bibliography. Reconstructed DOI 10.1609/AAAI.V34I09.7123 resolves to 'Energy and Policy Considerations for Modern Deep Learning Research'. A reader following the printed text alone cannot reach it.","snippet":"E. Strubell, A. Ganesh, A. McCallum, Energy and policy considerations for modern deep learning research, in: The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial In","arxiv_id":"2607.14149","detector":"doi_compliance","evidence":{"ref_index":5,"verdict_class":"incontrovertible","resolved_title":"Energy and Policy Considerations for Modern Deep Learning Research","printed_excerpt":"10.1609/aaai","reconstructed_doi":"10.1609/AAAI.V34I09.7123"},"severity":"advisory","ref_index":5,"audited_at":"2026-08-02T06:30:58.191127Z","event_type":"pith.integrity.v1","detected_doi":"10.1609/AAAI.V34I09.7123","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"99ad4cc8e77465b6dce4c504e3493f7ddc3e46c120e2785dd9b809f2b09afe13","paper_version":1,"verdict_class":"incontrovertible","resolved_title":"Energy and Policy Considerations for Modern Deep Learning Research","detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":17370,"payload_sha256":"aefb7a995ad2b999570a95011867d6daddea0240ac3fdb22b6c60104081f4340","signature_b64":"gRG1kHKH/WCVIe+9bcgWGf8Nu4qe7X40dO/xnJ7qBWHGyp9WCOPkmdBVH1TkPQrAY6CGhNHrQPUKb+edIt+hAw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-02T06:33:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cy6yCbNXfHM0zx+M8WMGW63V5BQWW7oWe1pcoSTssokT5KgNBSuknyx6wqu8rUhOQTOIEHMqmPjMdKqF2xbODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:00:28.771467Z"},"content_sha256":"e50f3e296bf5e56799a4ea532825b379ffd47eaeb02c5083c27d7f70dc3da8f7","schema_version":"1.0","event_id":"sha256:e50f3e296bf5e56799a4ea532825b379ffd47eaeb02c5083c27d7f70dc3da8f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/46SGLAQSENW6R6MUVU45LDY4FR/bundle.json","state_url":"https://pith.science/pith/46SGLAQSENW6R6MUVU45LDY4FR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/46SGLAQSENW6R6MUVU45LDY4FR/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":"2026-08-05T00:00:28Z","links":{"resolver":"https://pith.science/pith/46SGLAQSENW6R6MUVU45LDY4FR","bundle":"https://pith.science/pith/46SGLAQSENW6R6MUVU45LDY4FR/bundle.json","state":"https://pith.science/pith/46SGLAQSENW6R6MUVU45LDY4FR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/46SGLAQSENW6R6MUVU45LDY4FR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:46SGLAQSENW6R6MUVU45LDY4FR","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4c4661eef31d4dbcac66eb526973332287cb7395f63200d2a632d48bae45ba7a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-14T13:07:46Z","title_canon_sha256":"febe249d3906881ab15ec7b6ce96852d132bd0a52ad8bb20ada5419e2a9009e2"},"schema_version":"1.0","source":{"id":"2607.14149","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.14149","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.14149v1","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14149","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_12","alias_value":"46SGLAQSENW6","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_16","alias_value":"46SGLAQSENW6R6MU","created_at":"2026-07-17T00:20:54Z"},{"alias_kind":"pith_short_8","alias_value":"46SGLAQS","created_at":"2026-07-17T00:20:54Z"}],"graph_snapshots":[{"event_id":"sha256:0ddc3f8d3f6541be22d014cbf1f9aa24c8da178cc627494ca36416c280734c47","target":"graph","created_at":"2026-07-17T00:20:54Z","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/2607.14149/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although large language models (LLMs) have set benchmarks for zero-shot reasoning, their deployment remains cost-prohibitive and environmentally taxing. Small Language Models (SLMs) offer a sustainable alternative, but prone to errors, on tasks requiring complex, multi-hop logical grounding. We investigate a neuro-symbolic agentic framework to enhance the reasoning capabilities of SLMs, specifically Gemma 3 (1B, 4B) and Llama 3.2 (3B), using the CLUTRR kinship benchmark. Our approach transforms the SLM into a minimalist agent utilizing two specialized tool calls: extract_facts for symbolic tri","authors_text":"Dimitrios Kelesis, Georgios Paliouras, Konstantinos Bougiatiotis","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-14T13:07:46Z","title":"Enhancing Small Language Models Reasoning through Knowledge Graph Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14149","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":"sha256:9421ae77d055c2e0bf0b6f44afa895460cc74977e77a1b5165cdafb536b58989","target":"record","created_at":"2026-07-17T00:20:54Z","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":"4c4661eef31d4dbcac66eb526973332287cb7395f63200d2a632d48bae45ba7a","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-14T13:07:46Z","title_canon_sha256":"febe249d3906881ab15ec7b6ce96852d132bd0a52ad8bb20ada5419e2a9009e2"},"schema_version":"1.0","source":{"id":"2607.14149","kind":"arxiv","version":1}},"canonical_sha256":"e7a4658212236de8f994ad39d58f1c2c6527145e51a96f4fbb378a7aa8b5c7fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7a4658212236de8f994ad39d58f1c2c6527145e51a96f4fbb378a7aa8b5c7fd","first_computed_at":"2026-07-17T00:20:54.064547Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T00:20:54.064547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P6VIxSNeYbPoWXRkP4JKN2bOHUeIsywYvfowwX8vUzp6SxrbQtNorpo/2lDQ9CZUW2yWL7O8SHSZB7JcNiLfBQ==","signature_status":"signed_v1","signed_at":"2026-07-17T00:20:54.065384Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.14149","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9421ae77d055c2e0bf0b6f44afa895460cc74977e77a1b5165cdafb536b58989","sha256:0ddc3f8d3f6541be22d014cbf1f9aa24c8da178cc627494ca36416c280734c47","sha256:e50f3e296bf5e56799a4ea532825b379ffd47eaeb02c5083c27d7f70dc3da8f7"],"state_sha256":"5d9740ee22e372cbe7207ffa5a66576951eccc02458fdb936f328f293cdeff68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k3Sl7j2WC1NYqT/F8hXGySbg4LCjZ1f46S6Zo6GxKemlfF4aybsJwDvavcgdzh7dTvIVgw3b3om8RKhPLhXKDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T00:00:28.773550Z","bundle_sha256":"4c4b6884268ed77ed75549b0c81ad8d8677e6704bb21a09ffa41ae861c1f1481"}}