{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LHDACGK2WDO77Q7XD4EEKPTWSV","short_pith_number":"pith:LHDACGK2","schema_version":"1.0","canonical_sha256":"59c601195ab0ddffc3f71f08453e7695799b089374db77352c529518ff4b7144","source":{"kind":"arxiv","id":"2607.25122","version":1},"attestation_state":"computed","paper":{"title":"Semantic Space Search Trajectory Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alberto Tonda, Cristina Manfredotti, Evelyne Lutton, Gabriela Ochoa, Julian Agudelo, Vincent Guigue","submitted_at":"2026-07-27T22:30:02Z","abstract_excerpt":"Search Trajectory Networks (STNs) are a graph-based tool for visualizing and characterizing the behavior of optimization algorithms. STNs' reliance on discretization of the search space has largely confined them to low-dimensional or combinatorial settings. We introduce a methodology for constructing STNs in semantic spaces, defined as the space of a model's predictions on a fixed sample set. Our approach discretizes semantic vectors and aggregates them into network nodes via agglomerative clustering with complete linkage under a normalized Hamming distance. Since any predictor can be summariz"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.25122","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T22:30:02Z","cross_cats_sorted":[],"title_canon_sha256":"89eeacc650de17cb31c45c582b53015c39a7e593ce88c611f91a081d6160423b","abstract_canon_sha256":"f49553eb936688fb43bee374bac189ea922b65fe1e022a7e9fb60d504df7042c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:25:03.907393Z","signature_b64":"ZgYt0z/3QtL6EROMr+PXKKD7DYs/pTZDfAQc2wf4SFxqxcamYPpCvV15QJ8uEq7Rjv4UFtOHV08y0Mau7zvnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59c601195ab0ddffc3f71f08453e7695799b089374db77352c529518ff4b7144","last_reissued_at":"2026-07-29T00:25:03.906481Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:25:03.906481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Space Search Trajectory Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alberto Tonda, Cristina Manfredotti, Evelyne Lutton, Gabriela Ochoa, Julian Agudelo, Vincent Guigue","submitted_at":"2026-07-27T22:30:02Z","abstract_excerpt":"Search Trajectory Networks (STNs) are a graph-based tool for visualizing and characterizing the behavior of optimization algorithms. STNs' reliance on discretization of the search space has largely confined them to low-dimensional or combinatorial settings. We introduce a methodology for constructing STNs in semantic spaces, defined as the space of a model's predictions on a fixed sample set. Our approach discretizes semantic vectors and aggregates them into network nodes via agglomerative clustering with complete linkage under a normalized Hamming distance. Since any predictor can be summariz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25122","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/2607.25122/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.25122","created_at":"2026-07-29T00:25:03.906932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.25122v1","created_at":"2026-07-29T00:25:03.906932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25122","created_at":"2026-07-29T00:25:03.906932+00:00"},{"alias_kind":"pith_short_12","alias_value":"LHDACGK2WDO7","created_at":"2026-07-29T00:25:03.906932+00:00"},{"alias_kind":"pith_short_16","alias_value":"LHDACGK2WDO77Q7X","created_at":"2026-07-29T00:25:03.906932+00:00"},{"alias_kind":"pith_short_8","alias_value":"LHDACGK2","created_at":"2026-07-29T00:25:03.906932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LHDACGK2WDO77Q7XD4EEKPTWSV","json":"https://pith.science/pith/LHDACGK2WDO77Q7XD4EEKPTWSV.json","graph_json":"https://pith.science/api/pith-number/LHDACGK2WDO77Q7XD4EEKPTWSV/graph.json","events_json":"https://pith.science/api/pith-number/LHDACGK2WDO77Q7XD4EEKPTWSV/events.json","paper":"https://pith.science/paper/LHDACGK2"},"agent_actions":{"view_html":"https://pith.science/pith/LHDACGK2WDO77Q7XD4EEKPTWSV","download_json":"https://pith.science/pith/LHDACGK2WDO77Q7XD4EEKPTWSV.json","view_paper":"https://pith.science/paper/LHDACGK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.25122&json=true","fetch_graph":"https://pith.science/api/pith-number/LHDACGK2WDO77Q7XD4EEKPTWSV/graph.json","fetch_events":"https://pith.science/api/pith-number/LHDACGK2WDO77Q7XD4EEKPTWSV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LHDACGK2WDO77Q7XD4EEKPTWSV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LHDACGK2WDO77Q7XD4EEKPTWSV/action/storage_attestation","attest_author":"https://pith.science/pith/LHDACGK2WDO77Q7XD4EEKPTWSV/action/author_attestation","sign_citation":"https://pith.science/pith/LHDACGK2WDO77Q7XD4EEKPTWSV/action/citation_signature","submit_replication":"https://pith.science/pith/LHDACGK2WDO77Q7XD4EEKPTWSV/action/replication_record"}},"created_at":"2026-07-29T00:25:03.906932+00:00","updated_at":"2026-07-29T00:25:03.906932+00:00"}