{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2TT3Y5HS7TC2PYXKGC76INGWKQ","short_pith_number":"pith:2TT3Y5HS","schema_version":"1.0","canonical_sha256":"d4e7bc74f2fcc5a7e2ea30bfe434d6541228aedf62959697745ed23a1fa6e4cf","source":{"kind":"arxiv","id":"2411.17932","version":1},"attestation_state":"computed","paper":{"title":"Neural Networks Use Distance Metrics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alan Oursland","submitted_at":"2024-11-26T23:04:56Z","abstract_excerpt":"We present empirical evidence that neural networks with ReLU and Absolute Value activations learn distance-based representations. We independently manipulate both distance and intensity properties of internal activations in trained models, finding that both architectures are highly sensitive to small distance-based perturbations while maintaining robust performance under large intensity-based perturbations. These findings challenge the prevailing intensity-based interpretation of neural network activations and offer new insights into their learning and decision-making processes."},"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":"2411.17932","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-26T23:04:56Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4bd9ad1e8231de9b78ab4cb62da7de7a7259cd37e058478379cd21d51dc50472","abstract_canon_sha256":"d8291103b67b77b4aee77857419e736c1b06e144e538bb2860ed509603fd658a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:09.163979Z","signature_b64":"9FXLsEfRzsG2u8lYUQpuzlC+wAT5Wp+5Wr5Rkr4DkmlAGXnuCxljwlfrxu9XPR1u8iLkNEo8HbDlJU/JnlYFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4e7bc74f2fcc5a7e2ea30bfe434d6541228aedf62959697745ed23a1fa6e4cf","last_reissued_at":"2026-07-05T09:41:09.163618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:09.163618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Networks Use Distance Metrics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alan Oursland","submitted_at":"2024-11-26T23:04:56Z","abstract_excerpt":"We present empirical evidence that neural networks with ReLU and Absolute Value activations learn distance-based representations. We independently manipulate both distance and intensity properties of internal activations in trained models, finding that both architectures are highly sensitive to small distance-based perturbations while maintaining robust performance under large intensity-based perturbations. These findings challenge the prevailing intensity-based interpretation of neural network activations and offer new insights into their learning and decision-making processes."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17932","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/2411.17932/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":"2411.17932","created_at":"2026-07-05T09:41:09.163675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17932v1","created_at":"2026-07-05T09:41:09.163675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17932","created_at":"2026-07-05T09:41:09.163675+00:00"},{"alias_kind":"pith_short_12","alias_value":"2TT3Y5HS7TC2","created_at":"2026-07-05T09:41:09.163675+00:00"},{"alias_kind":"pith_short_16","alias_value":"2TT3Y5HS7TC2PYXK","created_at":"2026-07-05T09:41:09.163675+00:00"},{"alias_kind":"pith_short_8","alias_value":"2TT3Y5HS","created_at":"2026-07-05T09:41:09.163675+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02103","citing_title":"Neural Networks Learn Distance Metrics","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2TT3Y5HS7TC2PYXKGC76INGWKQ","json":"https://pith.science/pith/2TT3Y5HS7TC2PYXKGC76INGWKQ.json","graph_json":"https://pith.science/api/pith-number/2TT3Y5HS7TC2PYXKGC76INGWKQ/graph.json","events_json":"https://pith.science/api/pith-number/2TT3Y5HS7TC2PYXKGC76INGWKQ/events.json","paper":"https://pith.science/paper/2TT3Y5HS"},"agent_actions":{"view_html":"https://pith.science/pith/2TT3Y5HS7TC2PYXKGC76INGWKQ","download_json":"https://pith.science/pith/2TT3Y5HS7TC2PYXKGC76INGWKQ.json","view_paper":"https://pith.science/paper/2TT3Y5HS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17932&json=true","fetch_graph":"https://pith.science/api/pith-number/2TT3Y5HS7TC2PYXKGC76INGWKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/2TT3Y5HS7TC2PYXKGC76INGWKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2TT3Y5HS7TC2PYXKGC76INGWKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2TT3Y5HS7TC2PYXKGC76INGWKQ/action/storage_attestation","attest_author":"https://pith.science/pith/2TT3Y5HS7TC2PYXKGC76INGWKQ/action/author_attestation","sign_citation":"https://pith.science/pith/2TT3Y5HS7TC2PYXKGC76INGWKQ/action/citation_signature","submit_replication":"https://pith.science/pith/2TT3Y5HS7TC2PYXKGC76INGWKQ/action/replication_record"}},"created_at":"2026-07-05T09:41:09.163675+00:00","updated_at":"2026-07-05T09:41:09.163675+00:00"}