{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:J4OUXZZD7OTZXPJGACC6BRYQDM","short_pith_number":"pith:J4OUXZZD","schema_version":"1.0","canonical_sha256":"4f1d4be723fba79bbd260085e0c7101b2726d7d0249d449b465eb6c139054739","source":{"kind":"arxiv","id":"2211.11665","version":2},"attestation_state":"computed","paper":{"title":"Representational dissimilarity metric spaces for stochastic neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.NC"],"primary_cat":"cs.LG","authors_text":"Alex H. Williams, Jeroen Olieslagers, Jingyang Zhou, Josue Nassar, Jules Berman, Lyndon R. Duong","submitted_at":"2022-11-21T17:32:40Z","abstract_excerpt":"Quantifying similarity between neural representations -- e.g. hidden layer activation vectors -- is a perennial problem in deep learning and neuroscience research. Existing methods compare deterministic responses (e.g. artificial networks that lack stochastic layers) or averaged responses (e.g., trial-averaged firing rates in biological data). However, these measures of _deterministic_ representational similarity ignore the scale and geometric structure of noise, both of which play important roles in neural computation. To rectify this, we generalize previously proposed shape metrics (Williams"},"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":"2211.11665","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-21T17:32:40Z","cross_cats_sorted":["q-bio.NC"],"title_canon_sha256":"342ba323afd8ae9e34cae89bc808ff5eab052fc7a5323be239535964bacc8fb7","abstract_canon_sha256":"f4d55bb6003417ddae4b5c4c729fc720d6d639e1970e15dee2d59b59c0f14473"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:45.673400Z","signature_b64":"jOF2mILNUS/NAFm6jI7k4YUJtYeV2LJmP9H6J0zkrfUtDO2gmErT8XdBa7VuGW9dUdCM+TA1Om1pVHkrblhNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f1d4be723fba79bbd260085e0c7101b2726d7d0249d449b465eb6c139054739","last_reissued_at":"2026-07-05T05:38:45.672996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:45.672996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representational dissimilarity metric spaces for stochastic neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.NC"],"primary_cat":"cs.LG","authors_text":"Alex H. Williams, Jeroen Olieslagers, Jingyang Zhou, Josue Nassar, Jules Berman, Lyndon R. Duong","submitted_at":"2022-11-21T17:32:40Z","abstract_excerpt":"Quantifying similarity between neural representations -- e.g. hidden layer activation vectors -- is a perennial problem in deep learning and neuroscience research. Existing methods compare deterministic responses (e.g. artificial networks that lack stochastic layers) or averaged responses (e.g., trial-averaged firing rates in biological data). However, these measures of _deterministic_ representational similarity ignore the scale and geometric structure of noise, both of which play important roles in neural computation. To rectify this, we generalize previously proposed shape metrics (Williams"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11665","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/2211.11665/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":"2211.11665","created_at":"2026-07-05T05:38:45.673052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.11665v2","created_at":"2026-07-05T05:38:45.673052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11665","created_at":"2026-07-05T05:38:45.673052+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4OUXZZD7OTZ","created_at":"2026-07-05T05:38:45.673052+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4OUXZZD7OTZXPJG","created_at":"2026-07-05T05:38:45.673052+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4OUXZZD","created_at":"2026-07-05T05:38:45.673052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.05505","citing_title":"Dynamical Archetype Analysis: Autonomous Computation","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J4OUXZZD7OTZXPJGACC6BRYQDM","json":"https://pith.science/pith/J4OUXZZD7OTZXPJGACC6BRYQDM.json","graph_json":"https://pith.science/api/pith-number/J4OUXZZD7OTZXPJGACC6BRYQDM/graph.json","events_json":"https://pith.science/api/pith-number/J4OUXZZD7OTZXPJGACC6BRYQDM/events.json","paper":"https://pith.science/paper/J4OUXZZD"},"agent_actions":{"view_html":"https://pith.science/pith/J4OUXZZD7OTZXPJGACC6BRYQDM","download_json":"https://pith.science/pith/J4OUXZZD7OTZXPJGACC6BRYQDM.json","view_paper":"https://pith.science/paper/J4OUXZZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.11665&json=true","fetch_graph":"https://pith.science/api/pith-number/J4OUXZZD7OTZXPJGACC6BRYQDM/graph.json","fetch_events":"https://pith.science/api/pith-number/J4OUXZZD7OTZXPJGACC6BRYQDM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4OUXZZD7OTZXPJGACC6BRYQDM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4OUXZZD7OTZXPJGACC6BRYQDM/action/storage_attestation","attest_author":"https://pith.science/pith/J4OUXZZD7OTZXPJGACC6BRYQDM/action/author_attestation","sign_citation":"https://pith.science/pith/J4OUXZZD7OTZXPJGACC6BRYQDM/action/citation_signature","submit_replication":"https://pith.science/pith/J4OUXZZD7OTZXPJGACC6BRYQDM/action/replication_record"}},"created_at":"2026-07-05T05:38:45.673052+00:00","updated_at":"2026-07-05T05:38:45.673052+00:00"}