{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WG5VE2QD7C4MRIUV6PR33LUM3K","short_pith_number":"pith:WG5VE2QD","schema_version":"1.0","canonical_sha256":"b1bb526a03f8b8c8a295f3e3bdae8cda872655a0d2ba22578787981fc005b005","source":{"kind":"arxiv","id":"2502.01803","version":1},"attestation_state":"computed","paper":{"title":"Discovering Chunks in Neural Embeddings for Interpretability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eric Schulz, Shuchen Wu, Stephan Alaniz, Zeynep Akata","submitted_at":"2025-02-03T20:30:46Z","abstract_excerpt":"Understanding neural networks is challenging due to their high-dimensional, interacting components. Inspired by human cognition, which processes complex sensory data by chunking it into recurring entities, we propose leveraging this principle to interpret artificial neural population activities. Biological and artificial intelligence share the challenge of learning from structured, naturalistic data, and we hypothesize that the cognitive mechanism of chunking can provide insights into artificial systems. We first demonstrate this concept in recurrent neural networks (RNNs) trained on artificia"},"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":"2502.01803","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T20:30:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3f013fda7352e2f9e87afd01d7dfcfeb5a12da63e639f284b0de3d554173fcad","abstract_canon_sha256":"f5ff01faf30480a49df2c3dcd125e00720624ee53b4dd4e67daadfed1d144636"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:19.402900Z","signature_b64":"cMQdyXR4yJgmHhSx0+UKK+5She21jlY7ZheovABQMvk9d4Bd5N6ErEKiHQDlLx+dHGHGe3RviE/phELetdUTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1bb526a03f8b8c8a295f3e3bdae8cda872655a0d2ba22578787981fc005b005","last_reissued_at":"2026-07-05T10:09:19.402361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:19.402361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discovering Chunks in Neural Embeddings for Interpretability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eric Schulz, Shuchen Wu, Stephan Alaniz, Zeynep Akata","submitted_at":"2025-02-03T20:30:46Z","abstract_excerpt":"Understanding neural networks is challenging due to their high-dimensional, interacting components. Inspired by human cognition, which processes complex sensory data by chunking it into recurring entities, we propose leveraging this principle to interpret artificial neural population activities. Biological and artificial intelligence share the challenge of learning from structured, naturalistic data, and we hypothesize that the cognitive mechanism of chunking can provide insights into artificial systems. We first demonstrate this concept in recurrent neural networks (RNNs) trained on artificia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01803","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/2502.01803/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":"2502.01803","created_at":"2026-07-05T10:09:19.402423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01803v1","created_at":"2026-07-05T10:09:19.402423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01803","created_at":"2026-07-05T10:09:19.402423+00:00"},{"alias_kind":"pith_short_12","alias_value":"WG5VE2QD7C4M","created_at":"2026-07-05T10:09:19.402423+00:00"},{"alias_kind":"pith_short_16","alias_value":"WG5VE2QD7C4MRIUV","created_at":"2026-07-05T10:09:19.402423+00:00"},{"alias_kind":"pith_short_8","alias_value":"WG5VE2QD","created_at":"2026-07-05T10:09:19.402423+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/WG5VE2QD7C4MRIUV6PR33LUM3K","json":"https://pith.science/pith/WG5VE2QD7C4MRIUV6PR33LUM3K.json","graph_json":"https://pith.science/api/pith-number/WG5VE2QD7C4MRIUV6PR33LUM3K/graph.json","events_json":"https://pith.science/api/pith-number/WG5VE2QD7C4MRIUV6PR33LUM3K/events.json","paper":"https://pith.science/paper/WG5VE2QD"},"agent_actions":{"view_html":"https://pith.science/pith/WG5VE2QD7C4MRIUV6PR33LUM3K","download_json":"https://pith.science/pith/WG5VE2QD7C4MRIUV6PR33LUM3K.json","view_paper":"https://pith.science/paper/WG5VE2QD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01803&json=true","fetch_graph":"https://pith.science/api/pith-number/WG5VE2QD7C4MRIUV6PR33LUM3K/graph.json","fetch_events":"https://pith.science/api/pith-number/WG5VE2QD7C4MRIUV6PR33LUM3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WG5VE2QD7C4MRIUV6PR33LUM3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WG5VE2QD7C4MRIUV6PR33LUM3K/action/storage_attestation","attest_author":"https://pith.science/pith/WG5VE2QD7C4MRIUV6PR33LUM3K/action/author_attestation","sign_citation":"https://pith.science/pith/WG5VE2QD7C4MRIUV6PR33LUM3K/action/citation_signature","submit_replication":"https://pith.science/pith/WG5VE2QD7C4MRIUV6PR33LUM3K/action/replication_record"}},"created_at":"2026-07-05T10:09:19.402423+00:00","updated_at":"2026-07-05T10:09:19.402423+00:00"}