{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:J3KSYD4POTS2BOOJC7PXPZLZPH","short_pith_number":"pith:J3KSYD4P","schema_version":"1.0","canonical_sha256":"4ed52c0f8f74e5a0b9c917df77e57979dffbd72869df18a14e6d92e5bb99af7a","source":{"kind":"arxiv","id":"2606.01302","version":1},"attestation_state":"computed","paper":{"title":"Structure and Scale in Simplicial Sequence Modelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Matthew Farrugia-Roberts","submitted_at":"2026-05-31T15:44:57Z","abstract_excerpt":"Modern large-scale deep learning exhibits two striking empirical phenomena: behavioural scaling laws (predictable performance gains with increasing scale) and emergent mechanisms (structured internal representations and circuits in deep neural networks). We hypothesise that these two phenomena are connected: that predictable changes in behaviour are the result of predictable changes in internal computational structure. In this paper, we report preliminary evidence of such a connection. We find a correlation between scaling patterns in performance and representations in small transformers train"},"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":"2606.01302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T15:44:57Z","cross_cats_sorted":[],"title_canon_sha256":"9753d7be0f597689e4a32fe74584abdad7561ec7d12a51d39f03d3bc215d494a","abstract_canon_sha256":"9a19fa7737717bbca0875632323613a6579d8536db3848a7395eeabfb54a0912"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:29.525644Z","signature_b64":"lM43DumfDvgme6wOj+632Pah/MU0mL4cw3xijyT4hV19bInQWFXgC3fTg/hKS+zTWLNKtas7Wf65z1jFNXPvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ed52c0f8f74e5a0b9c917df77e57979dffbd72869df18a14e6d92e5bb99af7a","last_reissued_at":"2026-06-02T02:04:29.525212Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:29.525212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structure and Scale in Simplicial Sequence Modelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Matthew Farrugia-Roberts","submitted_at":"2026-05-31T15:44:57Z","abstract_excerpt":"Modern large-scale deep learning exhibits two striking empirical phenomena: behavioural scaling laws (predictable performance gains with increasing scale) and emergent mechanisms (structured internal representations and circuits in deep neural networks). We hypothesise that these two phenomena are connected: that predictable changes in behaviour are the result of predictable changes in internal computational structure. In this paper, we report preliminary evidence of such a connection. We find a correlation between scaling patterns in performance and representations in small transformers train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01302","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/2606.01302/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":"2606.01302","created_at":"2026-06-02T02:04:29.525276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01302v1","created_at":"2026-06-02T02:04:29.525276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01302","created_at":"2026-06-02T02:04:29.525276+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3KSYD4POTS2","created_at":"2026-06-02T02:04:29.525276+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3KSYD4POTS2BOOJ","created_at":"2026-06-02T02:04:29.525276+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3KSYD4P","created_at":"2026-06-02T02:04:29.525276+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/J3KSYD4POTS2BOOJC7PXPZLZPH","json":"https://pith.science/pith/J3KSYD4POTS2BOOJC7PXPZLZPH.json","graph_json":"https://pith.science/api/pith-number/J3KSYD4POTS2BOOJC7PXPZLZPH/graph.json","events_json":"https://pith.science/api/pith-number/J3KSYD4POTS2BOOJC7PXPZLZPH/events.json","paper":"https://pith.science/paper/J3KSYD4P"},"agent_actions":{"view_html":"https://pith.science/pith/J3KSYD4POTS2BOOJC7PXPZLZPH","download_json":"https://pith.science/pith/J3KSYD4POTS2BOOJC7PXPZLZPH.json","view_paper":"https://pith.science/paper/J3KSYD4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01302&json=true","fetch_graph":"https://pith.science/api/pith-number/J3KSYD4POTS2BOOJC7PXPZLZPH/graph.json","fetch_events":"https://pith.science/api/pith-number/J3KSYD4POTS2BOOJC7PXPZLZPH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3KSYD4POTS2BOOJC7PXPZLZPH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3KSYD4POTS2BOOJC7PXPZLZPH/action/storage_attestation","attest_author":"https://pith.science/pith/J3KSYD4POTS2BOOJC7PXPZLZPH/action/author_attestation","sign_citation":"https://pith.science/pith/J3KSYD4POTS2BOOJC7PXPZLZPH/action/citation_signature","submit_replication":"https://pith.science/pith/J3KSYD4POTS2BOOJC7PXPZLZPH/action/replication_record"}},"created_at":"2026-06-02T02:04:29.525276+00:00","updated_at":"2026-06-02T02:04:29.525276+00:00"}