{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OGHAE6UYPBOV6JU5J7OEEEZG46","short_pith_number":"pith:OGHAE6UY","schema_version":"1.0","canonical_sha256":"718e027a98785d5f269d4fdc421326e788184cd5c40f069bc8b0098fb0c0294e","source":{"kind":"arxiv","id":"2605.12992","version":1},"attestation_state":"computed","paper":{"title":"SpikeProphecy: A Large-Scale Benchmark for Autoregressive Neural Population Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A three-part breakdown of spike forecasting metrics reveals stable brain-region predictability rankings that hold after correcting for firing statistics.","cross_cats":["cs.LG"],"primary_cat":"q-bio.NC","authors_text":"Ash Robbins, David Haussler, Jason K. Eshraghian, Jesus Gonzalez-Ferrer, Jinghui Geng, John R. Minnick, Kamran Hussain, Mircea Teodorescu, Mohammed A. Mostajo-Radji","submitted_at":"2026-05-13T04:45:35Z","abstract_excerpt":"Neural population models, which predict the joint firing of many simultaneously recorded neurons forward in time, are typically evaluated by a single aggregate Pearson correlation $r$ between predicted and actual spike counts, a number that masks critical structure. We argue that how we evaluate spike forecasting matters as much as what we build, and introduce SpikeProphecy, the first large-scale benchmark for causal, autoregressive spike-count forecasting on real electrophysiology recordings. Our core contribution is a population metric decomposition that separates aggregate performance into "},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.12992","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.NC","submitted_at":"2026-05-13T04:45:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c90e7dd64600257aed60ce0537a6d9898bbd84a989f9948b5c7494e159a0bd28","abstract_canon_sha256":"25419648de73807054565c42ffa419fdb30a5f85a19e7744ec39d36650b73113"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:00.525062Z","signature_b64":"ddiKm6zTR5qZELRApyvuks7Mym7+/sCOBtUc+NXbNhb3iXNCAyuuBq6lTEEatDThDTNqZPUYcLtMCyLwy6VzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"718e027a98785d5f269d4fdc421326e788184cd5c40f069bc8b0098fb0c0294e","last_reissued_at":"2026-05-18T03:09:00.524583Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:00.524583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpikeProphecy: A Large-Scale Benchmark for Autoregressive Neural Population Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A three-part breakdown of spike forecasting metrics reveals stable brain-region predictability rankings that hold after correcting for firing statistics.","cross_cats":["cs.LG"],"primary_cat":"q-bio.NC","authors_text":"Ash Robbins, David Haussler, Jason K. Eshraghian, Jesus Gonzalez-Ferrer, Jinghui Geng, John R. Minnick, Kamran Hussain, Mircea Teodorescu, Mohammed A. Mostajo-Radji","submitted_at":"2026-05-13T04:45:35Z","abstract_excerpt":"Neural population models, which predict the joint firing of many simultaneously recorded neurons forward in time, are typically evaluated by a single aggregate Pearson correlation $r$ between predicted and actual spike counts, a number that masks critical structure. We argue that how we evaluate spike forecasting matters as much as what we build, and introduce SpikeProphecy, the first large-scale benchmark for causal, autoregressive spike-count forecasting on real electrophysiology recordings. Our core contribution is a population metric decomposition that separates aggregate performance into "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The population metric decomposition surfaces a brain-region predictability ranking that reproduces across all seven baselines and survives ANCOVA correction for firing-statistics constraints (region ΔR² = 0.018 above the firing-statistics covariates). It also exposes a sub-Poisson evaluation floor and yields a negative result on KL-on-output-rates distillation for ANN-to-SNN transfer.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the three-way metric decomposition captures biologically meaningful and independent aspects of forecasting quality rather than merely re-expressing the same aggregate correlation in different coordinates, and that the ANCOVA covariates fully capture firing-statistics confounds without residual selection effects from the chosen sessions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SpikeProphecy decomposes spike-count forecasting performance into temporal fidelity, spatial pattern accuracy, and magnitude-invariant alignment, revealing reproducible brain-region predictability rankings and a sub-Poisson evaluation floor across seven model families on 105 Neuropixels sessions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A three-part breakdown of spike forecasting metrics reveals stable brain-region predictability rankings that hold after correcting for firing statistics.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"659aafa6360ff17780ad87f695eb98c58ef8dc15ec4fa87c58f421d5173ee01a"},"source":{"id":"2605.12992","kind":"arxiv","version":1},"verdict":{"id":"79f38982-a567-4ffa-9336-e76aa82365d5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T02:13:37.499343Z","strongest_claim":"The population metric decomposition surfaces a brain-region predictability ranking that reproduces across all seven baselines and survives ANCOVA correction for firing-statistics constraints (region ΔR² = 0.018 above the firing-statistics covariates). It also exposes a sub-Poisson evaluation floor and yields a negative result on KL-on-output-rates distillation for ANN-to-SNN transfer.","one_line_summary":"SpikeProphecy decomposes spike-count forecasting performance into temporal fidelity, spatial pattern accuracy, and magnitude-invariant alignment, revealing reproducible brain-region predictability rankings and a sub-Poisson evaluation floor across seven model families on 105 Neuropixels sessions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the three-way metric decomposition captures biologically meaningful and independent aspects of forecasting quality rather than merely re-expressing the same aggregate correlation in different coordinates, and that the ANCOVA covariates fully capture firing-statistics confounds without residual selection effects from the chosen sessions.","pith_extraction_headline":"A three-part breakdown of spike forecasting metrics reveals stable brain-region predictability rankings that hold after correcting for firing statistics."},"references":{"count":17,"sample":[{"doi":"","year":null,"title":"Advances in Neural Information Processing Systems , volume=","work_id":"235aac2e-9d5f-43a6-9028-09a9884baa23","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"POCO: Scalable neural forecasting through population conditioning , author=. ArXiv , pages=","work_id":"b77235be-1ee6-483f-b6c0-50f26da1e17a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1986,"title":"Neuronal population coding of movement direction , author=. Science , volume=. 1986 , publisher=","work_id":"1f597a82-2d31-4a48-848e-78a7c127f68f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","work_id":"4ee75248-1199-492c-a52f-6661e0f4adff","ref_index":4,"cited_arxiv_id":"2312.00752","is_internal_anchor":true},{"doi":"","year":null,"title":"arXiv preprint arXiv:2404.07904 , year=","work_id":"62f21939-fe4f-4159-bb1e-6a303fdc7b42","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":17,"snapshot_sha256":"c05d5b66dc4967a2b39253c496d8e6f524f762b6570e7df5a19eca72d80ee442","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0727341fb9525ffec36e36531e5ee5b5c6560331cf6555f69ba81d306f00409e"},"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":"2605.12992","created_at":"2026-05-18T03:09:00.524650+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12992v1","created_at":"2026-05-18T03:09:00.524650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12992","created_at":"2026-05-18T03:09:00.524650+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGHAE6UYPBOV","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGHAE6UYPBOV6JU5","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGHAE6UY","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OGHAE6UYPBOV6JU5J7OEEEZG46","json":"https://pith.science/pith/OGHAE6UYPBOV6JU5J7OEEEZG46.json","graph_json":"https://pith.science/api/pith-number/OGHAE6UYPBOV6JU5J7OEEEZG46/graph.json","events_json":"https://pith.science/api/pith-number/OGHAE6UYPBOV6JU5J7OEEEZG46/events.json","paper":"https://pith.science/paper/OGHAE6UY"},"agent_actions":{"view_html":"https://pith.science/pith/OGHAE6UYPBOV6JU5J7OEEEZG46","download_json":"https://pith.science/pith/OGHAE6UYPBOV6JU5J7OEEEZG46.json","view_paper":"https://pith.science/paper/OGHAE6UY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12992&json=true","fetch_graph":"https://pith.science/api/pith-number/OGHAE6UYPBOV6JU5J7OEEEZG46/graph.json","fetch_events":"https://pith.science/api/pith-number/OGHAE6UYPBOV6JU5J7OEEEZG46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGHAE6UYPBOV6JU5J7OEEEZG46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGHAE6UYPBOV6JU5J7OEEEZG46/action/storage_attestation","attest_author":"https://pith.science/pith/OGHAE6UYPBOV6JU5J7OEEEZG46/action/author_attestation","sign_citation":"https://pith.science/pith/OGHAE6UYPBOV6JU5J7OEEEZG46/action/citation_signature","submit_replication":"https://pith.science/pith/OGHAE6UYPBOV6JU5J7OEEEZG46/action/replication_record"}},"created_at":"2026-05-18T03:09:00.524650+00:00","updated_at":"2026-05-18T03:09:00.524650+00:00"}