{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Q5EPHG7IGI36TO4OWHGA7TX2QF","short_pith_number":"pith:Q5EPHG7I","schema_version":"1.0","canonical_sha256":"8748f39be83237e9bb8eb1cc0fcefa816700063fec17afe678d7e063e9e46bc3","source":{"kind":"arxiv","id":"2211.16607","version":2},"attestation_state":"computed","paper":{"title":"Transfer Entropy Bottleneck: Learning Sequence to Sequence Information Transfer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Blake Richards, Damjan Kalajdzievski, Guillaume Lajoie, Pascal Fortier-Poisson, Ximeng Mao","submitted_at":"2022-11-29T22:02:20Z","abstract_excerpt":"When presented with a data stream of two statistically dependent variables, predicting the future of one of the variables (the target stream) can benefit from information about both its history and the history of the other variable (the source stream). For example, fluctuations in temperature at a weather station can be predicted using both temperatures and barometric readings. However, a challenge when modelling such data is that it is easy for a neural network to rely on the greatest joint correlations within the target stream, which may ignore a crucial but small information transfer from t"},"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":"2211.16607","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-29T22:02:20Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"eeb59ad517da70690917d63c40bc664f0ec9268a98eee036d9e2a1e307ca1190","abstract_canon_sha256":"ac81f8f17c4d28e95fa875aadb8490a0cca14a0b61d42acb3688a1fc68d7aaef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:31.624413Z","signature_b64":"rW9MjIFqTpJarC7dlioNbBvgsZ5wEec6A0PI6UYZO2NQGwYliqbFFIwhwL0P7Sa0qDZsfVjIq1WIQt9wdZAzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8748f39be83237e9bb8eb1cc0fcefa816700063fec17afe678d7e063e9e46bc3","last_reissued_at":"2026-07-05T05:49:31.623778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:31.623778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transfer Entropy Bottleneck: Learning Sequence to Sequence Information Transfer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Blake Richards, Damjan Kalajdzievski, Guillaume Lajoie, Pascal Fortier-Poisson, Ximeng Mao","submitted_at":"2022-11-29T22:02:20Z","abstract_excerpt":"When presented with a data stream of two statistically dependent variables, predicting the future of one of the variables (the target stream) can benefit from information about both its history and the history of the other variable (the source stream). For example, fluctuations in temperature at a weather station can be predicted using both temperatures and barometric readings. However, a challenge when modelling such data is that it is easy for a neural network to rely on the greatest joint correlations within the target stream, which may ignore a crucial but small information transfer from t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.16607","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/2211.16607/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":"2211.16607","created_at":"2026-07-05T05:49:31.623865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.16607v2","created_at":"2026-07-05T05:49:31.623865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.16607","created_at":"2026-07-05T05:49:31.623865+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5EPHG7IGI36","created_at":"2026-07-05T05:49:31.623865+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5EPHG7IGI36TO4O","created_at":"2026-07-05T05:49:31.623865+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5EPHG7I","created_at":"2026-07-05T05:49:31.623865+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08884","citing_title":"InfoDPCCA: Information-Theoretic Dynamic Probabilistic Canonical Correlation Analysis","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q5EPHG7IGI36TO4OWHGA7TX2QF","json":"https://pith.science/pith/Q5EPHG7IGI36TO4OWHGA7TX2QF.json","graph_json":"https://pith.science/api/pith-number/Q5EPHG7IGI36TO4OWHGA7TX2QF/graph.json","events_json":"https://pith.science/api/pith-number/Q5EPHG7IGI36TO4OWHGA7TX2QF/events.json","paper":"https://pith.science/paper/Q5EPHG7I"},"agent_actions":{"view_html":"https://pith.science/pith/Q5EPHG7IGI36TO4OWHGA7TX2QF","download_json":"https://pith.science/pith/Q5EPHG7IGI36TO4OWHGA7TX2QF.json","view_paper":"https://pith.science/paper/Q5EPHG7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.16607&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5EPHG7IGI36TO4OWHGA7TX2QF/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5EPHG7IGI36TO4OWHGA7TX2QF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5EPHG7IGI36TO4OWHGA7TX2QF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5EPHG7IGI36TO4OWHGA7TX2QF/action/storage_attestation","attest_author":"https://pith.science/pith/Q5EPHG7IGI36TO4OWHGA7TX2QF/action/author_attestation","sign_citation":"https://pith.science/pith/Q5EPHG7IGI36TO4OWHGA7TX2QF/action/citation_signature","submit_replication":"https://pith.science/pith/Q5EPHG7IGI36TO4OWHGA7TX2QF/action/replication_record"}},"created_at":"2026-07-05T05:49:31.623865+00:00","updated_at":"2026-07-05T05:49:31.623865+00:00"}