{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NOQCEUFIORBN27D5WGB4SZXJSA","short_pith_number":"pith:NOQCEUFI","canonical_record":{"source":{"id":"2412.15983","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T15:24:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1db79a7073fe27e60358d4c216dd1dd84a4a8bce6b7463f7e18ffeb8dd0d35f3","abstract_canon_sha256":"99c2a4e4ae0cfe5fcf84bb6d768028d2374d9f75f455074d9d3ac5c4d90feb5c"},"schema_version":"1.0"},"canonical_sha256":"6ba02250a87442dd7c7db183c966e9902b866959200e9c79997a242395d2f886","source":{"kind":"arxiv","id":"2412.15983","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15983","created_at":"2026-07-05T09:52:33Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15983v1","created_at":"2026-07-05T09:52:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15983","created_at":"2026-07-05T09:52:33Z"},{"alias_kind":"pith_short_12","alias_value":"NOQCEUFIORBN","created_at":"2026-07-05T09:52:33Z"},{"alias_kind":"pith_short_16","alias_value":"NOQCEUFIORBN27D5","created_at":"2026-07-05T09:52:33Z"},{"alias_kind":"pith_short_8","alias_value":"NOQCEUFI","created_at":"2026-07-05T09:52:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NOQCEUFIORBN27D5WGB4SZXJSA","target":"record","payload":{"canonical_record":{"source":{"id":"2412.15983","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T15:24:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1db79a7073fe27e60358d4c216dd1dd84a4a8bce6b7463f7e18ffeb8dd0d35f3","abstract_canon_sha256":"99c2a4e4ae0cfe5fcf84bb6d768028d2374d9f75f455074d9d3ac5c4d90feb5c"},"schema_version":"1.0"},"canonical_sha256":"6ba02250a87442dd7c7db183c966e9902b866959200e9c79997a242395d2f886","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:33.038971Z","signature_b64":"d7ETnA/kCAm/QUnLz6/6XT7riD9J6IOSPeueQjI6XhrYviahoigM333mF+VMpVt407wJoe8OhrWSel9dDTK2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ba02250a87442dd7c7db183c966e9902b866959200e9c79997a242395d2f886","last_reissued_at":"2026-07-05T09:52:33.038495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:33.038495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.15983","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:52:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MQsg3/vFKo+WbXVtl7K7R7slkhKORZMDT61Bfihlrsez5mJ869lxX7ufiBGVzDAjqDm8H5SC5d7jMoEvk4EMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:35:40.286408Z"},"content_sha256":"70701c81e6adf829963d890340e369e18b545f5cabb84b4b5ad9d4e44dbd573d","schema_version":"1.0","event_id":"sha256:70701c81e6adf829963d890340e369e18b545f5cabb84b4b5ad9d4e44dbd573d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NOQCEUFIORBN27D5WGB4SZXJSA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bojian Yin, Federico Corradi","submitted_at":"2024-12-20T15:24:28Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) are widely used for sequential processing but face fundamental limitations with continual inference due to state saturation, requiring disruptive hidden state resets. However, reset-based methods impose synchronization requirements with input boundaries and increase computational costs at inference. To address this, we propose an adaptive loss function that eliminates the need for resets during inference while preserving high accuracy over extended sequences. By combining cross-entropy and Kullback-Leibler divergence, the loss dynamically modulates the gradient"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15983","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/2412.15983/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:52:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mptp530hi4MZ8UL4H9XstIkyGy8/jNmD5V6yvKZWPkpo1b4eKVCyYYAAlbiqIZhJWVpe0apHTLUZQeel762eCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:35:40.287585Z"},"content_sha256":"fbed27340bf789170626a6c23e9de91a391250df2e42a0abe3fdcfab249f3df4","schema_version":"1.0","event_id":"sha256:fbed27340bf789170626a6c23e9de91a391250df2e42a0abe3fdcfab249f3df4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NOQCEUFIORBN27D5WGB4SZXJSA/bundle.json","state_url":"https://pith.science/pith/NOQCEUFIORBN27D5WGB4SZXJSA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NOQCEUFIORBN27D5WGB4SZXJSA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T15:35:40Z","links":{"resolver":"https://pith.science/pith/NOQCEUFIORBN27D5WGB4SZXJSA","bundle":"https://pith.science/pith/NOQCEUFIORBN27D5WGB4SZXJSA/bundle.json","state":"https://pith.science/pith/NOQCEUFIORBN27D5WGB4SZXJSA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NOQCEUFIORBN27D5WGB4SZXJSA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NOQCEUFIORBN27D5WGB4SZXJSA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"99c2a4e4ae0cfe5fcf84bb6d768028d2374d9f75f455074d9d3ac5c4d90feb5c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T15:24:28Z","title_canon_sha256":"1db79a7073fe27e60358d4c216dd1dd84a4a8bce6b7463f7e18ffeb8dd0d35f3"},"schema_version":"1.0","source":{"id":"2412.15983","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15983","created_at":"2026-07-05T09:52:33Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15983v1","created_at":"2026-07-05T09:52:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15983","created_at":"2026-07-05T09:52:33Z"},{"alias_kind":"pith_short_12","alias_value":"NOQCEUFIORBN","created_at":"2026-07-05T09:52:33Z"},{"alias_kind":"pith_short_16","alias_value":"NOQCEUFIORBN27D5","created_at":"2026-07-05T09:52:33Z"},{"alias_kind":"pith_short_8","alias_value":"NOQCEUFI","created_at":"2026-07-05T09:52:33Z"}],"graph_snapshots":[{"event_id":"sha256:fbed27340bf789170626a6c23e9de91a391250df2e42a0abe3fdcfab249f3df4","target":"graph","created_at":"2026-07-05T09:52:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.15983/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recurrent Neural Networks (RNNs) are widely used for sequential processing but face fundamental limitations with continual inference due to state saturation, requiring disruptive hidden state resets. However, reset-based methods impose synchronization requirements with input boundaries and increase computational costs at inference. To address this, we propose an adaptive loss function that eliminates the need for resets during inference while preserving high accuracy over extended sequences. By combining cross-entropy and Kullback-Leibler divergence, the loss dynamically modulates the gradient","authors_text":"Bojian Yin, Federico Corradi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T15:24:28Z","title":"Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15983","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:70701c81e6adf829963d890340e369e18b545f5cabb84b4b5ad9d4e44dbd573d","target":"record","created_at":"2026-07-05T09:52:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"99c2a4e4ae0cfe5fcf84bb6d768028d2374d9f75f455074d9d3ac5c4d90feb5c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-20T15:24:28Z","title_canon_sha256":"1db79a7073fe27e60358d4c216dd1dd84a4a8bce6b7463f7e18ffeb8dd0d35f3"},"schema_version":"1.0","source":{"id":"2412.15983","kind":"arxiv","version":1}},"canonical_sha256":"6ba02250a87442dd7c7db183c966e9902b866959200e9c79997a242395d2f886","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ba02250a87442dd7c7db183c966e9902b866959200e9c79997a242395d2f886","first_computed_at":"2026-07-05T09:52:33.038495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:33.038495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d7ETnA/kCAm/QUnLz6/6XT7riD9J6IOSPeueQjI6XhrYviahoigM333mF+VMpVt407wJoe8OhrWSel9dDTK2Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:33.038971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15983","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70701c81e6adf829963d890340e369e18b545f5cabb84b4b5ad9d4e44dbd573d","sha256:fbed27340bf789170626a6c23e9de91a391250df2e42a0abe3fdcfab249f3df4"],"state_sha256":"c0f1596aaa86fd8bb1c39dd4d93c6181e88c0b5c56bac468c31b0f200e6c2f25"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wE8lfMZAMMS4IVtQb4jy7blgAtGZHAVbfp/nlIuJqZnlwBSc3iOg/9Y9kp5b7HO13f14x/g6bo6qim0sB2vgBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T15:35:40.293184Z","bundle_sha256":"4cf870faf630ccb55ca83f829fdc33c379bd19ef02d8175106e90dac8184c207"}}