{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4RKJTZ7MJLC6JZLCYW4KEJGQ73","short_pith_number":"pith:4RKJTZ7M","canonical_record":{"source":{"id":"2403.09024","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T01:28:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"46772a2a2d244a6ddc6df6c0caafa4a8de40a6f0536469955a76134b4e6a2d14","abstract_canon_sha256":"d71e7514874ed6a5356c047aab810288f23b8f8015ea149ae020d2071b7318b6"},"schema_version":"1.0"},"canonical_sha256":"e45499e7ec4ac5e4e562c5b8a224d0fef082ab029ede24577708dd133e9f7fa6","source":{"kind":"arxiv","id":"2403.09024","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09024","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09024v1","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09024","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_12","alias_value":"4RKJTZ7MJLC6","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_16","alias_value":"4RKJTZ7MJLC6JZLC","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_8","alias_value":"4RKJTZ7M","created_at":"2026-07-05T07:55:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4RKJTZ7MJLC6JZLCYW4KEJGQ73","target":"record","payload":{"canonical_record":{"source":{"id":"2403.09024","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T01:28:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"46772a2a2d244a6ddc6df6c0caafa4a8de40a6f0536469955a76134b4e6a2d14","abstract_canon_sha256":"d71e7514874ed6a5356c047aab810288f23b8f8015ea149ae020d2071b7318b6"},"schema_version":"1.0"},"canonical_sha256":"e45499e7ec4ac5e4e562c5b8a224d0fef082ab029ede24577708dd133e9f7fa6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:50.704149Z","signature_b64":"cl3o7OY0o7k+nHb+Nf3RnHWyQ7h/5E6fc04OI+RrDoQA3iL4sQ6nfnzLz9gDVKkGAYlxdvhb89asxFRsJ7EgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e45499e7ec4ac5e4e562c5b8a224d0fef082ab029ede24577708dd133e9f7fa6","last_reissued_at":"2026-07-05T07:55:50.703703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:50.703703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.09024","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":"2026-07-05T07:55:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R0JaxX/HlE3uX/mPH4TRCj5cKY1wk2g0QVRrLTTnKJ2zVPv27ip59Uvn7Se/SxhdDJ4trXIbduHv1BdmNaSlCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:27:40.875988Z"},"content_sha256":"6c33e681adb9e3786e647a7a211506fa94b372bec07a8a38ef42f8c429558882","schema_version":"1.0","event_id":"sha256:6c33e681adb9e3786e647a7a211506fa94b372bec07a8a38ef42f8c429558882"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4RKJTZ7MJLC6JZLCYW4KEJGQ73","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semiparametric Token-Sequence Co-Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Doyoung Kim, Hyunji Lee, Jihoon Jun, Joel Jang, Kyoung-Woon On, Minjoon Seo, Sejune Joo","submitted_at":"2024-03-14T01:28:13Z","abstract_excerpt":"In this work, we introduce a semiparametric token-sequence co-supervision training method. It trains a language model by simultaneously leveraging supervision from the traditional next token prediction loss which is calculated over the parametric token embedding space and the next sequence prediction loss which is calculated over the nonparametric sequence embedding space. The nonparametric sequence embedding space is constructed by a separate language model tasked to condense an input text into a single representative embedding. Our experiments demonstrate that a model trained via both superv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09024","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/2403.09024/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":"2026-07-05T07:55:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M7EBRlZaaNEkNwmc9WuM/8myMmKOfImgMQfKAV9naLo7yBCg5iBSaCeN7SMSCRr0z9iZCmHDpZwW37Fn85anAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T12:27:40.877326Z"},"content_sha256":"0d184a2f9ff8c1c586a3ed2aa7e07ff61b240f71b6b932f712c689a5ace8f329","schema_version":"1.0","event_id":"sha256:0d184a2f9ff8c1c586a3ed2aa7e07ff61b240f71b6b932f712c689a5ace8f329"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4RKJTZ7MJLC6JZLCYW4KEJGQ73/bundle.json","state_url":"https://pith.science/pith/4RKJTZ7MJLC6JZLCYW4KEJGQ73/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4RKJTZ7MJLC6JZLCYW4KEJGQ73/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":"2026-08-11T12:27:40Z","links":{"resolver":"https://pith.science/pith/4RKJTZ7MJLC6JZLCYW4KEJGQ73","bundle":"https://pith.science/pith/4RKJTZ7MJLC6JZLCYW4KEJGQ73/bundle.json","state":"https://pith.science/pith/4RKJTZ7MJLC6JZLCYW4KEJGQ73/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4RKJTZ7MJLC6JZLCYW4KEJGQ73/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4RKJTZ7MJLC6JZLCYW4KEJGQ73","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":"d71e7514874ed6a5356c047aab810288f23b8f8015ea149ae020d2071b7318b6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T01:28:13Z","title_canon_sha256":"46772a2a2d244a6ddc6df6c0caafa4a8de40a6f0536469955a76134b4e6a2d14"},"schema_version":"1.0","source":{"id":"2403.09024","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09024","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09024v1","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09024","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_12","alias_value":"4RKJTZ7MJLC6","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_16","alias_value":"4RKJTZ7MJLC6JZLC","created_at":"2026-07-05T07:55:50Z"},{"alias_kind":"pith_short_8","alias_value":"4RKJTZ7M","created_at":"2026-07-05T07:55:50Z"}],"graph_snapshots":[{"event_id":"sha256:0d184a2f9ff8c1c586a3ed2aa7e07ff61b240f71b6b932f712c689a5ace8f329","target":"graph","created_at":"2026-07-05T07:55:50Z","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/2403.09024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we introduce a semiparametric token-sequence co-supervision training method. It trains a language model by simultaneously leveraging supervision from the traditional next token prediction loss which is calculated over the parametric token embedding space and the next sequence prediction loss which is calculated over the nonparametric sequence embedding space. The nonparametric sequence embedding space is constructed by a separate language model tasked to condense an input text into a single representative embedding. Our experiments demonstrate that a model trained via both superv","authors_text":"Doyoung Kim, Hyunji Lee, Jihoon Jun, Joel Jang, Kyoung-Woon On, Minjoon Seo, Sejune Joo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T01:28:13Z","title":"Semiparametric Token-Sequence Co-Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09024","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":"sha256:6c33e681adb9e3786e647a7a211506fa94b372bec07a8a38ef42f8c429558882","target":"record","created_at":"2026-07-05T07:55:50Z","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":"d71e7514874ed6a5356c047aab810288f23b8f8015ea149ae020d2071b7318b6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T01:28:13Z","title_canon_sha256":"46772a2a2d244a6ddc6df6c0caafa4a8de40a6f0536469955a76134b4e6a2d14"},"schema_version":"1.0","source":{"id":"2403.09024","kind":"arxiv","version":1}},"canonical_sha256":"e45499e7ec4ac5e4e562c5b8a224d0fef082ab029ede24577708dd133e9f7fa6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e45499e7ec4ac5e4e562c5b8a224d0fef082ab029ede24577708dd133e9f7fa6","first_computed_at":"2026-07-05T07:55:50.703703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:50.703703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cl3o7OY0o7k+nHb+Nf3RnHWyQ7h/5E6fc04OI+RrDoQA3iL4sQ6nfnzLz9gDVKkGAYlxdvhb89asxFRsJ7EgDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:50.704149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.09024","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c33e681adb9e3786e647a7a211506fa94b372bec07a8a38ef42f8c429558882","sha256:0d184a2f9ff8c1c586a3ed2aa7e07ff61b240f71b6b932f712c689a5ace8f329"],"state_sha256":"5e5192906a325fb376158f8e6a138d55057dfbb0c3bb34200aeb8f0c3cbb7e8f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3iLgxEyxHHorrAsaTS0f7kW9BFdblkNB8GdkgK8PnZUz/SGSedRRHLB+fYlRHN1koOmXnsgwHLwq/TSYGCyWBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T12:27:40.884237Z","bundle_sha256":"7ace44707f203b1ed011946cf6e66d1243d12a8eb182a8bf5d8594b9378db149"}}