{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UP5VQ22RLZ4K6OZU2O2STUXW2Z","short_pith_number":"pith:UP5VQ22R","canonical_record":{"source":{"id":"2409.16654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-25T06:17:23Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"3c94de0056965005222730aac867682ab6638a383161ef0d3422320e067bd427","abstract_canon_sha256":"17ce28ea6b8625f4d494f7073c54f79bf94540061a7520d70e57b4ddd7da5754"},"schema_version":"1.0"},"canonical_sha256":"a3fb586b515e78af3b34d3b529d2f6d6416d85e0997e66084ef0f0d8dc8adaf5","source":{"kind":"arxiv","id":"2409.16654","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.16654","created_at":"2026-07-05T09:11:37Z"},{"alias_kind":"arxiv_version","alias_value":"2409.16654v1","created_at":"2026-07-05T09:11:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16654","created_at":"2026-07-05T09:11:37Z"},{"alias_kind":"pith_short_12","alias_value":"UP5VQ22RLZ4K","created_at":"2026-07-05T09:11:37Z"},{"alias_kind":"pith_short_16","alias_value":"UP5VQ22RLZ4K6OZU","created_at":"2026-07-05T09:11:37Z"},{"alias_kind":"pith_short_8","alias_value":"UP5VQ22R","created_at":"2026-07-05T09:11:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UP5VQ22RLZ4K6OZU2O2STUXW2Z","target":"record","payload":{"canonical_record":{"source":{"id":"2409.16654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-25T06:17:23Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"3c94de0056965005222730aac867682ab6638a383161ef0d3422320e067bd427","abstract_canon_sha256":"17ce28ea6b8625f4d494f7073c54f79bf94540061a7520d70e57b4ddd7da5754"},"schema_version":"1.0"},"canonical_sha256":"a3fb586b515e78af3b34d3b529d2f6d6416d85e0997e66084ef0f0d8dc8adaf5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:37.399635Z","signature_b64":"kGE8Y3kZ32ATBENc1UUWSJQoCWUdZe6y2p3ePZy4ArXQ5X4EiPHbyM/+TbhtggcvHqRrYzg9HfOo2wJDwFuoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3fb586b515e78af3b34d3b529d2f6d6416d85e0997e66084ef0f0d8dc8adaf5","last_reissued_at":"2026-07-05T09:11:37.399156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:37.399156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.16654","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":"2026-07-05T09:11:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bkzogIDqn8I9II8lqEO4NnmScizGxk4HIuSxqjRF8XaYYQoIQR8C7fxWMD2YletBMPmk1tRdm/VBc+Br7ydTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T16:04:59.016924Z"},"content_sha256":"a23470eb5b9844889941610c65e2eedf140b5a56f0ce0f94ae95ccc460c8050b","schema_version":"1.0","event_id":"sha256:a23470eb5b9844889941610c65e2eedf140b5a56f0ce0f94ae95ccc460c8050b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UP5VQ22RLZ4K6OZU2O2STUXW2Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speech Recognition Rescoring with Large Speech-Text Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Aditya Gourav, Ankur Gandhe, Ariya Rastrow, Ivan Bulyko, Jari Kolehmainen, Prashanth Gurunath Shivakumar, Yi Gu","submitted_at":"2024-09-25T06:17:23Z","abstract_excerpt":"Large language models (LLM) have demonstrated the ability to understand human language by leveraging large amount of text data. Automatic speech recognition (ASR) systems are often limited by available transcribed speech data and benefit from a second pass rescoring using LLM. Recently multi-modal large language models, particularly speech and text foundational models have demonstrated strong spoken language understanding. Speech-Text foundational models leverage large amounts of unlabelled and labelled data both in speech and text modalities to model human language. In this work, we propose n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16654","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/2409.16654/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":"2026-07-05T09:11:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"95NREbPrmo2ui7KmZGxf/h/TW/kFMnec9BKASU0XITqhKyy8IweTZqmpG3jR8FLzcYel7phRRYYNUNlO9msjCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T16:04:59.017264Z"},"content_sha256":"7ce396eb4224a5b93ce7ed5fdcfbb32682a363b68bb73d40c1d6f42952a9fd8b","schema_version":"1.0","event_id":"sha256:7ce396eb4224a5b93ce7ed5fdcfbb32682a363b68bb73d40c1d6f42952a9fd8b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UP5VQ22RLZ4K6OZU2O2STUXW2Z/bundle.json","state_url":"https://pith.science/pith/UP5VQ22RLZ4K6OZU2O2STUXW2Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UP5VQ22RLZ4K6OZU2O2STUXW2Z/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":"2026-08-23T16:04:59Z","links":{"resolver":"https://pith.science/pith/UP5VQ22RLZ4K6OZU2O2STUXW2Z","bundle":"https://pith.science/pith/UP5VQ22RLZ4K6OZU2O2STUXW2Z/bundle.json","state":"https://pith.science/pith/UP5VQ22RLZ4K6OZU2O2STUXW2Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UP5VQ22RLZ4K6OZU2O2STUXW2Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UP5VQ22RLZ4K6OZU2O2STUXW2Z","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":"17ce28ea6b8625f4d494f7073c54f79bf94540061a7520d70e57b4ddd7da5754","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-25T06:17:23Z","title_canon_sha256":"3c94de0056965005222730aac867682ab6638a383161ef0d3422320e067bd427"},"schema_version":"1.0","source":{"id":"2409.16654","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.16654","created_at":"2026-07-05T09:11:37Z"},{"alias_kind":"arxiv_version","alias_value":"2409.16654v1","created_at":"2026-07-05T09:11:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16654","created_at":"2026-07-05T09:11:37Z"},{"alias_kind":"pith_short_12","alias_value":"UP5VQ22RLZ4K","created_at":"2026-07-05T09:11:37Z"},{"alias_kind":"pith_short_16","alias_value":"UP5VQ22RLZ4K6OZU","created_at":"2026-07-05T09:11:37Z"},{"alias_kind":"pith_short_8","alias_value":"UP5VQ22R","created_at":"2026-07-05T09:11:37Z"}],"graph_snapshots":[{"event_id":"sha256:7ce396eb4224a5b93ce7ed5fdcfbb32682a363b68bb73d40c1d6f42952a9fd8b","target":"graph","created_at":"2026-07-05T09:11:37Z","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/2409.16654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLM) have demonstrated the ability to understand human language by leveraging large amount of text data. Automatic speech recognition (ASR) systems are often limited by available transcribed speech data and benefit from a second pass rescoring using LLM. Recently multi-modal large language models, particularly speech and text foundational models have demonstrated strong spoken language understanding. Speech-Text foundational models leverage large amounts of unlabelled and labelled data both in speech and text modalities to model human language. In this work, we propose n","authors_text":"Aditya Gourav, Ankur Gandhe, Ariya Rastrow, Ivan Bulyko, Jari Kolehmainen, Prashanth Gurunath Shivakumar, Yi Gu","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-25T06:17:23Z","title":"Speech Recognition Rescoring with Large Speech-Text Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16654","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:a23470eb5b9844889941610c65e2eedf140b5a56f0ce0f94ae95ccc460c8050b","target":"record","created_at":"2026-07-05T09:11:37Z","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":"17ce28ea6b8625f4d494f7073c54f79bf94540061a7520d70e57b4ddd7da5754","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-25T06:17:23Z","title_canon_sha256":"3c94de0056965005222730aac867682ab6638a383161ef0d3422320e067bd427"},"schema_version":"1.0","source":{"id":"2409.16654","kind":"arxiv","version":1}},"canonical_sha256":"a3fb586b515e78af3b34d3b529d2f6d6416d85e0997e66084ef0f0d8dc8adaf5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3fb586b515e78af3b34d3b529d2f6d6416d85e0997e66084ef0f0d8dc8adaf5","first_computed_at":"2026-07-05T09:11:37.399156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:11:37.399156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kGE8Y3kZ32ATBENc1UUWSJQoCWUdZe6y2p3ePZy4ArXQ5X4EiPHbyM/+TbhtggcvHqRrYzg9HfOo2wJDwFuoDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:11:37.399635Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.16654","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a23470eb5b9844889941610c65e2eedf140b5a56f0ce0f94ae95ccc460c8050b","sha256:7ce396eb4224a5b93ce7ed5fdcfbb32682a363b68bb73d40c1d6f42952a9fd8b"],"state_sha256":"2799eb175d25874f3f840c818f786265ccd460adb9860e8dc8f30570865eb72e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tFzFYMoNbYVGtwFhSlVrp14tCsREThWpX5TM/jvgXfh/1tva3nOH7whjhwGBZsveA8bSj25GKMGTo9CG4KTmAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T16:04:59.021237Z","bundle_sha256":"b9e368f596c88bdbd94a8f1717fe5f67335aa4e9d497bb069a5f1789cd193fc8"}}