{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NGUR4YJ3N5LX64REA55PZEH6TL","short_pith_number":"pith:NGUR4YJ3","canonical_record":{"source":{"id":"2407.02005","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T07:22:57Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"fbbd610adb396e4c1a015c46820db9017677984187b16e406c9f54bfec9be175","abstract_canon_sha256":"e4f67d1a0691d17ea3d06a4879e7bfab0567ff40a17e7f8d35cde8ecb9ff620f"},"schema_version":"1.0"},"canonical_sha256":"69a91e613b6f577f7224077afc90fe9ace6133c37ca17d1b7a9cec6eb31bd163","source":{"kind":"arxiv","id":"2407.02005","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02005","created_at":"2026-07-05T08:39:08Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02005v1","created_at":"2026-07-05T08:39:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02005","created_at":"2026-07-05T08:39:08Z"},{"alias_kind":"pith_short_12","alias_value":"NGUR4YJ3N5LX","created_at":"2026-07-05T08:39:08Z"},{"alias_kind":"pith_short_16","alias_value":"NGUR4YJ3N5LX64RE","created_at":"2026-07-05T08:39:08Z"},{"alias_kind":"pith_short_8","alias_value":"NGUR4YJ3","created_at":"2026-07-05T08:39:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NGUR4YJ3N5LX64REA55PZEH6TL","target":"record","payload":{"canonical_record":{"source":{"id":"2407.02005","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T07:22:57Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"fbbd610adb396e4c1a015c46820db9017677984187b16e406c9f54bfec9be175","abstract_canon_sha256":"e4f67d1a0691d17ea3d06a4879e7bfab0567ff40a17e7f8d35cde8ecb9ff620f"},"schema_version":"1.0"},"canonical_sha256":"69a91e613b6f577f7224077afc90fe9ace6133c37ca17d1b7a9cec6eb31bd163","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:08.498627Z","signature_b64":"NeEvKLpZYu4qhgb4v6lugTU1e4BF0Y/w3ZhvbWV+o8EluQEx+JjC1BNkm2vhpAkDcdqvcoQax7R3O667hDAVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69a91e613b6f577f7224077afc90fe9ace6133c37ca17d1b7a9cec6eb31bd163","last_reissued_at":"2026-07-05T08:39:08.498161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:08.498161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.02005","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":"2026-07-05T08:39:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C9fvd6UBPUk086jJRODj6U4OHx05b2dBVAUWBrhfmYRMjbenaEY0CjTASsycx8XO6aLNjXGXEJCT+aX8SpfxAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:25:55.944293Z"},"content_sha256":"a30cea13645ca85da29b7f7995eff43c6930982fb66abc7d94421d56f52ddacf","schema_version":"1.0","event_id":"sha256:a30cea13645ca85da29b7f7995eff43c6930982fb66abc7d94421d56f52ddacf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NGUR4YJ3N5LX64REA55PZEH6TL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An End-to-End Speech Summarization Using Large Language Model","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Daimeng Wei, Hao Yang, Hengchao Shang, Jiaxin Guo, Shaojun Li, Yuanchang Luo, Zhiqiang Rao, Zongyao Li","submitted_at":"2024-07-02T07:22:57Z","abstract_excerpt":"Abstractive Speech Summarization (SSum) aims to generate human-like text summaries from spoken content. It encounters difficulties in handling long speech input and capturing the intricate cross-modal mapping between long speech inputs and short text summaries. Research on large language models (LLMs) and multimodal information fusion has provided new insights for addressing these challenges. In this paper, we propose an end-to-end SSum model that utilizes Q-Former as a connector for the audio-text modality and employs LLMs to generate text summaries directly from speech features. We adopt a m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02005","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/2407.02005/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":"2026-07-05T08:39:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O/Olkho6TI76v/SI0hgWe1unjvfQoEbuJ8xtGF0ZpxvktrVfs0Nre0Xkf33OQ1wFTgcMLCjJCqE8Ydk55COUCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:25:55.945384Z"},"content_sha256":"465f72bdbd6047de69da0ea6c8dd586c76cd2e3f9de5ccb66b9e8c171a8aee83","schema_version":"1.0","event_id":"sha256:465f72bdbd6047de69da0ea6c8dd586c76cd2e3f9de5ccb66b9e8c171a8aee83"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NGUR4YJ3N5LX64REA55PZEH6TL/bundle.json","state_url":"https://pith.science/pith/NGUR4YJ3N5LX64REA55PZEH6TL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NGUR4YJ3N5LX64REA55PZEH6TL/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":"2026-08-03T19:25:55Z","links":{"resolver":"https://pith.science/pith/NGUR4YJ3N5LX64REA55PZEH6TL","bundle":"https://pith.science/pith/NGUR4YJ3N5LX64REA55PZEH6TL/bundle.json","state":"https://pith.science/pith/NGUR4YJ3N5LX64REA55PZEH6TL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NGUR4YJ3N5LX64REA55PZEH6TL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NGUR4YJ3N5LX64REA55PZEH6TL","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":"e4f67d1a0691d17ea3d06a4879e7bfab0567ff40a17e7f8d35cde8ecb9ff620f","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T07:22:57Z","title_canon_sha256":"fbbd610adb396e4c1a015c46820db9017677984187b16e406c9f54bfec9be175"},"schema_version":"1.0","source":{"id":"2407.02005","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02005","created_at":"2026-07-05T08:39:08Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02005v1","created_at":"2026-07-05T08:39:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02005","created_at":"2026-07-05T08:39:08Z"},{"alias_kind":"pith_short_12","alias_value":"NGUR4YJ3N5LX","created_at":"2026-07-05T08:39:08Z"},{"alias_kind":"pith_short_16","alias_value":"NGUR4YJ3N5LX64RE","created_at":"2026-07-05T08:39:08Z"},{"alias_kind":"pith_short_8","alias_value":"NGUR4YJ3","created_at":"2026-07-05T08:39:08Z"}],"graph_snapshots":[{"event_id":"sha256:465f72bdbd6047de69da0ea6c8dd586c76cd2e3f9de5ccb66b9e8c171a8aee83","target":"graph","created_at":"2026-07-05T08:39:08Z","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/2407.02005/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Abstractive Speech Summarization (SSum) aims to generate human-like text summaries from spoken content. It encounters difficulties in handling long speech input and capturing the intricate cross-modal mapping between long speech inputs and short text summaries. Research on large language models (LLMs) and multimodal information fusion has provided new insights for addressing these challenges. In this paper, we propose an end-to-end SSum model that utilizes Q-Former as a connector for the audio-text modality and employs LLMs to generate text summaries directly from speech features. We adopt a m","authors_text":"Daimeng Wei, Hao Yang, Hengchao Shang, Jiaxin Guo, Shaojun Li, Yuanchang Luo, Zhiqiang Rao, Zongyao Li","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T07:22:57Z","title":"An End-to-End Speech Summarization Using Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02005","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:a30cea13645ca85da29b7f7995eff43c6930982fb66abc7d94421d56f52ddacf","target":"record","created_at":"2026-07-05T08:39:08Z","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":"e4f67d1a0691d17ea3d06a4879e7bfab0567ff40a17e7f8d35cde8ecb9ff620f","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T07:22:57Z","title_canon_sha256":"fbbd610adb396e4c1a015c46820db9017677984187b16e406c9f54bfec9be175"},"schema_version":"1.0","source":{"id":"2407.02005","kind":"arxiv","version":1}},"canonical_sha256":"69a91e613b6f577f7224077afc90fe9ace6133c37ca17d1b7a9cec6eb31bd163","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69a91e613b6f577f7224077afc90fe9ace6133c37ca17d1b7a9cec6eb31bd163","first_computed_at":"2026-07-05T08:39:08.498161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:08.498161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NeEvKLpZYu4qhgb4v6lugTU1e4BF0Y/w3ZhvbWV+o8EluQEx+JjC1BNkm2vhpAkDcdqvcoQax7R3O667hDAVDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:08.498627Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02005","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a30cea13645ca85da29b7f7995eff43c6930982fb66abc7d94421d56f52ddacf","sha256:465f72bdbd6047de69da0ea6c8dd586c76cd2e3f9de5ccb66b9e8c171a8aee83"],"state_sha256":"49ea6a1bf08cc58cb9e971a2575c0e41bf360e0caf2e27cca780dcdf538237e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tEZp0G8kSo+LQv0K9k4thPsMsi8eS4RYVOnMk5nnjNtDHA8ef6cL3Imy30WcIaJquYS/Wv+qXCuOLijyQxsoAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:25:55.952669Z","bundle_sha256":"780f85c1439a42efdb349c6c83c572f255e2c2f8ff2d2377da67b5c5d8ecf5b4"}}