{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4WHD46EDB5RMU2BCVXS2GCCXND","short_pith_number":"pith:4WHD46ED","canonical_record":{"source":{"id":"2401.09759","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-18T07:19:10Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"fac47cbe64b723854a234079e4848c32240524af66beb31fa3267aeb456c7827","abstract_canon_sha256":"5bd7ed82ffca6def499e00eadd97f23d06aa86ef77b5c90eeae153a6d8a66067"},"schema_version":"1.0"},"canonical_sha256":"e58e3e78830f62ca6822ade5a3085768f88cad54666796bb48801a01bba2cf18","source":{"kind":"arxiv","id":"2401.09759","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.09759","created_at":"2026-07-05T08:38:56Z"},{"alias_kind":"arxiv_version","alias_value":"2401.09759v2","created_at":"2026-07-05T08:38:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09759","created_at":"2026-07-05T08:38:56Z"},{"alias_kind":"pith_short_12","alias_value":"4WHD46EDB5RM","created_at":"2026-07-05T08:38:56Z"},{"alias_kind":"pith_short_16","alias_value":"4WHD46EDB5RMU2BC","created_at":"2026-07-05T08:38:56Z"},{"alias_kind":"pith_short_8","alias_value":"4WHD46ED","created_at":"2026-07-05T08:38:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4WHD46EDB5RMU2BCVXS2GCCXND","target":"record","payload":{"canonical_record":{"source":{"id":"2401.09759","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-18T07:19:10Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"fac47cbe64b723854a234079e4848c32240524af66beb31fa3267aeb456c7827","abstract_canon_sha256":"5bd7ed82ffca6def499e00eadd97f23d06aa86ef77b5c90eeae153a6d8a66067"},"schema_version":"1.0"},"canonical_sha256":"e58e3e78830f62ca6822ade5a3085768f88cad54666796bb48801a01bba2cf18","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:56.774043Z","signature_b64":"kNYxzRr7BRHpBiHbAfL7KG8Q+tX7B5bCGxz7/FrqSg7kelqkdAEO2sqlG559VPD2tpUOSXK1FMasxV+mnbkACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e58e3e78830f62ca6822ade5a3085768f88cad54666796bb48801a01bba2cf18","last_reissued_at":"2026-07-05T08:38:56.773527Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:56.773527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.09759","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:38:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pe9bAwFlr147aQqil/1W7V9GDKJiUdnaQGjME8jNwMkl3Wy5D8FOKuA9ol1/BZpPzso6JlC92dqyGwzHZ1k2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:17:32.829591Z"},"content_sha256":"691f2a9a7475b3cd7d7ce0932c9f0ed9f2f11a305571ef589ac522507e2fdc01","schema_version":"1.0","event_id":"sha256:691f2a9a7475b3cd7d7ce0932c9f0ed9f2f11a305571ef589ac522507e2fdc01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4WHD46EDB5RMU2BCVXS2GCCXND","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SlideAVSR: A Dataset of Paper Explanation Videos for Audio-Visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Daisuke Kawahara, Hao Wang, Shuhei Kurita, Shuichiro Shimizu","submitted_at":"2024-01-18T07:19:10Z","abstract_excerpt":"Audio-visual speech recognition (AVSR) is a multimodal extension of automatic speech recognition (ASR), using video as a complement to audio. In AVSR, considerable efforts have been directed at datasets for facial features such as lip-readings, while they often fall short in evaluating the image comprehension capabilities in broader contexts. In this paper, we construct SlideAVSR, an AVSR dataset using scientific paper explanation videos. SlideAVSR provides a new benchmark where models transcribe speech utterances with texts on the slides on the presentation recordings. As technical terminolog"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09759","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/2401.09759/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":"2026-07-05T08:38:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xyOjokH701/NsXQJS9060DJzxZEzBuOgfNs0Ru57xjdNGQWeHGYX/ArmMPBc7859lCz8VlTNl9feCWyv9mn2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:17:32.830083Z"},"content_sha256":"df4381b01eceab488983d99d24a5c3d2c827a8bd47804db9ca4868bf059ed84f","schema_version":"1.0","event_id":"sha256:df4381b01eceab488983d99d24a5c3d2c827a8bd47804db9ca4868bf059ed84f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4WHD46EDB5RMU2BCVXS2GCCXND/bundle.json","state_url":"https://pith.science/pith/4WHD46EDB5RMU2BCVXS2GCCXND/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4WHD46EDB5RMU2BCVXS2GCCXND/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":"2026-08-06T06:17:32Z","links":{"resolver":"https://pith.science/pith/4WHD46EDB5RMU2BCVXS2GCCXND","bundle":"https://pith.science/pith/4WHD46EDB5RMU2BCVXS2GCCXND/bundle.json","state":"https://pith.science/pith/4WHD46EDB5RMU2BCVXS2GCCXND/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4WHD46EDB5RMU2BCVXS2GCCXND/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4WHD46EDB5RMU2BCVXS2GCCXND","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":"5bd7ed82ffca6def499e00eadd97f23d06aa86ef77b5c90eeae153a6d8a66067","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-18T07:19:10Z","title_canon_sha256":"fac47cbe64b723854a234079e4848c32240524af66beb31fa3267aeb456c7827"},"schema_version":"1.0","source":{"id":"2401.09759","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.09759","created_at":"2026-07-05T08:38:56Z"},{"alias_kind":"arxiv_version","alias_value":"2401.09759v2","created_at":"2026-07-05T08:38:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09759","created_at":"2026-07-05T08:38:56Z"},{"alias_kind":"pith_short_12","alias_value":"4WHD46EDB5RM","created_at":"2026-07-05T08:38:56Z"},{"alias_kind":"pith_short_16","alias_value":"4WHD46EDB5RMU2BC","created_at":"2026-07-05T08:38:56Z"},{"alias_kind":"pith_short_8","alias_value":"4WHD46ED","created_at":"2026-07-05T08:38:56Z"}],"graph_snapshots":[{"event_id":"sha256:df4381b01eceab488983d99d24a5c3d2c827a8bd47804db9ca4868bf059ed84f","target":"graph","created_at":"2026-07-05T08:38:56Z","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/2401.09759/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual speech recognition (AVSR) is a multimodal extension of automatic speech recognition (ASR), using video as a complement to audio. In AVSR, considerable efforts have been directed at datasets for facial features such as lip-readings, while they often fall short in evaluating the image comprehension capabilities in broader contexts. In this paper, we construct SlideAVSR, an AVSR dataset using scientific paper explanation videos. SlideAVSR provides a new benchmark where models transcribe speech utterances with texts on the slides on the presentation recordings. As technical terminolog","authors_text":"Daisuke Kawahara, Hao Wang, Shuhei Kurita, Shuichiro Shimizu","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-18T07:19:10Z","title":"SlideAVSR: A Dataset of Paper Explanation Videos for Audio-Visual Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09759","kind":"arxiv","version":2},"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":"sha256:691f2a9a7475b3cd7d7ce0932c9f0ed9f2f11a305571ef589ac522507e2fdc01","target":"record","created_at":"2026-07-05T08:38:56Z","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":"5bd7ed82ffca6def499e00eadd97f23d06aa86ef77b5c90eeae153a6d8a66067","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-18T07:19:10Z","title_canon_sha256":"fac47cbe64b723854a234079e4848c32240524af66beb31fa3267aeb456c7827"},"schema_version":"1.0","source":{"id":"2401.09759","kind":"arxiv","version":2}},"canonical_sha256":"e58e3e78830f62ca6822ade5a3085768f88cad54666796bb48801a01bba2cf18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e58e3e78830f62ca6822ade5a3085768f88cad54666796bb48801a01bba2cf18","first_computed_at":"2026-07-05T08:38:56.773527Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:56.773527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kNYxzRr7BRHpBiHbAfL7KG8Q+tX7B5bCGxz7/FrqSg7kelqkdAEO2sqlG559VPD2tpUOSXK1FMasxV+mnbkACg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:56.774043Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.09759","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:691f2a9a7475b3cd7d7ce0932c9f0ed9f2f11a305571ef589ac522507e2fdc01","sha256:df4381b01eceab488983d99d24a5c3d2c827a8bd47804db9ca4868bf059ed84f"],"state_sha256":"b330e498ec73a24b94f4596762f2d174f6095ee98acd4cb1198cf27f82387ba3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0+AS9k5X1r4dxcJT98QUj8lvdHN8JjRfxiA7uZohdi+CunY29zKta2vsevZ4ZwnzRu3uEYPCIJRUPXsxq5h2Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:17:32.834151Z","bundle_sha256":"6380d22379ee6051c5aa4fb418427b757d528e8970dbdf0a989b312cdb3f7a6f"}}