{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Y43AAPGICGXLF4RNSDVDCRXGIC","short_pith_number":"pith:Y43AAPGI","canonical_record":{"source":{"id":"2506.23714","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T10:41:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"083b16c083f88b25a0cb5ab82100be7055aa9c9165dd03e182b8e07829fe988f","abstract_canon_sha256":"14407a84f41f8dc7784e34a869523cc5fae46f68453c85ce726c70d017414dd9"},"schema_version":"1.0"},"canonical_sha256":"c736003cc811aeb2f22d90ea3146e6408f55cb1668b4388b88bc346fbc4e8876","source":{"kind":"arxiv","id":"2506.23714","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23714","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23714v1","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23714","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"pith_short_12","alias_value":"Y43AAPGICGXL","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"pith_short_16","alias_value":"Y43AAPGICGXLF4RN","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"pith_short_8","alias_value":"Y43AAPGI","created_at":"2026-07-05T11:29:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Y43AAPGICGXLF4RNSDVDCRXGIC","target":"record","payload":{"canonical_record":{"source":{"id":"2506.23714","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T10:41:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"083b16c083f88b25a0cb5ab82100be7055aa9c9165dd03e182b8e07829fe988f","abstract_canon_sha256":"14407a84f41f8dc7784e34a869523cc5fae46f68453c85ce726c70d017414dd9"},"schema_version":"1.0"},"canonical_sha256":"c736003cc811aeb2f22d90ea3146e6408f55cb1668b4388b88bc346fbc4e8876","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:26.949514Z","signature_b64":"b7noJZeFfSiTBMfanXKGyoCy3IF7MW7+5ZgeBRn3EB+FkWg/qUcam32IGq2Tg98Gn3PUOCq3gzw4/c8rruPODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c736003cc811aeb2f22d90ea3146e6408f55cb1668b4388b88bc346fbc4e8876","last_reissued_at":"2026-07-05T11:29:26.949033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:26.949033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.23714","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":"2026-07-05T11:29:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EZh3dY466VBHoFjaHQbc+ccZhGvRzUW8Th2QNfL1PXgdob5NR2krBu4PfCX3Dvk+rZN5JafgDYV3XeaRDor9AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:42:33.845963Z"},"content_sha256":"5655674f285a9e6477534ecfd772aa32ee1ca780306c81578dd00aefabce5041","schema_version":"1.0","event_id":"sha256:5655674f285a9e6477534ecfd772aa32ee1ca780306c81578dd00aefabce5041"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Y43AAPGICGXLF4RNSDVDCRXGIC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards an Automated Multimodal Approach for Video Summarization: Building a Bridge Between Text, Audio and Facial Cue-Based Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Janne Heikkil\\\"a, Md Moinul Islam, Mourad Oussalah, Sofoklis Kakouros","submitted_at":"2025-06-30T10:41:33Z","abstract_excerpt":"The increasing volume of video content in educational, professional, and social domains necessitates effective summarization techniques that go beyond traditional unimodal approaches. This paper proposes a behaviour-aware multimodal video summarization framework that integrates textual, audio, and visual cues to generate timestamp-aligned summaries. By extracting prosodic features, textual cues and visual indicators, the framework identifies semantically and emotionally important moments. A key contribution is the identification of bonus words, which are terms emphasized across multiple modali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23714","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/2506.23714/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":"2026-07-05T11:29:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fuCnvca54Y78Q+3YrJLhTrlDeELKJ3ja8tsC51gOp72lWwcfcxRGHoZd59OO1J2i3RU127eyd5Sg3jFxI9FSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:42:33.846498Z"},"content_sha256":"df1b0f921786d64155a03aff39054559d84fc0693aa4c087520fb758de68f448","schema_version":"1.0","event_id":"sha256:df1b0f921786d64155a03aff39054559d84fc0693aa4c087520fb758de68f448"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y43AAPGICGXLF4RNSDVDCRXGIC/bundle.json","state_url":"https://pith.science/pith/Y43AAPGICGXLF4RNSDVDCRXGIC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y43AAPGICGXLF4RNSDVDCRXGIC/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":"2026-08-09T03:42:33Z","links":{"resolver":"https://pith.science/pith/Y43AAPGICGXLF4RNSDVDCRXGIC","bundle":"https://pith.science/pith/Y43AAPGICGXLF4RNSDVDCRXGIC/bundle.json","state":"https://pith.science/pith/Y43AAPGICGXLF4RNSDVDCRXGIC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y43AAPGICGXLF4RNSDVDCRXGIC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y43AAPGICGXLF4RNSDVDCRXGIC","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":"14407a84f41f8dc7784e34a869523cc5fae46f68453c85ce726c70d017414dd9","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T10:41:33Z","title_canon_sha256":"083b16c083f88b25a0cb5ab82100be7055aa9c9165dd03e182b8e07829fe988f"},"schema_version":"1.0","source":{"id":"2506.23714","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23714","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23714v1","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23714","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"pith_short_12","alias_value":"Y43AAPGICGXL","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"pith_short_16","alias_value":"Y43AAPGICGXLF4RN","created_at":"2026-07-05T11:29:26Z"},{"alias_kind":"pith_short_8","alias_value":"Y43AAPGI","created_at":"2026-07-05T11:29:26Z"}],"graph_snapshots":[{"event_id":"sha256:df1b0f921786d64155a03aff39054559d84fc0693aa4c087520fb758de68f448","target":"graph","created_at":"2026-07-05T11:29:26Z","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/2506.23714/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasing volume of video content in educational, professional, and social domains necessitates effective summarization techniques that go beyond traditional unimodal approaches. This paper proposes a behaviour-aware multimodal video summarization framework that integrates textual, audio, and visual cues to generate timestamp-aligned summaries. By extracting prosodic features, textual cues and visual indicators, the framework identifies semantically and emotionally important moments. A key contribution is the identification of bonus words, which are terms emphasized across multiple modali","authors_text":"Janne Heikkil\\\"a, Md Moinul Islam, Mourad Oussalah, Sofoklis Kakouros","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T10:41:33Z","title":"Towards an Automated Multimodal Approach for Video Summarization: Building a Bridge Between Text, Audio and Facial Cue-Based Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23714","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":"sha256:5655674f285a9e6477534ecfd772aa32ee1ca780306c81578dd00aefabce5041","target":"record","created_at":"2026-07-05T11:29:26Z","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":"14407a84f41f8dc7784e34a869523cc5fae46f68453c85ce726c70d017414dd9","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T10:41:33Z","title_canon_sha256":"083b16c083f88b25a0cb5ab82100be7055aa9c9165dd03e182b8e07829fe988f"},"schema_version":"1.0","source":{"id":"2506.23714","kind":"arxiv","version":1}},"canonical_sha256":"c736003cc811aeb2f22d90ea3146e6408f55cb1668b4388b88bc346fbc4e8876","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c736003cc811aeb2f22d90ea3146e6408f55cb1668b4388b88bc346fbc4e8876","first_computed_at":"2026-07-05T11:29:26.949033Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:26.949033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b7noJZeFfSiTBMfanXKGyoCy3IF7MW7+5ZgeBRn3EB+FkWg/qUcam32IGq2Tg98Gn3PUOCq3gzw4/c8rruPODg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:26.949514Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23714","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5655674f285a9e6477534ecfd772aa32ee1ca780306c81578dd00aefabce5041","sha256:df1b0f921786d64155a03aff39054559d84fc0693aa4c087520fb758de68f448"],"state_sha256":"d391f851e09468081894e268c531a687217239bf3c2b3a7abf8788889fdfdd5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OkFxLJ4Ll0khsEMEbWvKhWDO0jtuCFzf54rnDyOBmumaIAxpflQG5qLeqy7GBEDfUg8F6M7iilXIQlVmJhwMCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:42:33.852392Z","bundle_sha256":"3291a284827fea0ac7102a43e2ef1ecf218a1211c5801bf904a3eb94489b57d4"}}