{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:S3NQW7BN3LSYDYNN3C6QMMBYLA","short_pith_number":"pith:S3NQW7BN","canonical_record":{"source":{"id":"2306.09947","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-16T16:28:03Z","cross_cats_sorted":[],"title_canon_sha256":"dc741328c19f94fd4eca3c298e777347f87aa932004af38a0c05623fcee39721","abstract_canon_sha256":"e86eed6788fb238320a9839a353fd34725da4d80af482c0dda42c417ec9d0ec1"},"schema_version":"1.0"},"canonical_sha256":"96db0b7c2ddae581e1add8bd0630385812861614ca989baf401245fb5439508f","source":{"kind":"arxiv","id":"2306.09947","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09947","created_at":"2026-07-05T06:21:25Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09947v1","created_at":"2026-07-05T06:21:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09947","created_at":"2026-07-05T06:21:25Z"},{"alias_kind":"pith_short_12","alias_value":"S3NQW7BN3LSY","created_at":"2026-07-05T06:21:25Z"},{"alias_kind":"pith_short_16","alias_value":"S3NQW7BN3LSYDYNN","created_at":"2026-07-05T06:21:25Z"},{"alias_kind":"pith_short_8","alias_value":"S3NQW7BN","created_at":"2026-07-05T06:21:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:S3NQW7BN3LSYDYNN3C6QMMBYLA","target":"record","payload":{"canonical_record":{"source":{"id":"2306.09947","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-16T16:28:03Z","cross_cats_sorted":[],"title_canon_sha256":"dc741328c19f94fd4eca3c298e777347f87aa932004af38a0c05623fcee39721","abstract_canon_sha256":"e86eed6788fb238320a9839a353fd34725da4d80af482c0dda42c417ec9d0ec1"},"schema_version":"1.0"},"canonical_sha256":"96db0b7c2ddae581e1add8bd0630385812861614ca989baf401245fb5439508f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:25.805117Z","signature_b64":"+NPhKCtaxbOyJpMIRCmFf2USQmTXhw1oc7MmZ1bvivNFEFAlCcLVSHwFc5dU9+IB5JTzK77/ugmFuVLECxZpBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96db0b7c2ddae581e1add8bd0630385812861614ca989baf401245fb5439508f","last_reissued_at":"2026-07-05T06:21:25.804555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:25.804555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.09947","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":"2026-07-05T06:21:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8PqxpcFh2o4XQ/DPqqThuu63fTMvUP4+8pPYBPVeDhbbIfEfLa9D512oGnGPRERUFVcafe9gtt3OjMDL7xqhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:27:29.521096Z"},"content_sha256":"2eb6c6245b2ce75860f0dd3c789678af2cbff77a7bf8039aeb16674f7005b41e","schema_version":"1.0","event_id":"sha256:2eb6c6245b2ce75860f0dd3c789678af2cbff77a7bf8039aeb16674f7005b41e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:S3NQW7BN3LSYDYNN3C6QMMBYLA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Knowledge Distillation for Efficient Audio-Visual Video Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"\\\"Ozkan \\c{C}ayl{\\i}, Volkan K{\\i}l{\\i}\\c{c}, Wenwu Wang, Xubo Liu","submitted_at":"2023-06-16T16:28:03Z","abstract_excerpt":"Automatically describing audio-visual content with texts, namely video captioning, has received significant attention due to its potential applications across diverse fields. Deep neural networks are the dominant methods, offering state-of-the-art performance. However, these methods are often undeployable in low-power devices like smartphones due to the large size of the model parameters. In this paper, we propose to exploit simple pooling front-end and down-sampling algorithms with knowledge distillation for audio and visual attributes using a reduced number of audio-visual frames. With the h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09947","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/2306.09947/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":"2026-07-05T06:21:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VDIw1CoqZBAljTM1KGXb3estK8QJF/eoySJEJZg3NRxKXbbs43//oGMR31nCaN3KtOVkmCA8qSBAeGv1f5lZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:27:29.521618Z"},"content_sha256":"021d7305116ea8667d38295e0259cda1f063db72716b51a38fedc6687410b0a1","schema_version":"1.0","event_id":"sha256:021d7305116ea8667d38295e0259cda1f063db72716b51a38fedc6687410b0a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S3NQW7BN3LSYDYNN3C6QMMBYLA/bundle.json","state_url":"https://pith.science/pith/S3NQW7BN3LSYDYNN3C6QMMBYLA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S3NQW7BN3LSYDYNN3C6QMMBYLA/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":"2026-08-03T16:27:29Z","links":{"resolver":"https://pith.science/pith/S3NQW7BN3LSYDYNN3C6QMMBYLA","bundle":"https://pith.science/pith/S3NQW7BN3LSYDYNN3C6QMMBYLA/bundle.json","state":"https://pith.science/pith/S3NQW7BN3LSYDYNN3C6QMMBYLA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S3NQW7BN3LSYDYNN3C6QMMBYLA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:S3NQW7BN3LSYDYNN3C6QMMBYLA","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":"e86eed6788fb238320a9839a353fd34725da4d80af482c0dda42c417ec9d0ec1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-16T16:28:03Z","title_canon_sha256":"dc741328c19f94fd4eca3c298e777347f87aa932004af38a0c05623fcee39721"},"schema_version":"1.0","source":{"id":"2306.09947","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.09947","created_at":"2026-07-05T06:21:25Z"},{"alias_kind":"arxiv_version","alias_value":"2306.09947v1","created_at":"2026-07-05T06:21:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09947","created_at":"2026-07-05T06:21:25Z"},{"alias_kind":"pith_short_12","alias_value":"S3NQW7BN3LSY","created_at":"2026-07-05T06:21:25Z"},{"alias_kind":"pith_short_16","alias_value":"S3NQW7BN3LSYDYNN","created_at":"2026-07-05T06:21:25Z"},{"alias_kind":"pith_short_8","alias_value":"S3NQW7BN","created_at":"2026-07-05T06:21:25Z"}],"graph_snapshots":[{"event_id":"sha256:021d7305116ea8667d38295e0259cda1f063db72716b51a38fedc6687410b0a1","target":"graph","created_at":"2026-07-05T06:21:25Z","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/2306.09947/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatically describing audio-visual content with texts, namely video captioning, has received significant attention due to its potential applications across diverse fields. Deep neural networks are the dominant methods, offering state-of-the-art performance. However, these methods are often undeployable in low-power devices like smartphones due to the large size of the model parameters. In this paper, we propose to exploit simple pooling front-end and down-sampling algorithms with knowledge distillation for audio and visual attributes using a reduced number of audio-visual frames. With the h","authors_text":"\\\"Ozkan \\c{C}ayl{\\i}, Volkan K{\\i}l{\\i}\\c{c}, Wenwu Wang, Xubo Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-16T16:28:03Z","title":"Knowledge Distillation for Efficient Audio-Visual Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09947","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":"sha256:2eb6c6245b2ce75860f0dd3c789678af2cbff77a7bf8039aeb16674f7005b41e","target":"record","created_at":"2026-07-05T06:21:25Z","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":"e86eed6788fb238320a9839a353fd34725da4d80af482c0dda42c417ec9d0ec1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-16T16:28:03Z","title_canon_sha256":"dc741328c19f94fd4eca3c298e777347f87aa932004af38a0c05623fcee39721"},"schema_version":"1.0","source":{"id":"2306.09947","kind":"arxiv","version":1}},"canonical_sha256":"96db0b7c2ddae581e1add8bd0630385812861614ca989baf401245fb5439508f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96db0b7c2ddae581e1add8bd0630385812861614ca989baf401245fb5439508f","first_computed_at":"2026-07-05T06:21:25.804555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:21:25.804555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+NPhKCtaxbOyJpMIRCmFf2USQmTXhw1oc7MmZ1bvivNFEFAlCcLVSHwFc5dU9+IB5JTzK77/ugmFuVLECxZpBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:21:25.805117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.09947","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2eb6c6245b2ce75860f0dd3c789678af2cbff77a7bf8039aeb16674f7005b41e","sha256:021d7305116ea8667d38295e0259cda1f063db72716b51a38fedc6687410b0a1"],"state_sha256":"e524d5144b57d2ae175363884f6c5ba23fdcb7a39226325daff81a3a82592603"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lhu35nAM9yb3aaLl0Ays23k2nAYthxa28WX3Owk0l1IWZzxSYF+4U+ZQKJ/58taFqozZV0TWkJSXWIL+4aZ2Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:27:29.525145Z","bundle_sha256":"e2a69871ede0fbb9077b8a4be5f59d5a6abc1bbf0d9f31bd7be50cb3b54fe5bc"}}