{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GDNUGN44CQJEBIGU3FSWXVDO3I","short_pith_number":"pith:GDNUGN44","canonical_record":{"source":{"id":"2506.23196","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-29T11:50:19Z","cross_cats_sorted":[],"title_canon_sha256":"adeba99197e9a865245fdf4a84a59cce122a649a26d342b836b92cb6e11ed505","abstract_canon_sha256":"fd9f01f13dbd072da8a757b8a4dcacc3805efb347fc962264219072ad190a809"},"schema_version":"1.0"},"canonical_sha256":"30db43379c141240a0d4d9656bd46eda0274ccbbdc5642e05fadeacfadd3c366","source":{"kind":"arxiv","id":"2506.23196","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23196","created_at":"2026-07-05T11:29:17Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23196v1","created_at":"2026-07-05T11:29:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23196","created_at":"2026-07-05T11:29:17Z"},{"alias_kind":"pith_short_12","alias_value":"GDNUGN44CQJE","created_at":"2026-07-05T11:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"GDNUGN44CQJEBIGU","created_at":"2026-07-05T11:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"GDNUGN44","created_at":"2026-07-05T11:29:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GDNUGN44CQJEBIGU3FSWXVDO3I","target":"record","payload":{"canonical_record":{"source":{"id":"2506.23196","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-29T11:50:19Z","cross_cats_sorted":[],"title_canon_sha256":"adeba99197e9a865245fdf4a84a59cce122a649a26d342b836b92cb6e11ed505","abstract_canon_sha256":"fd9f01f13dbd072da8a757b8a4dcacc3805efb347fc962264219072ad190a809"},"schema_version":"1.0"},"canonical_sha256":"30db43379c141240a0d4d9656bd46eda0274ccbbdc5642e05fadeacfadd3c366","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:17.531032Z","signature_b64":"hkJDLeBzTbx/MEscA1eGLlkf8Xdf2FnNHqfp3Xa2zh1N5s9fQWmrSaMCgg1suVkABQxLEaOipYpENeCDWgfeCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30db43379c141240a0d4d9656bd46eda0274ccbbdc5642e05fadeacfadd3c366","last_reissued_at":"2026-07-05T11:29:17.530532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:17.530532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.23196","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":"2026-07-05T11:29:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U8zwxXiKGoik7wYRY+jKxhWN/wHHQ+ZRFql/l5b2S27PppRRyn9ULMOfuI66pSGVLQZ+uk2LfyZBusCzge3JCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:05:33.573943Z"},"content_sha256":"524302994742f91c421996131bc787606f7e96165179f2942cfcb260c7497dce","schema_version":"1.0","event_id":"sha256:524302994742f91c421996131bc787606f7e96165179f2942cfcb260c7497dce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GDNUGN44CQJEBIGU3FSWXVDO3I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DEL: Dense Event Localization for Multi-modal Audio-Visual Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amir Shirian, Andrew Gilbert, Frank Guerin, Mona Ahmadian","submitted_at":"2025-06-29T11:50:19Z","abstract_excerpt":"Real-world videos often contain overlapping events and complex temporal dependencies, making multimodal interaction modeling particularly challenging. We introduce DEL, a framework for dense semantic action localization, aiming to accurately detect and classify multiple actions at fine-grained temporal resolutions in long untrimmed videos. DEL consists of two key modules: the alignment of audio and visual features that leverage masked self-attention to enhance intra-mode consistency and a multimodal interaction refinement module that models cross-modal dependencies across multiple scales, enab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23196","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/2506.23196/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":"2026-07-05T11:29:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"trIhOCCqfx0zXKCNKDCSp5e/SrRGoXhXu3MxaUPlxR7s1TVFFz4TNX1Bf2VJiCZD0DIIlMmFPFZ112ZXEbvSDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:05:33.574855Z"},"content_sha256":"0ee97c8849ba9a55f3aafcc1a18d2fdeef04eb0ad4823cfce01f63277aaab10d","schema_version":"1.0","event_id":"sha256:0ee97c8849ba9a55f3aafcc1a18d2fdeef04eb0ad4823cfce01f63277aaab10d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GDNUGN44CQJEBIGU3FSWXVDO3I/bundle.json","state_url":"https://pith.science/pith/GDNUGN44CQJEBIGU3FSWXVDO3I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GDNUGN44CQJEBIGU3FSWXVDO3I/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":"2026-08-07T21:05:33Z","links":{"resolver":"https://pith.science/pith/GDNUGN44CQJEBIGU3FSWXVDO3I","bundle":"https://pith.science/pith/GDNUGN44CQJEBIGU3FSWXVDO3I/bundle.json","state":"https://pith.science/pith/GDNUGN44CQJEBIGU3FSWXVDO3I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GDNUGN44CQJEBIGU3FSWXVDO3I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GDNUGN44CQJEBIGU3FSWXVDO3I","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":"fd9f01f13dbd072da8a757b8a4dcacc3805efb347fc962264219072ad190a809","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-29T11:50:19Z","title_canon_sha256":"adeba99197e9a865245fdf4a84a59cce122a649a26d342b836b92cb6e11ed505"},"schema_version":"1.0","source":{"id":"2506.23196","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23196","created_at":"2026-07-05T11:29:17Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23196v1","created_at":"2026-07-05T11:29:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23196","created_at":"2026-07-05T11:29:17Z"},{"alias_kind":"pith_short_12","alias_value":"GDNUGN44CQJE","created_at":"2026-07-05T11:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"GDNUGN44CQJEBIGU","created_at":"2026-07-05T11:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"GDNUGN44","created_at":"2026-07-05T11:29:17Z"}],"graph_snapshots":[{"event_id":"sha256:0ee97c8849ba9a55f3aafcc1a18d2fdeef04eb0ad4823cfce01f63277aaab10d","target":"graph","created_at":"2026-07-05T11:29:17Z","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/2506.23196/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-world videos often contain overlapping events and complex temporal dependencies, making multimodal interaction modeling particularly challenging. We introduce DEL, a framework for dense semantic action localization, aiming to accurately detect and classify multiple actions at fine-grained temporal resolutions in long untrimmed videos. DEL consists of two key modules: the alignment of audio and visual features that leverage masked self-attention to enhance intra-mode consistency and a multimodal interaction refinement module that models cross-modal dependencies across multiple scales, enab","authors_text":"Amir Shirian, Andrew Gilbert, Frank Guerin, Mona Ahmadian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-29T11:50:19Z","title":"DEL: Dense Event Localization for Multi-modal Audio-Visual Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23196","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":"sha256:524302994742f91c421996131bc787606f7e96165179f2942cfcb260c7497dce","target":"record","created_at":"2026-07-05T11:29:17Z","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":"fd9f01f13dbd072da8a757b8a4dcacc3805efb347fc962264219072ad190a809","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-29T11:50:19Z","title_canon_sha256":"adeba99197e9a865245fdf4a84a59cce122a649a26d342b836b92cb6e11ed505"},"schema_version":"1.0","source":{"id":"2506.23196","kind":"arxiv","version":1}},"canonical_sha256":"30db43379c141240a0d4d9656bd46eda0274ccbbdc5642e05fadeacfadd3c366","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30db43379c141240a0d4d9656bd46eda0274ccbbdc5642e05fadeacfadd3c366","first_computed_at":"2026-07-05T11:29:17.530532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:17.530532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hkJDLeBzTbx/MEscA1eGLlkf8Xdf2FnNHqfp3Xa2zh1N5s9fQWmrSaMCgg1suVkABQxLEaOipYpENeCDWgfeCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:17.531032Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23196","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:524302994742f91c421996131bc787606f7e96165179f2942cfcb260c7497dce","sha256:0ee97c8849ba9a55f3aafcc1a18d2fdeef04eb0ad4823cfce01f63277aaab10d"],"state_sha256":"f1f2646665f01f0323252ec284353091075a2175cafa5e93de1145aa472a952b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2wfaB1x/xKbZl4hXKrpMe3mfiPpbMhLEZ3JsnsHTmLcsNAUDzq3clVM0WFc+Fz/mhNetSVLtU4/J5x1Hh3OzBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T21:05:33.586748Z","bundle_sha256":"fcb643184f5c00d02eded15b3b5d7a678cdc1ab1f61b069431dbbe702789a9e4"}}