{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HRQKZT6NZDZMJVYBCYE22N2AV3","short_pith_number":"pith:HRQKZT6N","canonical_record":{"source":{"id":"2505.02096","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-05-04T13:03:13Z","cross_cats_sorted":[],"title_canon_sha256":"57107c0fdf02e8ca5c4c94ac7310d063cec401a1acddfd1f95b5d099c2f2e21f","abstract_canon_sha256":"fd4193af308bef79d597e085bd35c6c95dc97af07963eb4e3235243594bf02ae"},"schema_version":"1.0"},"canonical_sha256":"3c60accfcdc8f2c4d7011609ad3740aed92400138b4b0de0b0a3b8a22e92f111","source":{"kind":"arxiv","id":"2505.02096","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02096","created_at":"2026-07-05T10:58:31Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02096v1","created_at":"2026-07-05T10:58:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02096","created_at":"2026-07-05T10:58:31Z"},{"alias_kind":"pith_short_12","alias_value":"HRQKZT6NZDZM","created_at":"2026-07-05T10:58:31Z"},{"alias_kind":"pith_short_16","alias_value":"HRQKZT6NZDZMJVYB","created_at":"2026-07-05T10:58:31Z"},{"alias_kind":"pith_short_8","alias_value":"HRQKZT6N","created_at":"2026-07-05T10:58:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HRQKZT6NZDZMJVYBCYE22N2AV3","target":"record","payload":{"canonical_record":{"source":{"id":"2505.02096","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-05-04T13:03:13Z","cross_cats_sorted":[],"title_canon_sha256":"57107c0fdf02e8ca5c4c94ac7310d063cec401a1acddfd1f95b5d099c2f2e21f","abstract_canon_sha256":"fd4193af308bef79d597e085bd35c6c95dc97af07963eb4e3235243594bf02ae"},"schema_version":"1.0"},"canonical_sha256":"3c60accfcdc8f2c4d7011609ad3740aed92400138b4b0de0b0a3b8a22e92f111","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:31.874546Z","signature_b64":"Qx2AGdAaBE0els5AIIAeLovz71tk+VCrkoGHFn+eBO5PX0RSc9H4oSOxo3wieGJVbHDuiS5TxzZSS8c09JpICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c60accfcdc8f2c4d7011609ad3740aed92400138b4b0de0b0a3b8a22e92f111","last_reissued_at":"2026-07-05T10:58:31.873957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:31.873957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.02096","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":"2026-07-05T10:58:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M/6JIAJzNrgEapvqVqx6r5fLAXUuVgWdBQ5Idon7/gjtUZL7OLrN8+3hI+rreHnVyMPkd2ekfhoei8SudSVnCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:34:32.550898Z"},"content_sha256":"35cbeec7629d9999c3e02272d76e1e64a07eb74e81c212781e3be4b18a63c0bb","schema_version":"1.0","event_id":"sha256:35cbeec7629d9999c3e02272d76e1e64a07eb74e81c212781e3be4b18a63c0bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HRQKZT6NZDZMJVYBCYE22N2AV3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TeMTG: Text-Enhanced Multi-Hop Temporal Graph Modeling for Audio-Visual Video Parsing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Faegheh Sardari, Fei Li, Peiliang Zhang, Ruohao Guo, Wenwu Wang, Yaru Chen, Zhenbo Li","submitted_at":"2025-05-04T13:03:13Z","abstract_excerpt":"Audio-Visual Video Parsing (AVVP) task aims to parse the event categories and occurrence times from audio and visual modalities in a given video. Existing methods usually focus on implicitly modeling audio and visual features through weak labels, without mining semantic relationships for different modalities and explicit modeling of event temporal dependencies. This makes it difficult for the model to accurately parse event information for each segment under weak supervision, especially when high similarity between segmental modal features leads to ambiguous event boundaries. Hence, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02096","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/2505.02096/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":"2026-07-05T10:58:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fNlp2p4erbQOoLKr6d4HVgRzfe2ggaqsJv2eYlRUqOP4iu+nv4Vv0OdDN/QBGEunGddNdvSD5zk2AX6lMyAFCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:34:32.551262Z"},"content_sha256":"f085ba172862c69e93efc933629fcc16309942d0966cd0f62c5e40b967c5dae1","schema_version":"1.0","event_id":"sha256:f085ba172862c69e93efc933629fcc16309942d0966cd0f62c5e40b967c5dae1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HRQKZT6NZDZMJVYBCYE22N2AV3/bundle.json","state_url":"https://pith.science/pith/HRQKZT6NZDZMJVYBCYE22N2AV3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HRQKZT6NZDZMJVYBCYE22N2AV3/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":"2026-08-18T23:34:32Z","links":{"resolver":"https://pith.science/pith/HRQKZT6NZDZMJVYBCYE22N2AV3","bundle":"https://pith.science/pith/HRQKZT6NZDZMJVYBCYE22N2AV3/bundle.json","state":"https://pith.science/pith/HRQKZT6NZDZMJVYBCYE22N2AV3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HRQKZT6NZDZMJVYBCYE22N2AV3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HRQKZT6NZDZMJVYBCYE22N2AV3","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":"fd4193af308bef79d597e085bd35c6c95dc97af07963eb4e3235243594bf02ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-05-04T13:03:13Z","title_canon_sha256":"57107c0fdf02e8ca5c4c94ac7310d063cec401a1acddfd1f95b5d099c2f2e21f"},"schema_version":"1.0","source":{"id":"2505.02096","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02096","created_at":"2026-07-05T10:58:31Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02096v1","created_at":"2026-07-05T10:58:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02096","created_at":"2026-07-05T10:58:31Z"},{"alias_kind":"pith_short_12","alias_value":"HRQKZT6NZDZM","created_at":"2026-07-05T10:58:31Z"},{"alias_kind":"pith_short_16","alias_value":"HRQKZT6NZDZMJVYB","created_at":"2026-07-05T10:58:31Z"},{"alias_kind":"pith_short_8","alias_value":"HRQKZT6N","created_at":"2026-07-05T10:58:31Z"}],"graph_snapshots":[{"event_id":"sha256:f085ba172862c69e93efc933629fcc16309942d0966cd0f62c5e40b967c5dae1","target":"graph","created_at":"2026-07-05T10:58:31Z","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/2505.02096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Video Parsing (AVVP) task aims to parse the event categories and occurrence times from audio and visual modalities in a given video. Existing methods usually focus on implicitly modeling audio and visual features through weak labels, without mining semantic relationships for different modalities and explicit modeling of event temporal dependencies. This makes it difficult for the model to accurately parse event information for each segment under weak supervision, especially when high similarity between segmental modal features leads to ambiguous event boundaries. Hence, we propose","authors_text":"Faegheh Sardari, Fei Li, Peiliang Zhang, Ruohao Guo, Wenwu Wang, Yaru Chen, Zhenbo Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-05-04T13:03:13Z","title":"TeMTG: Text-Enhanced Multi-Hop Temporal Graph Modeling for Audio-Visual Video Parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02096","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":"sha256:35cbeec7629d9999c3e02272d76e1e64a07eb74e81c212781e3be4b18a63c0bb","target":"record","created_at":"2026-07-05T10:58:31Z","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":"fd4193af308bef79d597e085bd35c6c95dc97af07963eb4e3235243594bf02ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-05-04T13:03:13Z","title_canon_sha256":"57107c0fdf02e8ca5c4c94ac7310d063cec401a1acddfd1f95b5d099c2f2e21f"},"schema_version":"1.0","source":{"id":"2505.02096","kind":"arxiv","version":1}},"canonical_sha256":"3c60accfcdc8f2c4d7011609ad3740aed92400138b4b0de0b0a3b8a22e92f111","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c60accfcdc8f2c4d7011609ad3740aed92400138b4b0de0b0a3b8a22e92f111","first_computed_at":"2026-07-05T10:58:31.873957Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:58:31.873957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qx2AGdAaBE0els5AIIAeLovz71tk+VCrkoGHFn+eBO5PX0RSc9H4oSOxo3wieGJVbHDuiS5TxzZSS8c09JpICQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:58:31.874546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.02096","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35cbeec7629d9999c3e02272d76e1e64a07eb74e81c212781e3be4b18a63c0bb","sha256:f085ba172862c69e93efc933629fcc16309942d0966cd0f62c5e40b967c5dae1"],"state_sha256":"a46ab3876f295fe1bf08795a3d617254321641253ddfb04a8f1e45c59172733c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+1ftDrQKHOnSm/f7NTvSTHpsraKwBimw8DKaGFaa2fpZUcz8+pByZ3phMe8gcd/pMox8JcUAeH0xbU285ZzFBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T23:34:32.554638Z","bundle_sha256":"3eac35cc8ae8d2f5f33af7965f00901c6766f7ab75749457babdc323f4b91fb7"}}