{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DUBHSILN5BDELEQPDWMNZIQ2EW","short_pith_number":"pith:DUBHSILN","canonical_record":{"source":{"id":"2407.07577","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T12:11:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"480ff943185e00860b7d3a3acd67f708bd81a1335dc5d1f5c20804c6254ad015","abstract_canon_sha256":"d4cb8242be8eca68c344139be808898beffcc2f8573e85fa28e322249554029a"},"schema_version":"1.0"},"canonical_sha256":"1d0279216de84645920f1d98dca21a259b3c6f2f8e511aef89be46b3bd87c2ad","source":{"kind":"arxiv","id":"2407.07577","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07577","created_at":"2026-07-05T08:42:14Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07577v1","created_at":"2026-07-05T08:42:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07577","created_at":"2026-07-05T08:42:14Z"},{"alias_kind":"pith_short_12","alias_value":"DUBHSILN5BDE","created_at":"2026-07-05T08:42:14Z"},{"alias_kind":"pith_short_16","alias_value":"DUBHSILN5BDELEQP","created_at":"2026-07-05T08:42:14Z"},{"alias_kind":"pith_short_8","alias_value":"DUBHSILN","created_at":"2026-07-05T08:42:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DUBHSILN5BDELEQPDWMNZIQ2EW","target":"record","payload":{"canonical_record":{"source":{"id":"2407.07577","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T12:11:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"480ff943185e00860b7d3a3acd67f708bd81a1335dc5d1f5c20804c6254ad015","abstract_canon_sha256":"d4cb8242be8eca68c344139be808898beffcc2f8573e85fa28e322249554029a"},"schema_version":"1.0"},"canonical_sha256":"1d0279216de84645920f1d98dca21a259b3c6f2f8e511aef89be46b3bd87c2ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:14.508781Z","signature_b64":"Kzd/wDoyozrWJj96ocg6G/wlCK2SL8o9LD/dlulxyqCizEOmQc6nlxgnVwG8kJrZVxPNarTpiELfHAkfWCJVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d0279216de84645920f1d98dca21a259b3c6f2f8e511aef89be46b3bd87c2ad","last_reissued_at":"2026-07-05T08:42:14.508342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:14.508342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.07577","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":"2026-07-05T08:42:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pUjkuv85HGNZCHrfdX4XPaW3hHq8eKOMw0XHRjceCgArts7dH9pwXe/mlEe0roEiexcvFGHZ89Z+RoZULI8jDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:36:49.189613Z"},"content_sha256":"d23116414ed84ad9171bb54b9fe8533a8542c35e047cb6cf8c6b63cdd0e2b166","schema_version":"1.0","event_id":"sha256:d23116414ed84ad9171bb54b9fe8533a8542c35e047cb6cf8c6b63cdd0e2b166"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DUBHSILN5BDELEQPDWMNZIQ2EW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jie Wu, Peize Sun, Ping Luo, Shilong Zhang, Sidi Yang, Weifeng Chen, Xuefeng Xiao, Yatai Ji, Yujiu Yang","submitted_at":"2024-07-10T12:11:59Z","abstract_excerpt":"The rapid advancement of Large Vision-Language models (LVLMs) has demonstrated a spectrum of emergent capabilities. Nevertheless, current models only focus on the visual content of a single scenario, while their ability to associate instances across different scenes has not yet been explored, which is essential for understanding complex visual content, such as movies with multiple characters and intricate plots. Towards movie understanding, a critical initial step for LVLMs is to unleash the potential of character identities memory and recognition across multiple visual scenarios. To achieve t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07577","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/2407.07577/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":"2026-07-05T08:42:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9fSbSQ3gZI/i/lsacnVKWMjlpmFXUazb+KzFLYfxLXjiYJnEpDMj6huXyMeTExzLI1Iw5tz7b/jwmzO5468HBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:36:49.190314Z"},"content_sha256":"d080eec7bdee5f4d63a46b8853359a150f35351cdeccd8146e4a4a3c2c0c8094","schema_version":"1.0","event_id":"sha256:d080eec7bdee5f4d63a46b8853359a150f35351cdeccd8146e4a4a3c2c0c8094"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DUBHSILN5BDELEQPDWMNZIQ2EW/bundle.json","state_url":"https://pith.science/pith/DUBHSILN5BDELEQPDWMNZIQ2EW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DUBHSILN5BDELEQPDWMNZIQ2EW/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":"2026-08-11T10:36:49Z","links":{"resolver":"https://pith.science/pith/DUBHSILN5BDELEQPDWMNZIQ2EW","bundle":"https://pith.science/pith/DUBHSILN5BDELEQPDWMNZIQ2EW/bundle.json","state":"https://pith.science/pith/DUBHSILN5BDELEQPDWMNZIQ2EW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DUBHSILN5BDELEQPDWMNZIQ2EW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DUBHSILN5BDELEQPDWMNZIQ2EW","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":"d4cb8242be8eca68c344139be808898beffcc2f8573e85fa28e322249554029a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T12:11:59Z","title_canon_sha256":"480ff943185e00860b7d3a3acd67f708bd81a1335dc5d1f5c20804c6254ad015"},"schema_version":"1.0","source":{"id":"2407.07577","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07577","created_at":"2026-07-05T08:42:14Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07577v1","created_at":"2026-07-05T08:42:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07577","created_at":"2026-07-05T08:42:14Z"},{"alias_kind":"pith_short_12","alias_value":"DUBHSILN5BDE","created_at":"2026-07-05T08:42:14Z"},{"alias_kind":"pith_short_16","alias_value":"DUBHSILN5BDELEQP","created_at":"2026-07-05T08:42:14Z"},{"alias_kind":"pith_short_8","alias_value":"DUBHSILN","created_at":"2026-07-05T08:42:14Z"}],"graph_snapshots":[{"event_id":"sha256:d080eec7bdee5f4d63a46b8853359a150f35351cdeccd8146e4a4a3c2c0c8094","target":"graph","created_at":"2026-07-05T08:42:14Z","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/2407.07577/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancement of Large Vision-Language models (LVLMs) has demonstrated a spectrum of emergent capabilities. Nevertheless, current models only focus on the visual content of a single scenario, while their ability to associate instances across different scenes has not yet been explored, which is essential for understanding complex visual content, such as movies with multiple characters and intricate plots. Towards movie understanding, a critical initial step for LVLMs is to unleash the potential of character identities memory and recognition across multiple visual scenarios. To achieve t","authors_text":"Jie Wu, Peize Sun, Ping Luo, Shilong Zhang, Sidi Yang, Weifeng Chen, Xuefeng Xiao, Yatai Ji, Yujiu Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T12:11:59Z","title":"IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07577","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:d23116414ed84ad9171bb54b9fe8533a8542c35e047cb6cf8c6b63cdd0e2b166","target":"record","created_at":"2026-07-05T08:42:14Z","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":"d4cb8242be8eca68c344139be808898beffcc2f8573e85fa28e322249554029a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T12:11:59Z","title_canon_sha256":"480ff943185e00860b7d3a3acd67f708bd81a1335dc5d1f5c20804c6254ad015"},"schema_version":"1.0","source":{"id":"2407.07577","kind":"arxiv","version":1}},"canonical_sha256":"1d0279216de84645920f1d98dca21a259b3c6f2f8e511aef89be46b3bd87c2ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d0279216de84645920f1d98dca21a259b3c6f2f8e511aef89be46b3bd87c2ad","first_computed_at":"2026-07-05T08:42:14.508342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:14.508342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kzd/wDoyozrWJj96ocg6G/wlCK2SL8o9LD/dlulxyqCizEOmQc6nlxgnVwG8kJrZVxPNarTpiELfHAkfWCJVDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:14.508781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.07577","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d23116414ed84ad9171bb54b9fe8533a8542c35e047cb6cf8c6b63cdd0e2b166","sha256:d080eec7bdee5f4d63a46b8853359a150f35351cdeccd8146e4a4a3c2c0c8094"],"state_sha256":"1faccebac5d0a99eefa98ad37cb2886a824c838b0e67ef9c659916ee8c9d242e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eHVa2pvqu24Q29yBORJ355CEIQzgfT4QllmXHO9MVmFlZf0U1bU3rQxLLipHLWCBj/0K+15J2wH/k9w8e6hRBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T10:36:49.196507Z","bundle_sha256":"d6b749f48586f9d601e9dd310814a487bfb3346a3a975f830b812d7cf80a5c4f"}}