{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QMFIVEHEOTUNQYUKBPO7SOAE4W","short_pith_number":"pith:QMFIVEHE","canonical_record":{"source":{"id":"2306.07207","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T16:11:10Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1105366a330eb94b3ec402c228006df5045596d65a1d5dbafa7a5f4d77c909f8","abstract_canon_sha256":"4fc310cd6bbf865a970b88cd263b25aad714f59e9bed354a0b6ba77a5d032dcd"},"schema_version":"1.0"},"canonical_sha256":"830a8a90e474e8d8628a0bddf93804e58808ea195f72f6ad866347161b86e228","source":{"kind":"arxiv","id":"2306.07207","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07207","created_at":"2026-07-05T10:32:23Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07207v3","created_at":"2026-07-05T10:32:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07207","created_at":"2026-07-05T10:32:23Z"},{"alias_kind":"pith_short_12","alias_value":"QMFIVEHEOTUN","created_at":"2026-07-05T10:32:23Z"},{"alias_kind":"pith_short_16","alias_value":"QMFIVEHEOTUNQYUK","created_at":"2026-07-05T10:32:23Z"},{"alias_kind":"pith_short_8","alias_value":"QMFIVEHE","created_at":"2026-07-05T10:32:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QMFIVEHEOTUNQYUKBPO7SOAE4W","target":"record","payload":{"canonical_record":{"source":{"id":"2306.07207","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T16:11:10Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1105366a330eb94b3ec402c228006df5045596d65a1d5dbafa7a5f4d77c909f8","abstract_canon_sha256":"4fc310cd6bbf865a970b88cd263b25aad714f59e9bed354a0b6ba77a5d032dcd"},"schema_version":"1.0"},"canonical_sha256":"830a8a90e474e8d8628a0bddf93804e58808ea195f72f6ad866347161b86e228","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:23.291528Z","signature_b64":"m4APRj7WU6iPBNSuc4Y59wJMntTnJFRgeIdK5bTjuiaWU+zr/TBbQoYpiZCIGobkFzRjq6Kkl52WHbeUIdlpCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"830a8a90e474e8d8628a0bddf93804e58808ea195f72f6ad866347161b86e228","last_reissued_at":"2026-07-05T10:32:23.291043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:23.291043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.07207","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:32:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c9ZlcsV6KR7DcPspC3GWcrSSULj4RHcWxKOF5D9w3r0L5aJt/YjC5Aeb5+F9NreR0YNGIqwcP2TTJj3E1ZgBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:14:59.483436Z"},"content_sha256":"8616e888fecd726c6264fe25c3ae0d037ad31adbe327803d0a15e6189b8e5212","schema_version":"1.0","event_id":"sha256:8616e888fecd726c6264fe25c3ae0d037ad31adbe327803d0a15e6189b8e5212"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QMFIVEHEOTUNQYUKBPO7SOAE4W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Valley: Video Assistant with Large Language model Enhanced abilitY","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Cen Chen, Minghui Qiu, Min Yang, Ruipu Luo, Tao Wang, Yanhao Wang, Zheming Yang, Zhongyu Wei, Ziwang Zhao","submitted_at":"2023-06-12T16:11:10Z","abstract_excerpt":"Large Language Models (LLMs), with remarkable conversational capability, have emerged as AI assistants that can handle both visual and textual modalities. However, their effectiveness in joint video and language understanding has not been extensively explored. In the paper, we introduce Valley, a multi-modal foundation model that is designed to enable enhanced video comprehension and instruction-following capabilities. To this end, we construct two datasets, namely Valley-702k and Valley-instruct-73k, to cover a diverse range of video-text alignment and video-based instruction tasks, such as m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07207","kind":"arxiv","version":3},"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/2306.07207/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":"2026-07-05T10:32:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XVNMuICU+6xi5FP2xaJkc9qJu/y/HqrZGnH9u5LR0qRC1KbxsrfQLuZLSMbgHzUQUIuFl+SBWbkR+xqeyKf+Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:14:59.485581Z"},"content_sha256":"813802fa593b260b6a2b17410b9d24237b6b1b8d0ccc5a94e70faf9152f39e04","schema_version":"1.0","event_id":"sha256:813802fa593b260b6a2b17410b9d24237b6b1b8d0ccc5a94e70faf9152f39e04"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QMFIVEHEOTUNQYUKBPO7SOAE4W/bundle.json","state_url":"https://pith.science/pith/QMFIVEHEOTUNQYUKBPO7SOAE4W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QMFIVEHEOTUNQYUKBPO7SOAE4W/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":"2026-08-05T09:14:59Z","links":{"resolver":"https://pith.science/pith/QMFIVEHEOTUNQYUKBPO7SOAE4W","bundle":"https://pith.science/pith/QMFIVEHEOTUNQYUKBPO7SOAE4W/bundle.json","state":"https://pith.science/pith/QMFIVEHEOTUNQYUKBPO7SOAE4W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QMFIVEHEOTUNQYUKBPO7SOAE4W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QMFIVEHEOTUNQYUKBPO7SOAE4W","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":"4fc310cd6bbf865a970b88cd263b25aad714f59e9bed354a0b6ba77a5d032dcd","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T16:11:10Z","title_canon_sha256":"1105366a330eb94b3ec402c228006df5045596d65a1d5dbafa7a5f4d77c909f8"},"schema_version":"1.0","source":{"id":"2306.07207","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07207","created_at":"2026-07-05T10:32:23Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07207v3","created_at":"2026-07-05T10:32:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07207","created_at":"2026-07-05T10:32:23Z"},{"alias_kind":"pith_short_12","alias_value":"QMFIVEHEOTUN","created_at":"2026-07-05T10:32:23Z"},{"alias_kind":"pith_short_16","alias_value":"QMFIVEHEOTUNQYUK","created_at":"2026-07-05T10:32:23Z"},{"alias_kind":"pith_short_8","alias_value":"QMFIVEHE","created_at":"2026-07-05T10:32:23Z"}],"graph_snapshots":[{"event_id":"sha256:813802fa593b260b6a2b17410b9d24237b6b1b8d0ccc5a94e70faf9152f39e04","target":"graph","created_at":"2026-07-05T10:32:23Z","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/2306.07207/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs), with remarkable conversational capability, have emerged as AI assistants that can handle both visual and textual modalities. However, their effectiveness in joint video and language understanding has not been extensively explored. In the paper, we introduce Valley, a multi-modal foundation model that is designed to enable enhanced video comprehension and instruction-following capabilities. To this end, we construct two datasets, namely Valley-702k and Valley-instruct-73k, to cover a diverse range of video-text alignment and video-based instruction tasks, such as m","authors_text":"Cen Chen, Minghui Qiu, Min Yang, Ruipu Luo, Tao Wang, Yanhao Wang, Zheming Yang, Zhongyu Wei, Ziwang Zhao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T16:11:10Z","title":"Valley: Video Assistant with Large Language model Enhanced abilitY"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07207","kind":"arxiv","version":3},"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":"sha256:8616e888fecd726c6264fe25c3ae0d037ad31adbe327803d0a15e6189b8e5212","target":"record","created_at":"2026-07-05T10:32:23Z","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":"4fc310cd6bbf865a970b88cd263b25aad714f59e9bed354a0b6ba77a5d032dcd","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-12T16:11:10Z","title_canon_sha256":"1105366a330eb94b3ec402c228006df5045596d65a1d5dbafa7a5f4d77c909f8"},"schema_version":"1.0","source":{"id":"2306.07207","kind":"arxiv","version":3}},"canonical_sha256":"830a8a90e474e8d8628a0bddf93804e58808ea195f72f6ad866347161b86e228","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"830a8a90e474e8d8628a0bddf93804e58808ea195f72f6ad866347161b86e228","first_computed_at":"2026-07-05T10:32:23.291043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:23.291043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m4APRj7WU6iPBNSuc4Y59wJMntTnJFRgeIdK5bTjuiaWU+zr/TBbQoYpiZCIGobkFzRjq6Kkl52WHbeUIdlpCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:23.291528Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07207","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8616e888fecd726c6264fe25c3ae0d037ad31adbe327803d0a15e6189b8e5212","sha256:813802fa593b260b6a2b17410b9d24237b6b1b8d0ccc5a94e70faf9152f39e04"],"state_sha256":"728d00bad90fb8d315949101cb3972bb5925559c55ffeb7674b53f83e4c9fb3c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A1iM2zDbxfnt6gY4BiCLZ2x8N4LyYA8PXxLLD5eHX41DpyWClKmlfvAevK7QBAlH3MVgoCV6iL2ONT5SsfqCAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:14:59.493228Z","bundle_sha256":"ceaf5df2461f70154dc9e61e499527c99975d37a5b2d504448e13dfe63c39c06"}}