{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:X345NTZDY6536QVEYZATVJFQFW","short_pith_number":"pith:X345NTZD","canonical_record":{"source":{"id":"2504.16030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T16:52:09Z","cross_cats_sorted":[],"title_canon_sha256":"7bb3edcc95b9cf1c7d2f3fe1b7796445c53f8e67245154ed85e3d75139abced5","abstract_canon_sha256":"e6a712388164a132136e57d8e6b0c3be37fbb7d9341dd9eaf986209d9c453b87"},"schema_version":"1.0"},"canonical_sha256":"bef9d6cf23c7bbbf42a4c6413aa4b02d87d79d1387f8bb40f4d25f37f32b7c87","source":{"kind":"arxiv","id":"2504.16030","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16030","created_at":"2026-07-05T10:52:33Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16030v1","created_at":"2026-07-05T10:52:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16030","created_at":"2026-07-05T10:52:33Z"},{"alias_kind":"pith_short_12","alias_value":"X345NTZDY653","created_at":"2026-07-05T10:52:33Z"},{"alias_kind":"pith_short_16","alias_value":"X345NTZDY6536QVE","created_at":"2026-07-05T10:52:33Z"},{"alias_kind":"pith_short_8","alias_value":"X345NTZD","created_at":"2026-07-05T10:52:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:X345NTZDY6536QVEYZATVJFQFW","target":"record","payload":{"canonical_record":{"source":{"id":"2504.16030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T16:52:09Z","cross_cats_sorted":[],"title_canon_sha256":"7bb3edcc95b9cf1c7d2f3fe1b7796445c53f8e67245154ed85e3d75139abced5","abstract_canon_sha256":"e6a712388164a132136e57d8e6b0c3be37fbb7d9341dd9eaf986209d9c453b87"},"schema_version":"1.0"},"canonical_sha256":"bef9d6cf23c7bbbf42a4c6413aa4b02d87d79d1387f8bb40f4d25f37f32b7c87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:33.715418Z","signature_b64":"wpRt+yqVF93BTO5Djn6d+4GUB9iEKoFJx+GSF0mEJHCw3B+CLouUvo9b1CqVyMnHqH9gudF8XkWthMqxKziHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bef9d6cf23c7bbbf42a4c6413aa4b02d87d79d1387f8bb40f4d25f37f32b7c87","last_reissued_at":"2026-07-05T10:52:33.714905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:33.714905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.16030","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":"2026-07-05T10:52:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tEecIMcjmgu5EAdnkvRZYE898dyB/eYnSezjFs84R2lloZu870awGdH3vOyzwq+t+NIV1vOdrGCXc6+EP6IVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:16:03.067344Z"},"content_sha256":"bc7d92c7f5cefe439709a005e46592f1f70bb9af1095049b95514e3fcfb3a41f","schema_version":"1.0","event_id":"sha256:bc7d92c7f5cefe439709a005e46592f1f70bb9af1095049b95514e3fcfb3a41f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:X345NTZDY6536QVEYZATVJFQFW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Joya Chen, Mike Zheng Shou, Wei Li, Yiqi Lin, Zejun Ma, Ziyun Zeng","submitted_at":"2025-04-22T16:52:09Z","abstract_excerpt":"Recent video large language models (Video LLMs) often depend on costly human annotations or proprietary model APIs (e.g., GPT-4o) to produce training data, which limits their training at scale. In this paper, we explore large-scale training for Video LLM with cheap automatic speech recognition (ASR) transcripts. Specifically, we propose a novel streaming training approach that densely interleaves the ASR words and video frames according to their timestamps. Compared to previous studies in vision-language representation with ASR, our method naturally fits the streaming characteristics of ASR, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16030","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/2504.16030/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":"2026-07-05T10:52:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JZAHMs/r/6zW+VFjLLLuay13iNrKcQiMLdPm5L7gz9afwLzpf5umSZfjQTuDf7O70IP8Lo0NjtSwdycS3tXvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:16:03.067874Z"},"content_sha256":"d7b3ec3ed4610d4f54cd972413d39b4d70d094e9bbd1dffe1ec5a46119ed49f2","schema_version":"1.0","event_id":"sha256:d7b3ec3ed4610d4f54cd972413d39b4d70d094e9bbd1dffe1ec5a46119ed49f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X345NTZDY6536QVEYZATVJFQFW/bundle.json","state_url":"https://pith.science/pith/X345NTZDY6536QVEYZATVJFQFW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X345NTZDY6536QVEYZATVJFQFW/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":"2026-08-19T22:16:03Z","links":{"resolver":"https://pith.science/pith/X345NTZDY6536QVEYZATVJFQFW","bundle":"https://pith.science/pith/X345NTZDY6536QVEYZATVJFQFW/bundle.json","state":"https://pith.science/pith/X345NTZDY6536QVEYZATVJFQFW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X345NTZDY6536QVEYZATVJFQFW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X345NTZDY6536QVEYZATVJFQFW","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":"e6a712388164a132136e57d8e6b0c3be37fbb7d9341dd9eaf986209d9c453b87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T16:52:09Z","title_canon_sha256":"7bb3edcc95b9cf1c7d2f3fe1b7796445c53f8e67245154ed85e3d75139abced5"},"schema_version":"1.0","source":{"id":"2504.16030","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16030","created_at":"2026-07-05T10:52:33Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16030v1","created_at":"2026-07-05T10:52:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16030","created_at":"2026-07-05T10:52:33Z"},{"alias_kind":"pith_short_12","alias_value":"X345NTZDY653","created_at":"2026-07-05T10:52:33Z"},{"alias_kind":"pith_short_16","alias_value":"X345NTZDY6536QVE","created_at":"2026-07-05T10:52:33Z"},{"alias_kind":"pith_short_8","alias_value":"X345NTZD","created_at":"2026-07-05T10:52:33Z"}],"graph_snapshots":[{"event_id":"sha256:d7b3ec3ed4610d4f54cd972413d39b4d70d094e9bbd1dffe1ec5a46119ed49f2","target":"graph","created_at":"2026-07-05T10:52:33Z","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/2504.16030/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent video large language models (Video LLMs) often depend on costly human annotations or proprietary model APIs (e.g., GPT-4o) to produce training data, which limits their training at scale. In this paper, we explore large-scale training for Video LLM with cheap automatic speech recognition (ASR) transcripts. Specifically, we propose a novel streaming training approach that densely interleaves the ASR words and video frames according to their timestamps. Compared to previous studies in vision-language representation with ASR, our method naturally fits the streaming characteristics of ASR, t","authors_text":"Joya Chen, Mike Zheng Shou, Wei Li, Yiqi Lin, Zejun Ma, Ziyun Zeng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T16:52:09Z","title":"LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16030","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:bc7d92c7f5cefe439709a005e46592f1f70bb9af1095049b95514e3fcfb3a41f","target":"record","created_at":"2026-07-05T10:52:33Z","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":"e6a712388164a132136e57d8e6b0c3be37fbb7d9341dd9eaf986209d9c453b87","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T16:52:09Z","title_canon_sha256":"7bb3edcc95b9cf1c7d2f3fe1b7796445c53f8e67245154ed85e3d75139abced5"},"schema_version":"1.0","source":{"id":"2504.16030","kind":"arxiv","version":1}},"canonical_sha256":"bef9d6cf23c7bbbf42a4c6413aa4b02d87d79d1387f8bb40f4d25f37f32b7c87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bef9d6cf23c7bbbf42a4c6413aa4b02d87d79d1387f8bb40f4d25f37f32b7c87","first_computed_at":"2026-07-05T10:52:33.714905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:33.714905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wpRt+yqVF93BTO5Djn6d+4GUB9iEKoFJx+GSF0mEJHCw3B+CLouUvo9b1CqVyMnHqH9gudF8XkWthMqxKziHCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:33.715418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.16030","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc7d92c7f5cefe439709a005e46592f1f70bb9af1095049b95514e3fcfb3a41f","sha256:d7b3ec3ed4610d4f54cd972413d39b4d70d094e9bbd1dffe1ec5a46119ed49f2"],"state_sha256":"56fc370053eef86ed5925553918c85648571693ea14df927210f36c58ca8c71e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oFqywteH/pH+5CeXN9Io5jHy9aFlE46g6wBn7TRPeQCYcAEScPUklmmnUSLysUpkxYtdVcoBlps19/wpfaFMBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T22:16:03.073579Z","bundle_sha256":"2a6bc8fba632807904acae1d1154147daa2190c71b7ca044e407d700aabb42c9"}}