{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:A6CR5O5RX2TRNFYG66EZFCAAKX","short_pith_number":"pith:A6CR5O5R","canonical_record":{"source":{"id":"2503.12769","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T03:05:31Z","cross_cats_sorted":[],"title_canon_sha256":"748b9e0f4b710c92e95df73f884590d23e8e997976478f978681d70590dfbb88","abstract_canon_sha256":"d74e4eb7125e7b8b47053902f7a21c620dbb7392320e14e64c2fed90c86e3c30"},"schema_version":"1.0"},"canonical_sha256":"07851ebbb1bea7169706f78992880055ebf104061814743a399e30e689b3c5e3","source":{"kind":"arxiv","id":"2503.12769","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12769","created_at":"2026-07-05T10:32:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12769v1","created_at":"2026-07-05T10:32:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12769","created_at":"2026-07-05T10:32:45Z"},{"alias_kind":"pith_short_12","alias_value":"A6CR5O5RX2TR","created_at":"2026-07-05T10:32:45Z"},{"alias_kind":"pith_short_16","alias_value":"A6CR5O5RX2TRNFYG","created_at":"2026-07-05T10:32:45Z"},{"alias_kind":"pith_short_8","alias_value":"A6CR5O5R","created_at":"2026-07-05T10:32:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:A6CR5O5RX2TRNFYG66EZFCAAKX","target":"record","payload":{"canonical_record":{"source":{"id":"2503.12769","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T03:05:31Z","cross_cats_sorted":[],"title_canon_sha256":"748b9e0f4b710c92e95df73f884590d23e8e997976478f978681d70590dfbb88","abstract_canon_sha256":"d74e4eb7125e7b8b47053902f7a21c620dbb7392320e14e64c2fed90c86e3c30"},"schema_version":"1.0"},"canonical_sha256":"07851ebbb1bea7169706f78992880055ebf104061814743a399e30e689b3c5e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:45.760957Z","signature_b64":"sxEC3BUY59KhXKlkhmiWKiuOyphdW97y4Q8HvlR/mCqfOjb6mLvwXimjriYqDzaliJzeuoDoNbC/wWA2a1i+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07851ebbb1bea7169706f78992880055ebf104061814743a399e30e689b3c5e3","last_reissued_at":"2026-07-05T10:32:45.760428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:45.760428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.12769","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":"2026-07-05T10:32:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zSmb+/dX79UgLwmvl8hqGjB70RaH5BH1o88OirDwkfh3iv3O83SgRpTdmEQpMmE7to9poLqjdf/G4NkfJsVcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T20:10:15.875269Z"},"content_sha256":"42e22f04bd366b09de13d6b977fe2d53563f732729412df354d6bdb8eafb28a6","schema_version":"1.0","event_id":"sha256:42e22f04bd366b09de13d6b977fe2d53563f732729412df354d6bdb8eafb28a6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:A6CR5O5RX2TRNFYG66EZFCAAKX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ViSpeak: Visual Instruction Feedback in Streaming Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian-Fang Hu, Kun-Yu Lin, Qize Yang, Shenghao Fu, Wei-Shi Zheng, Xiaohua Xie, Xihan Wei, Yi-Xing Peng, Yuan-Ming Li","submitted_at":"2025-03-17T03:05:31Z","abstract_excerpt":"Recent advances in Large Multi-modal Models (LMMs) are primarily focused on offline video understanding. Instead, streaming video understanding poses great challenges to recent models due to its time-sensitive, omni-modal and interactive characteristics. In this work, we aim to extend the streaming video understanding from a new perspective and propose a novel task named Visual Instruction Feedback in which models should be aware of visual contents and learn to extract instructions from them. For example, when users wave their hands to agents, agents should recognize the gesture and start conv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12769","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/2503.12769/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":"2026-07-05T10:32:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1R1ZHBIiczo5k71PkP9g7gi9J4VedQ21zQX18rNDkAmDSchZN/LOAHfzwyYVa4+XU8NM2H49QzJz6tCHPj0fBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T20:10:15.876165Z"},"content_sha256":"d14e566581c2af8735309d2ea9851fc091515e2421d6a9e7182cd566ca44900e","schema_version":"1.0","event_id":"sha256:d14e566581c2af8735309d2ea9851fc091515e2421d6a9e7182cd566ca44900e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A6CR5O5RX2TRNFYG66EZFCAAKX/bundle.json","state_url":"https://pith.science/pith/A6CR5O5RX2TRNFYG66EZFCAAKX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A6CR5O5RX2TRNFYG66EZFCAAKX/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":"2026-08-13T20:10:15Z","links":{"resolver":"https://pith.science/pith/A6CR5O5RX2TRNFYG66EZFCAAKX","bundle":"https://pith.science/pith/A6CR5O5RX2TRNFYG66EZFCAAKX/bundle.json","state":"https://pith.science/pith/A6CR5O5RX2TRNFYG66EZFCAAKX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A6CR5O5RX2TRNFYG66EZFCAAKX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A6CR5O5RX2TRNFYG66EZFCAAKX","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":"d74e4eb7125e7b8b47053902f7a21c620dbb7392320e14e64c2fed90c86e3c30","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T03:05:31Z","title_canon_sha256":"748b9e0f4b710c92e95df73f884590d23e8e997976478f978681d70590dfbb88"},"schema_version":"1.0","source":{"id":"2503.12769","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12769","created_at":"2026-07-05T10:32:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12769v1","created_at":"2026-07-05T10:32:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12769","created_at":"2026-07-05T10:32:45Z"},{"alias_kind":"pith_short_12","alias_value":"A6CR5O5RX2TR","created_at":"2026-07-05T10:32:45Z"},{"alias_kind":"pith_short_16","alias_value":"A6CR5O5RX2TRNFYG","created_at":"2026-07-05T10:32:45Z"},{"alias_kind":"pith_short_8","alias_value":"A6CR5O5R","created_at":"2026-07-05T10:32:45Z"}],"graph_snapshots":[{"event_id":"sha256:d14e566581c2af8735309d2ea9851fc091515e2421d6a9e7182cd566ca44900e","target":"graph","created_at":"2026-07-05T10:32:45Z","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/2503.12769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Large Multi-modal Models (LMMs) are primarily focused on offline video understanding. Instead, streaming video understanding poses great challenges to recent models due to its time-sensitive, omni-modal and interactive characteristics. In this work, we aim to extend the streaming video understanding from a new perspective and propose a novel task named Visual Instruction Feedback in which models should be aware of visual contents and learn to extract instructions from them. For example, when users wave their hands to agents, agents should recognize the gesture and start conv","authors_text":"Jian-Fang Hu, Kun-Yu Lin, Qize Yang, Shenghao Fu, Wei-Shi Zheng, Xiaohua Xie, Xihan Wei, Yi-Xing Peng, Yuan-Ming Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T03:05:31Z","title":"ViSpeak: Visual Instruction Feedback in Streaming Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12769","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":"sha256:42e22f04bd366b09de13d6b977fe2d53563f732729412df354d6bdb8eafb28a6","target":"record","created_at":"2026-07-05T10:32:45Z","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":"d74e4eb7125e7b8b47053902f7a21c620dbb7392320e14e64c2fed90c86e3c30","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T03:05:31Z","title_canon_sha256":"748b9e0f4b710c92e95df73f884590d23e8e997976478f978681d70590dfbb88"},"schema_version":"1.0","source":{"id":"2503.12769","kind":"arxiv","version":1}},"canonical_sha256":"07851ebbb1bea7169706f78992880055ebf104061814743a399e30e689b3c5e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07851ebbb1bea7169706f78992880055ebf104061814743a399e30e689b3c5e3","first_computed_at":"2026-07-05T10:32:45.760428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:45.760428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sxEC3BUY59KhXKlkhmiWKiuOyphdW97y4Q8HvlR/mCqfOjb6mLvwXimjriYqDzaliJzeuoDoNbC/wWA2a1i+BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:45.760957Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.12769","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42e22f04bd366b09de13d6b977fe2d53563f732729412df354d6bdb8eafb28a6","sha256:d14e566581c2af8735309d2ea9851fc091515e2421d6a9e7182cd566ca44900e"],"state_sha256":"5301890394a985fe6bfc254300a9e5558b91555702f59d5c358af90077a86f6b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sUYhKtOV7sefHebbYOsijQvn5FZZjx69+DVvX5LZ81YVo23nvha06lWlD6zauDJA26TAUsWveBkkGlFaJlN+AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T20:10:15.903533Z","bundle_sha256":"39b43342fdfb8d188415962628c79d9401b00c155f8793900b73ade769e98c9b"}}