{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OYQY4VBD2XX6W4HMQWATOIN5EX","short_pith_number":"pith:OYQY4VBD","canonical_record":{"source":{"id":"2503.10781","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T18:21:07Z","cross_cats_sorted":[],"title_canon_sha256":"83071162112298aaf985ee46a64c775af02023e17cc0d1b7f5fd20faa916ba55","abstract_canon_sha256":"c8e636a25ea9ce80c8b4ecbbf1af7c354361301345bf64938f694d177261dc3e"},"schema_version":"1.0"},"canonical_sha256":"76218e5423d5efeb70ec85813721bd25e14b8575e9a91ca1ed43c9f83eb397dd","source":{"kind":"arxiv","id":"2503.10781","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10781","created_at":"2026-07-05T12:07:03Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10781v3","created_at":"2026-07-05T12:07:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10781","created_at":"2026-07-05T12:07:03Z"},{"alias_kind":"pith_short_12","alias_value":"OYQY4VBD2XX6","created_at":"2026-07-05T12:07:03Z"},{"alias_kind":"pith_short_16","alias_value":"OYQY4VBD2XX6W4HM","created_at":"2026-07-05T12:07:03Z"},{"alias_kind":"pith_short_8","alias_value":"OYQY4VBD","created_at":"2026-07-05T12:07:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OYQY4VBD2XX6W4HMQWATOIN5EX","target":"record","payload":{"canonical_record":{"source":{"id":"2503.10781","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T18:21:07Z","cross_cats_sorted":[],"title_canon_sha256":"83071162112298aaf985ee46a64c775af02023e17cc0d1b7f5fd20faa916ba55","abstract_canon_sha256":"c8e636a25ea9ce80c8b4ecbbf1af7c354361301345bf64938f694d177261dc3e"},"schema_version":"1.0"},"canonical_sha256":"76218e5423d5efeb70ec85813721bd25e14b8575e9a91ca1ed43c9f83eb397dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:03.961547Z","signature_b64":"UkvgXHMZSBjwly8zfA9A7hpiH5Zx5js+RTCUjOw1DFndK636dxMrWMTtHOdVtcjpTtp+6bDWTlSMzHUT2xacDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76218e5423d5efeb70ec85813721bd25e14b8575e9a91ca1ed43c9f83eb397dd","last_reissued_at":"2026-07-05T12:07:03.961148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:03.961148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.10781","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":"2026-07-05T12:07:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vv3lKipLT4Z9gumqkgZpklE9ErBxov4UaNZUZdK2ouc+r3tXlmvLTniSTrmNXnJogqdfOeSbHmRmubMtCcf/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:14:55.393996Z"},"content_sha256":"e5934277fa6dab7bbde14311f8f8a863aafd1bf7c821e7d6fcf10a017a5fa3f2","schema_version":"1.0","event_id":"sha256:e5934277fa6dab7bbde14311f8f8a863aafd1bf7c821e7d6fcf10a017a5fa3f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OYQY4VBD2XX6W4HMQWATOIN5EX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large-scale Pre-training for Grounded Video Caption Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cordelia Schmid, Evangelos Kazakos, Josef Sivic","submitted_at":"2025-03-13T18:21:07Z","abstract_excerpt":"We propose a novel approach for captioning and object grounding in video, where the objects in the caption are grounded in the video via temporally dense bounding boxes. We introduce the following contributions. First, we present a large-scale automatic annotation method that aggregates frame-level captions grounded with bounding boxes into temporally dense and consistent annotations. We apply this approach on the HowTo100M dataset to construct a large-scale pre-training dataset, named HowToGround1M. We also introduce a Grounded Video Caption Generation model, dubbed GROVE, and pre-train the m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10781","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/2503.10781/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":"2026-07-05T12:07:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NqByqX/fMVcJsNi7NOTs8dDeN9jmzExUU4zcfTeaQb33nJf/NmiGzAmoh4hUGgY5wYoULnvehzFF9TeNSKx+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:14:55.394471Z"},"content_sha256":"2b7e04a2e4d14c94b1a77a20bee81ce098fa370e680a93f14a088e5cd63a1505","schema_version":"1.0","event_id":"sha256:2b7e04a2e4d14c94b1a77a20bee81ce098fa370e680a93f14a088e5cd63a1505"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OYQY4VBD2XX6W4HMQWATOIN5EX/bundle.json","state_url":"https://pith.science/pith/OYQY4VBD2XX6W4HMQWATOIN5EX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OYQY4VBD2XX6W4HMQWATOIN5EX/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":"2026-08-06T02:14:55Z","links":{"resolver":"https://pith.science/pith/OYQY4VBD2XX6W4HMQWATOIN5EX","bundle":"https://pith.science/pith/OYQY4VBD2XX6W4HMQWATOIN5EX/bundle.json","state":"https://pith.science/pith/OYQY4VBD2XX6W4HMQWATOIN5EX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OYQY4VBD2XX6W4HMQWATOIN5EX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OYQY4VBD2XX6W4HMQWATOIN5EX","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":"c8e636a25ea9ce80c8b4ecbbf1af7c354361301345bf64938f694d177261dc3e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T18:21:07Z","title_canon_sha256":"83071162112298aaf985ee46a64c775af02023e17cc0d1b7f5fd20faa916ba55"},"schema_version":"1.0","source":{"id":"2503.10781","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10781","created_at":"2026-07-05T12:07:03Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10781v3","created_at":"2026-07-05T12:07:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10781","created_at":"2026-07-05T12:07:03Z"},{"alias_kind":"pith_short_12","alias_value":"OYQY4VBD2XX6","created_at":"2026-07-05T12:07:03Z"},{"alias_kind":"pith_short_16","alias_value":"OYQY4VBD2XX6W4HM","created_at":"2026-07-05T12:07:03Z"},{"alias_kind":"pith_short_8","alias_value":"OYQY4VBD","created_at":"2026-07-05T12:07:03Z"}],"graph_snapshots":[{"event_id":"sha256:2b7e04a2e4d14c94b1a77a20bee81ce098fa370e680a93f14a088e5cd63a1505","target":"graph","created_at":"2026-07-05T12:07:03Z","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/2503.10781/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel approach for captioning and object grounding in video, where the objects in the caption are grounded in the video via temporally dense bounding boxes. We introduce the following contributions. First, we present a large-scale automatic annotation method that aggregates frame-level captions grounded with bounding boxes into temporally dense and consistent annotations. We apply this approach on the HowTo100M dataset to construct a large-scale pre-training dataset, named HowToGround1M. We also introduce a Grounded Video Caption Generation model, dubbed GROVE, and pre-train the m","authors_text":"Cordelia Schmid, Evangelos Kazakos, Josef Sivic","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T18:21:07Z","title":"Large-scale Pre-training for Grounded Video Caption Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10781","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:e5934277fa6dab7bbde14311f8f8a863aafd1bf7c821e7d6fcf10a017a5fa3f2","target":"record","created_at":"2026-07-05T12:07:03Z","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":"c8e636a25ea9ce80c8b4ecbbf1af7c354361301345bf64938f694d177261dc3e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T18:21:07Z","title_canon_sha256":"83071162112298aaf985ee46a64c775af02023e17cc0d1b7f5fd20faa916ba55"},"schema_version":"1.0","source":{"id":"2503.10781","kind":"arxiv","version":3}},"canonical_sha256":"76218e5423d5efeb70ec85813721bd25e14b8575e9a91ca1ed43c9f83eb397dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76218e5423d5efeb70ec85813721bd25e14b8575e9a91ca1ed43c9f83eb397dd","first_computed_at":"2026-07-05T12:07:03.961148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:07:03.961148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UkvgXHMZSBjwly8zfA9A7hpiH5Zx5js+RTCUjOw1DFndK636dxMrWMTtHOdVtcjpTtp+6bDWTlSMzHUT2xacDA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:07:03.961547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.10781","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5934277fa6dab7bbde14311f8f8a863aafd1bf7c821e7d6fcf10a017a5fa3f2","sha256:2b7e04a2e4d14c94b1a77a20bee81ce098fa370e680a93f14a088e5cd63a1505"],"state_sha256":"4aa10b52b548acbe869b7a1dc50d4c42b8783bbe8332918cbb78a6b4b434f05e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S6RNDkqcUuG8e/JVT5Ec51gB2iuq5Td7cOaUsMxGNJ6pid15Y73Unrp7uoqMRRjVX/Gbshkr3XrkEwXlzu5zBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:14:55.397878Z","bundle_sha256":"8ba528d01557e9e3398a3d185e2838907972603e5df3a952a0ad3aa4cf99dc5a"}}