{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TPWXXV6KEHKGZPJOFQ4MYSPAIH","short_pith_number":"pith:TPWXXV6K","canonical_record":{"source":{"id":"2405.20648","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T07:30:24Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"abe8c6d234c8bffa15cac04657adc75bd67d4d9e580fd7da74be497f21cadac6","abstract_canon_sha256":"7fe560f641ebee39992ad7028d25bda566609d00f92dd2103dda292d6193a493"},"schema_version":"1.0"},"canonical_sha256":"9bed7bd7ca21d46cbd2e2c38cc49e041dcf93ca1a3ebd54be35d3ddd2106bcbd","source":{"kind":"arxiv","id":"2405.20648","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20648","created_at":"2026-07-05T09:26:27Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20648v2","created_at":"2026-07-05T09:26:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20648","created_at":"2026-07-05T09:26:27Z"},{"alias_kind":"pith_short_12","alias_value":"TPWXXV6KEHKG","created_at":"2026-07-05T09:26:27Z"},{"alias_kind":"pith_short_16","alias_value":"TPWXXV6KEHKGZPJO","created_at":"2026-07-05T09:26:27Z"},{"alias_kind":"pith_short_8","alias_value":"TPWXXV6K","created_at":"2026-07-05T09:26:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TPWXXV6KEHKGZPJOFQ4MYSPAIH","target":"record","payload":{"canonical_record":{"source":{"id":"2405.20648","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T07:30:24Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"abe8c6d234c8bffa15cac04657adc75bd67d4d9e580fd7da74be497f21cadac6","abstract_canon_sha256":"7fe560f641ebee39992ad7028d25bda566609d00f92dd2103dda292d6193a493"},"schema_version":"1.0"},"canonical_sha256":"9bed7bd7ca21d46cbd2e2c38cc49e041dcf93ca1a3ebd54be35d3ddd2106bcbd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:27.479822Z","signature_b64":"StiKvIQNSyY87YkxZ2maZK0cFQahZrHhS78OWZv2Lr17AV90iyJjU2u+Nb2Wv+K/pB6AuAziL9UaY7KtmjJ8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bed7bd7ca21d46cbd2e2c38cc49e041dcf93ca1a3ebd54be35d3ddd2106bcbd","last_reissued_at":"2026-07-05T09:26:27.479381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:27.479381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.20648","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:26:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GDBoEJRdAAFglzJoyXUgnR/ouHAUb/+MDwb0w9vdJILnOiz6XxEC6HXMqQbdqtTSRdghX/bmsl0LqWu70ur2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:40:13.628104Z"},"content_sha256":"37c05cfdcbd2e485ba2381436b0779b6afb7ade87249d3f8ba2f12b037f49937","schema_version":"1.0","event_id":"sha256:37c05cfdcbd2e485ba2381436b0779b6afb7ade87249d3f8ba2f12b037f49937"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TPWXXV6KEHKGZPJOFQ4MYSPAIH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Shotluck Holmes: A Family of Efficient Small-Scale Large Language Vision Models For Video Captioning and Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Adithya Vasudev, Austin Peng, Richard Luo, Rishabh Jain","submitted_at":"2024-05-31T07:30:24Z","abstract_excerpt":"Video is an increasingly prominent and information-dense medium, yet it poses substantial challenges for language models. A typical video consists of a sequence of shorter segments, or shots, that collectively form a coherent narrative. Each shot is analogous to a word in a sentence where multiple data streams of information (such as visual and auditory data) must be processed simultaneously. Comprehension of the entire video requires not only understanding the visual-audio information of each shot but also requires that the model links the ideas between each shot to generate a larger, all-enc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20648","kind":"arxiv","version":2},"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/2405.20648/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":"2026-07-05T09:26:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OiFnS65apIWQibSGlKcUJWPXwgf4v57Kq8K8yaDMVBeahkbnkhTmn+5aPw8air6V7tfgPbF1NebAVrbyUZ0VBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:40:13.628615Z"},"content_sha256":"96d48d194d1c8f57776eed724fd85301912203bc283aa05c726882210b176e22","schema_version":"1.0","event_id":"sha256:96d48d194d1c8f57776eed724fd85301912203bc283aa05c726882210b176e22"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TPWXXV6KEHKGZPJOFQ4MYSPAIH/bundle.json","state_url":"https://pith.science/pith/TPWXXV6KEHKGZPJOFQ4MYSPAIH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TPWXXV6KEHKGZPJOFQ4MYSPAIH/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":"2026-08-07T05:40:13Z","links":{"resolver":"https://pith.science/pith/TPWXXV6KEHKGZPJOFQ4MYSPAIH","bundle":"https://pith.science/pith/TPWXXV6KEHKGZPJOFQ4MYSPAIH/bundle.json","state":"https://pith.science/pith/TPWXXV6KEHKGZPJOFQ4MYSPAIH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TPWXXV6KEHKGZPJOFQ4MYSPAIH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TPWXXV6KEHKGZPJOFQ4MYSPAIH","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":"7fe560f641ebee39992ad7028d25bda566609d00f92dd2103dda292d6193a493","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T07:30:24Z","title_canon_sha256":"abe8c6d234c8bffa15cac04657adc75bd67d4d9e580fd7da74be497f21cadac6"},"schema_version":"1.0","source":{"id":"2405.20648","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20648","created_at":"2026-07-05T09:26:27Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20648v2","created_at":"2026-07-05T09:26:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20648","created_at":"2026-07-05T09:26:27Z"},{"alias_kind":"pith_short_12","alias_value":"TPWXXV6KEHKG","created_at":"2026-07-05T09:26:27Z"},{"alias_kind":"pith_short_16","alias_value":"TPWXXV6KEHKGZPJO","created_at":"2026-07-05T09:26:27Z"},{"alias_kind":"pith_short_8","alias_value":"TPWXXV6K","created_at":"2026-07-05T09:26:27Z"}],"graph_snapshots":[{"event_id":"sha256:96d48d194d1c8f57776eed724fd85301912203bc283aa05c726882210b176e22","target":"graph","created_at":"2026-07-05T09:26:27Z","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/2405.20648/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video is an increasingly prominent and information-dense medium, yet it poses substantial challenges for language models. A typical video consists of a sequence of shorter segments, or shots, that collectively form a coherent narrative. Each shot is analogous to a word in a sentence where multiple data streams of information (such as visual and auditory data) must be processed simultaneously. Comprehension of the entire video requires not only understanding the visual-audio information of each shot but also requires that the model links the ideas between each shot to generate a larger, all-enc","authors_text":"Adithya Vasudev, Austin Peng, Richard Luo, Rishabh Jain","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T07:30:24Z","title":"Shotluck Holmes: A Family of Efficient Small-Scale Large Language Vision Models For Video Captioning and Summarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20648","kind":"arxiv","version":2},"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":"sha256:37c05cfdcbd2e485ba2381436b0779b6afb7ade87249d3f8ba2f12b037f49937","target":"record","created_at":"2026-07-05T09:26:27Z","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":"7fe560f641ebee39992ad7028d25bda566609d00f92dd2103dda292d6193a493","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T07:30:24Z","title_canon_sha256":"abe8c6d234c8bffa15cac04657adc75bd67d4d9e580fd7da74be497f21cadac6"},"schema_version":"1.0","source":{"id":"2405.20648","kind":"arxiv","version":2}},"canonical_sha256":"9bed7bd7ca21d46cbd2e2c38cc49e041dcf93ca1a3ebd54be35d3ddd2106bcbd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9bed7bd7ca21d46cbd2e2c38cc49e041dcf93ca1a3ebd54be35d3ddd2106bcbd","first_computed_at":"2026-07-05T09:26:27.479381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:26:27.479381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"StiKvIQNSyY87YkxZ2maZK0cFQahZrHhS78OWZv2Lr17AV90iyJjU2u+Nb2Wv+K/pB6AuAziL9UaY7KtmjJ8BA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:26:27.479822Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20648","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37c05cfdcbd2e485ba2381436b0779b6afb7ade87249d3f8ba2f12b037f49937","sha256:96d48d194d1c8f57776eed724fd85301912203bc283aa05c726882210b176e22"],"state_sha256":"79c90db34a1454ac6fe7f9fc7d54ab447cd7ce40ead0c40d4454055aff3844da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q0ZtlnX4PYADg3k2lyVGK9TKwc4n51I9P1rYEndKdx6lf80dUUqfx5CNH+NZRqBF5GVkixl0Sz3WqQSUQuRtCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T05:40:13.633434Z","bundle_sha256":"3f65757a213fc8c992c0213ee840f3ca8d65fc2fb7b8e92a1171faa184551431"}}